Skip to contentSkip to conversation

PowerPC VSX Stage 3

PATCH Superseded Tom Musta 3 participants 31 messages Dec 18, 2013 – Dec 24, 2013

v4 of 5 Superseded Latest is v5 →

lore
Share & tools
lore

Tom Musta

author
#0 lore raw

v4 cover PowerPC VSX Stage 3

This is the third series of patches to add PowerPC VSX emulation support to QEMU.

This series adds the floating point arithmetic, compare, conversion and rounding instructions. Instructions are implemented using helpers and wherever practical, existing floating point code such as the softfloat library and the existing PowerPC floating point helper code.

As with the previous series, the Power ISA V2.06 instructions are added but the V2.07 instructions are not. The latter will be implemented in a future patch series.

V2: Implemented changes based on feedback from Richard Henderson and Peter Maydell:
- Included float64_to_uint64() patch in this series rather than just cite it as a pre-requesite.
- Isolated float32_to_uint64() in its own patch.
- Re-implemented helpers and eliminated the need for some of the proposed softfloat routines (float*_is_denormal, float*_get_unbiased_exp).
- Re-implemented severy helpers so that corner cases (e.g. invalid operations) are detected by softfloat.
- Re-implemented fused multiply-add to use the softfloat muladd routines.
- Re-implemented the min/max instructions to used the softfloat min/max functions.
- assorted style fixes

V3: re-submitting due to patch corruption.

V4: Folded in softfloat bug fixes per Peter Maydell's request.

Tom Musta (22):
softfloat: Fix float64_to_uint64
softfloat: Add float32_to_uint64()
softfloat: Fix float64_to_uint64_round_to_zero
softfloat: Fix float64_to_uint32
softfloat: Fix float64_to_uint32_round_to_zero
target-ppc: Add set_fprf Argument to fload_invalid_op_excp()
target-ppc: General Support for VSX Helpers
target-ppc: Add VSX ISA2.06 xadd/xsub Instructions
target-ppc: Add VSX ISA2.06 xmul Instructions
target-ppc: Add VSX ISA2.06 xdiv Instructions
target-ppc: Add VSX ISA2.06 xre Instructions
target-ppc: Add VSX ISA2.06 xsqrt Instructions
target-ppc: Add VSX ISA2.06 xrsqrte Instructions
target-ppc: Add VSX ISA2.06 xtdiv Instructions
target-ppc: Add VSX ISA2.06 xtsqrt Instructions
target-ppc: Add VSX ISA2.06 Multiply Add Instructions
target-ppc: Add VSX xscmp*dp Instructions
target-ppc: Add VSX xmax/xmin Instructions
target-ppc: Add VSX Vector Compare Instructions
target-ppc: Add VSX Floating Point to Floating Point Conversion
Instructions
target-ppc: Add VSX ISA2.06 Integer Conversion Instructions
target-ppc: Add VSX Rounding Instructions

 fpu/softfloat.c         |  185 +++++++--
 include/fpu/softfloat.h |    1 +
 target-ppc/fpu_helper.c | 1002 ++++++++++++++++++++++++++++++++++++++++++++---
 target-ppc/helper.h     |  109 +++++
 target-ppc/translate.c  |  243 ++++++++++++
 5 files changed, 1460 insertions(+), 80 deletions(-)
author
#1 lore raw

PATCH v4 1/22 softfloat: Fix float64_to_uint64

The comment preceding the float64_to_uint64 routine suggests that the implementation is broken. And this is, indeed, the case.

This patch properly implements the conversion of a 64-bit floating point number to an unsigned, 64 bit integer.

This contribution can be licensed under either the softfloat-2a or -2b license.

V2: Added softfloat license statement.

V3: Modified to meet QEMU coding conventions.

V4: Fixed incorrect handling of small negatives, which, if rounded up to zero should not set the inexact flag.

---
 fpu/softfloat.c |   98 +++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 files changed, 89 insertions(+), 9 deletions(-)
fpu/softfloat.c +89 -9
index dbda61b..ec23908 100644
@@ -161,7 +161,6 @@ static int32 roundAndPackInt32( flag zSign, uint64_t absZ STATUS_PARAM)
 | exception is raised and the largest positive or negative integer is
 | returned.
 *----------------------------------------------------------------------------*/
-
 static int64 roundAndPackInt64( flag zSign, uint64_t absZ0, uint64_t absZ1 STATUS_PARAM)
 {
     int8 roundingMode;
@@ -204,6 +203,56 @@ static int64 roundAndPackInt64( flag zSign, uint64_t absZ0, uint64_t absZ1 STATU
 }
 
 /*----------------------------------------------------------------------------
+| Takes the 128-bit fixed-point value formed by concatenating `absZ0' and
+| `absZ1', with binary point between bits 63 and 64 (between the input words),
+| and returns the properly rounded 64-bit unsigned integer corresponding to the
+| input.  Ordinarily, the fixed-point input is simply rounded to an integer,
+| with the inexact exception raised if the input cannot be represented exactly
+| as an integer.  However, if the fixed-point input is too large, the invalid
+| exception is raised and the largest unsigned integer is returned.
+*----------------------------------------------------------------------------*/
+
+static int64 roundAndPackUint64(flag zSign, uint64_t absZ0,
+                                uint64_t absZ1 STATUS_PARAM)
+{
+    int8 roundingMode;
+    flag roundNearestEven, increment;
+
+    roundingMode = STATUS(float_rounding_mode);
+    roundNearestEven = (roundingMode == float_round_nearest_even);
+    increment = ((int64_t)absZ1 < 0);
+    if (!roundNearestEven) {
+        if (roundingMode == float_round_to_zero) {
+            increment = 0;
+        } else if (absZ1) {
+            if (zSign) {
+                increment = (roundingMode == float_round_down) && absZ1;
+            } else {
+                increment = (roundingMode == float_round_up) && absZ1;
+            }
+        }
+    }
+    if (increment) {
+        ++absZ0;
+        if (absZ0 == 0) {
+            float_raise(float_flag_invalid STATUS_VAR);
+            return LIT64(0xFFFFFFFFFFFFFFFF);
+        }
+        absZ0 &= ~(((uint64_t)(absZ1<<1) == 0) & roundNearestEven);
+    }
+
+    if (zSign && absZ0) {
+        float_raise(float_flag_invalid STATUS_VAR);
+        return 0;
+    }
+
+    if (absZ1) {
+        STATUS(float_exception_flags) |= float_flag_inexact;
+    }
+    return absZ0;
+}
+
+/*----------------------------------------------------------------------------
 | Returns the fraction bits of the single-precision floating-point value `a'.
 *----------------------------------------------------------------------------*/
 
@@ -6536,18 +6585,49 @@ uint_fast16_t float64_to_uint16_round_to_zero(float64 a STATUS_PARAM)
     return res;
 }
 
-/* FIXME: This looks broken.  */
-uint64_t float64_to_uint64 (float64 a STATUS_PARAM)
-{
-    int64_t v;
+/*----------------------------------------------------------------------------
+| Returns the result of converting the double-precision floating-point value
+| `a' to the 64-bit unsigned integer format.  The conversion is
+| performed according to the IEC/IEEE Standard for Binary Floating-Point
+| Arithmetic---which means in particular that the conversion is rounded
+| according to the current rounding mode.  If `a' is a NaN, the largest
+| positive integer is returned.  If the conversion overflows, the
+| largest unsigned integer is returned.  If 'a' is negative, zero is
+| returned.
+*----------------------------------------------------------------------------*/
 
-    v = float64_val(int64_to_float64(INT64_MIN STATUS_VAR));
-    v += float64_val(a);
-    v = float64_to_int64(make_float64(v) STATUS_VAR);
+uint64_t float64_to_uint64(float64 a STATUS_PARAM)
+{
+    flag aSign;
+    int_fast16_t aExp, shiftCount;
+    uint64_t aSig, aSigExtra;
+    a = float64_squash_input_denormal(a STATUS_VAR);
 
-    return v - INT64_MIN;
+    aSig = extractFloat64Frac(a);
+    aExp = extractFloat64Exp(a);
+    aSign = extractFloat64Sign(a);
+    if (aSign && (aExp > 1022)) {
+        float_raise(float_flag_invalid STATUS_VAR);
+        return 0;
+    }
+    if (aExp) {
+        aSig |= LIT64(0x0010000000000000);
+    }
+    shiftCount = 0x433 - aExp;
+    if (shiftCount <= 0) {
+        if (0x43E < aExp) {
+            float_raise(float_flag_invalid STATUS_VAR);
+            return LIT64(0xFFFFFFFFFFFFFFFF);
+        }
+        aSigExtra = 0;
+        aSig <<= -shiftCount;
+    } else {
+        shift64ExtraRightJamming(aSig, 0, shiftCount, &aSig, &aSigExtra);
+    }
+    return roundAndPackUint64(aSign, aSig, aSigExtra STATUS_VAR);
 }
 
+
 uint64_t float64_to_uint64_round_to_zero (float64 a STATUS_PARAM)
 {
     int64_t v;
Signature · 1 line
1.7.1
#2 lore raw

Re: [Qemu-devel] [V4 PATCH 01/22] softfloat: Fix float64_to_uint64

Quoted 35 lines · Tom Musta

The comment preceding the float64_to_uint64 routine suggests that the implementation is broken. And this is, indeed, the case.

This patch properly implements the conversion of a 64-bit floating point number to an unsigned, 64 bit integer.

This contribution can be licensed under either the softfloat-2a or -2b license.

V2: Added softfloat license statement.

V3: Modified to meet QEMU coding conventions.

V4: Fixed incorrect handling of small negatives, which, if rounded up to zero should not set the inexact flag.

---
 fpu/softfloat.c |   98 +++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 files changed, 89 insertions(+), 9 deletions(-)
fpu/softfloat.c +0 -1
index dbda61b..ec23908 100644
@@ -161,7 +161,6 @@ static int32 roundAndPackInt32( flag zSign, uint64_t absZ STATUS_PARAM)
 | exception is raised and the largest positive or negative integer is
 | returned.
 *----------------------------------------------------------------------------*/
-
 static int64 roundAndPackInt64( flag zSign, uint64_t absZ0, uint64_t absZ1 STATUS_PARAM)
 {
     int8 roundingMode;
@@ -204,6 +203,56 @@ static int64 roundAndPackInt64( flag zSign, uint64_t absZ0, uint64_t absZ1 STATU
 }

fpu/softfloat.c static int64 roundAndPackInt64( flag zSign, uint64_t absZ0, uint64_t absZ1 STATU · line 213

Quoted 10 lines
fpu/softfloat.c +8 -0
 
 /*----------------------------------------------------------------------------
+| Takes the 128-bit fixed-point value formed by concatenating `absZ0' and
+| `absZ1', with binary point between bits 63 and 64 (between the input words),
+| and returns the properly rounded 64-bit unsigned integer corresponding to the
+| input.  Ordinarily, the fixed-point input is simply rounded to an integer,
+| with the inexact exception raised if the input cannot be represented exactly
+| as an integer.  However, if the fixed-point input is too large, the invalid
+| exception is raised and the largest unsigned integer is returned.
+*----------------------------------------------------------------------------*/

You should probably say in this comment what the behaviour is for negative inputs.

Quoted 4 lines
fpu/softfloat.c +4 -0
+uint64_t float64_to_uint64(float64 a STATUS_PARAM)
+{
+    flag aSign;
+    int_fast16_t aExp, shiftCount;

fpu/softfloat.c uint_fast16_t float64_to_uint16_round_to_zero(float64 a STATUS_PARAM) · line 6611

Quoted 10 lines
fpu/softfloat.c +8 -1
+    uint64_t aSig, aSigExtra;
+    a = float64_squash_input_denormal(a STATUS_VAR);
 
-    return v - INT64_MIN;
+    aSig = extractFloat64Frac(a);
+    aExp = extractFloat64Exp(a);
+    aSign = extractFloat64Sign(a);
+    if (aSign && (aExp > 1022)) {
+        float_raise(float_flag_invalid STATUS_VAR);
+        return 0;

This incorrectly returns 0 rather than largest-positive-integer for NaNs with the sign bit set.

Quoted 7 lines
fpu/softfloat.c +7 -0
+    }
+    if (aExp) {
+        aSig |= LIT64(0x0010000000000000);
+    }
+    shiftCount = 0x433 - aExp;
+    if (shiftCount <= 0) {
+        if (0x43E < aExp) {

fpu/softfloat.c uint_fast16_t float64_to_uint16_round_to_zero(float64 a STATUS_PARAM) · line 6628

Quoted 10 lines
fpu/softfloat.c +9 -0
+            float_raise(float_flag_invalid STATUS_VAR);
+            return LIT64(0xFFFFFFFFFFFFFFFF);
+        }
+        aSigExtra = 0;
+        aSig <<= -shiftCount;
+    } else {
+        shift64ExtraRightJamming(aSig, 0, shiftCount, &aSig, &aSigExtra);
+    }
+    return roundAndPackUint64(aSign, aSig, aSigExtra STATUS_VAR);
 }

Other than that, the code *looks* OK, but it's really easy for "not quite right" code to slip through here (especially on corner cases like NaNs, denormals and odd rounding modes). How much testing have you given this? I really recommend testing by firing a huge pile of random (and semi random) test vectors at whatever guest instruction you're implementing and comparing against results on reference hardware.

thanks
-- PMM

author
#3 lore raw

Re: [Qemu-devel] [Qemu-ppc] [V4 PATCH 01/22] softfloat: Fix float64_to_uint64

Quoted 94 lines · Peter Maydell
Quoted 35 lines · Tom Musta

The comment preceding the float64_to_uint64 routine suggests that the implementation is broken. And this is, indeed, the case.

This patch properly implements the conversion of a 64-bit floating point number to an unsigned, 64 bit integer.

This contribution can be licensed under either the softfloat-2a or -2b license.

V2: Added softfloat license statement.

V3: Modified to meet QEMU coding conventions.

V4: Fixed incorrect handling of small negatives, which, if rounded up to zero should not set the inexact flag.

---
 fpu/softfloat.c |   98 +++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 files changed, 89 insertions(+), 9 deletions(-)
fpu/softfloat.c +0 -1
index dbda61b..ec23908 100644
@@ -161,7 +161,6 @@ static int32 roundAndPackInt32( flag zSign, uint64_t absZ STATUS_PARAM)
 | exception is raised and the largest positive or negative integer is
 | returned.
 *----------------------------------------------------------------------------*/
-
 static int64 roundAndPackInt64( flag zSign, uint64_t absZ0, uint64_t absZ1 STATUS_PARAM)
 {
     int8 roundingMode;
@@ -204,6 +203,56 @@ static int64 roundAndPackInt64( flag zSign, uint64_t absZ0, uint64_t absZ1 STATU
 }

fpu/softfloat.c static int64 roundAndPackInt64( flag zSign, uint64_t absZ0, uint64_t absZ1 STATU · line 213

Quoted 10 lines
fpu/softfloat.c +8 -0
 
 /*----------------------------------------------------------------------------
+| Takes the 128-bit fixed-point value formed by concatenating `absZ0' and
+| `absZ1', with binary point between bits 63 and 64 (between the input words),
+| and returns the properly rounded 64-bit unsigned integer corresponding to the
+| input.  Ordinarily, the fixed-point input is simply rounded to an integer,
+| with the inexact exception raised if the input cannot be represented exactly
+| as an integer.  However, if the fixed-point input is too large, the invalid
+| exception is raised and the largest unsigned integer is returned.
+*----------------------------------------------------------------------------*/

You should probably say in this comment what the behaviour is for negative inputs.

Quoted 4 lines
fpu/softfloat.c +4 -0
+uint64_t float64_to_uint64(float64 a STATUS_PARAM)
+{
+    flag aSign;
+    int_fast16_t aExp, shiftCount;

fpu/softfloat.c uint_fast16_t float64_to_uint16_round_to_zero(float64 a STATUS_PARAM) · line 6611

Quoted 10 lines
fpu/softfloat.c +8 -1
+    uint64_t aSig, aSigExtra;
+    a = float64_squash_input_denormal(a STATUS_VAR);
 
-    return v - INT64_MIN;
+    aSig = extractFloat64Frac(a);
+    aExp = extractFloat64Exp(a);
+    aSign = extractFloat64Sign(a);
+    if (aSign && (aExp > 1022)) {
+        float_raise(float_flag_invalid STATUS_VAR);
+        return 0;

This incorrectly returns 0 rather than largest-positive-integer for NaNs with the sign bit set.

Quoted 7 lines
fpu/softfloat.c +7 -0
+    }
+    if (aExp) {
+        aSig |= LIT64(0x0010000000000000);
+    }
+    shiftCount = 0x433 - aExp;
+    if (shiftCount <= 0) {
+        if (0x43E < aExp) {

fpu/softfloat.c uint_fast16_t float64_to_uint16_round_to_zero(float64 a STATUS_PARAM) · line 6628

Quoted 10 lines
fpu/softfloat.c +9 -0
+            float_raise(float_flag_invalid STATUS_VAR);
+            return LIT64(0xFFFFFFFFFFFFFFFF);
+        }
+        aSigExtra = 0;
+        aSig <<= -shiftCount;
+    } else {
+        shift64ExtraRightJamming(aSig, 0, shiftCount, &aSig, &aSigExtra);
+    }
+    return roundAndPackUint64(aSign, aSig, aSigExtra STATUS_VAR);
 }

Other than that, the code *looks* OK, but it's really easy for "not quite right" code to slip through here (especially on corner cases like NaNs, denormals and odd rounding modes). How much testing have you given this? I really recommend testing by firing a huge pile of random (and semi random) test vectors at whatever guest instruction you're implementing and comparing against results on reference hardware.

Quoted 3 lines

thanks
-- PMM

Peter:

I agree with the comments and also with the bug. I will fix.

I do test like you said ... random patterns with some biasing to try to get into corner cases. The bug you found was masked in the PowerPC code that wrapped to call to float64_to_uint64. I have constructed a variant of my test harness that invokes float64_to_uint64 directly and it has uncovered the bug.

author
#4 lore raw

PATCH v4 2/22 softfloat: Add float32_to_uint64()

In reply to Tom Musta

This patch adds the float32_to_uint64() routine, which converts a 32-bit floating point number to an unsigned 64 bit number.

This contribution can be licensed under either the softfloat-2a or -2b license.

V2: Reduced patch to just this single routine per feedback from Peter Maydell.

V4: Now passing sign to roundAndPackUint64()

---
 fpu/softfloat.c         |   45 +++++++++++++++++++++++++++++++++++++++++++++
 include/fpu/softfloat.h |    1 +
 2 files changed, 46 insertions(+), 0 deletions(-)
fpu/softfloat.c +45 -0
index ec23908..1ff59d0 100644
@@ -1558,6 +1558,51 @@ int64 float32_to_int64( float32 a STATUS_PARAM )
 
 /*----------------------------------------------------------------------------
 | Returns the result of converting the single-precision floating-point value
+| `a' to the 64-bit unsigned integer format.  The conversion is
+| performed according to the IEC/IEEE Standard for Binary Floating-Point
+| Arithmetic---which means in particular that the conversion is rounded
+| according to the current rounding mode.  If `a' is a NaN, the largest
+| unsigned integer is returned.  Otherwise, if the conversion overflows, the
+| largest unsigned integer is returned.  If the 'a' is negative, zero is
+| returned.
+*----------------------------------------------------------------------------*/
+
+uint64 float32_to_uint64(float32 a STATUS_PARAM)
+{
+    flag aSign;
+    int_fast16_t aExp, shiftCount;
+    uint32_t aSig;
+    uint64_t aSig64, aSigExtra;
+    a = float32_squash_input_denormal(a STATUS_VAR);
+
+    aSig = extractFloat32Frac(a);
+    aExp = extractFloat32Exp(a);
+    aSign = extractFloat32Sign(a);
+    if (aSign) {
+        if (aExp) {
+            float_raise(float_flag_invalid STATUS_VAR);
+        } else if (aSig) { /* negative denormalized */
+            float_raise(float_flag_inexact STATUS_VAR);
+        }
+        return 0;
+    }
+    shiftCount = 0xBE - aExp;
+    if (aExp) {
+        aSig |= 0x00800000;
+    }
+    if (shiftCount < 0) {
+        float_raise(float_flag_invalid STATUS_VAR);
+        return (int64_t)LIT64(0xFFFFFFFFFFFFFFFF);
+    }
+
+    aSig64 = aSig;
+    aSig64 <<= 40;
+    shift64ExtraRightJamming(aSig64, 0, shiftCount, &aSig64, &aSigExtra);
+    return roundAndPackUint64(aSign, aSig64, aSigExtra STATUS_VAR);
+}
+
+/*----------------------------------------------------------------------------
+| Returns the result of converting the single-precision floating-point value
 | `a' to the 64-bit two's complement integer format.  The conversion is
 | performed according to the IEC/IEEE Standard for Binary Floating-Point
 | Arithmetic, except that the conversion is always rounded toward zero.  If
include/fpu/softfloat.h +1 -0
index 2365274..080b36d 100644
@@ -272,6 +272,7 @@ int32 float32_to_int32_round_to_zero( float32 STATUS_PARAM );
 uint32 float32_to_uint32( float32 STATUS_PARAM );
 uint32 float32_to_uint32_round_to_zero( float32 STATUS_PARAM );
 int64 float32_to_int64( float32 STATUS_PARAM );
+uint64 float32_to_uint64(float32 STATUS_PARAM);
 int64 float32_to_int64_round_to_zero( float32 STATUS_PARAM );
 float64 float32_to_float64( float32 STATUS_PARAM );
 floatx80 float32_to_floatx80( float32 STATUS_PARAM );
Signature · 1 line
1.7.1
#5 lore raw

Re: [Qemu-devel] [V4 PATCH 02/22] softfloat: Add float32_to_uint64()

Quoted 38 lines · Tom Musta

This patch adds the float32_to_uint64() routine, which converts a 32-bit floating point number to an unsigned 64 bit number.

This contribution can be licensed under either the softfloat-2a or -2b license.

V2: Reduced patch to just this single routine per feedback from Peter Maydell.

V4: Now passing sign to roundAndPackUint64()

---
 fpu/softfloat.c         |   45 +++++++++++++++++++++++++++++++++++++++++++++
 include/fpu/softfloat.h |    1 +
 2 files changed, 46 insertions(+), 0 deletions(-)
fpu/softfloat.c +13 -0
index ec23908..1ff59d0 100644
@@ -1558,6 +1558,51 @@ int64 float32_to_int64( float32 a STATUS_PARAM )
 
 /*----------------------------------------------------------------------------
 | Returns the result of converting the single-precision floating-point value
+| `a' to the 64-bit unsigned integer format.  The conversion is
+| performed according to the IEC/IEEE Standard for Binary Floating-Point
+| Arithmetic---which means in particular that the conversion is rounded
+| according to the current rounding mode.  If `a' is a NaN, the largest
+| unsigned integer is returned.  Otherwise, if the conversion overflows, the
+| largest unsigned integer is returned.  If the 'a' is negative, zero is
+| returned.
+*----------------------------------------------------------------------------*/
+
+uint64 float32_to_uint64(float32 a STATUS_PARAM)
+{
+    flag aSign;
+    int_fast16_t aExp, shiftCount;

fpu/softfloat.c int64 float32_to_int64( float32 a STATUS_PARAM ) · line 1583

Quoted 10 lines
fpu/softfloat.c +10 -0
+    uint32_t aSig;
+    uint64_t aSig64, aSigExtra;
+    a = float32_squash_input_denormal(a STATUS_VAR);
+
+    aSig = extractFloat32Frac(a);
+    aExp = extractFloat32Exp(a);
+    aSign = extractFloat32Sign(a);
+    if (aSign) {
+        if (aExp) {
+            float_raise(float_flag_invalid STATUS_VAR);

NaNs with the sign bit set will wind up in this case and return 0 rather than largest-unsigned-integer.

Also it seems like this code says "negative inputs return zero if they're denormal or signal Invalid and return 0 if they're not". Are you sure this does the right thing for
(a) values which are not denormal but are close enough to zero to round to it and (b) different rounding modes?

Quoted 9 lines
fpu/softfloat.c +9 -0
+        } else if (aSig) { /* negative denormalized */
+            float_raise(float_flag_inexact STATUS_VAR);
+        }
+        return 0;
+    }
+    shiftCount = 0xBE - aExp;
+    if (aExp) {
+        aSig |= 0x00800000;
+    }

fpu/softfloat.c int64 float32_to_int64( float32 a STATUS_PARAM ) · line 1602

Quoted 10 lines
fpu/softfloat.c +10 -0
+    if (shiftCount < 0) {
+        float_raise(float_flag_invalid STATUS_VAR);
+        return (int64_t)LIT64(0xFFFFFFFFFFFFFFFF);
+    }
+
+    aSig64 = aSig;
+    aSig64 <<= 40;
+    shift64ExtraRightJamming(aSig64, 0, shiftCount, &aSig64, &aSigExtra);
+    return roundAndPackUint64(aSign, aSig64, aSigExtra STATUS_VAR);
+}

thanks
-- PMM

author
#6 lore raw

Re: [Qemu-devel] [V4 PATCH 02/22] softfloat: Add float32_to_uint64()

Quoted 73 lines · Peter Maydell
Quoted 38 lines · Tom Musta

This patch adds the float32_to_uint64() routine, which converts a 32-bit floating point number to an unsigned 64 bit number.

This contribution can be licensed under either the softfloat-2a or -2b license.

V2: Reduced patch to just this single routine per feedback from Peter Maydell.

V4: Now passing sign to roundAndPackUint64()

---
 fpu/softfloat.c         |   45 +++++++++++++++++++++++++++++++++++++++++++++
 include/fpu/softfloat.h |    1 +
 2 files changed, 46 insertions(+), 0 deletions(-)
fpu/softfloat.c +13 -0
index ec23908..1ff59d0 100644
@@ -1558,6 +1558,51 @@ int64 float32_to_int64( float32 a STATUS_PARAM )
 
 /*----------------------------------------------------------------------------
 | Returns the result of converting the single-precision floating-point value
+| `a' to the 64-bit unsigned integer format.  The conversion is
+| performed according to the IEC/IEEE Standard for Binary Floating-Point
+| Arithmetic---which means in particular that the conversion is rounded
+| according to the current rounding mode.  If `a' is a NaN, the largest
+| unsigned integer is returned.  Otherwise, if the conversion overflows, the
+| largest unsigned integer is returned.  If the 'a' is negative, zero is
+| returned.
+*----------------------------------------------------------------------------*/
+
+uint64 float32_to_uint64(float32 a STATUS_PARAM)
+{
+    flag aSign;
+    int_fast16_t aExp, shiftCount;

fpu/softfloat.c int64 float32_to_int64( float32 a STATUS_PARAM ) · line 1583

Quoted 10 lines
fpu/softfloat.c +10 -0
+    uint32_t aSig;
+    uint64_t aSig64, aSigExtra;
+    a = float32_squash_input_denormal(a STATUS_VAR);
+
+    aSig = extractFloat32Frac(a);
+    aExp = extractFloat32Exp(a);
+    aSign = extractFloat32Sign(a);
+    if (aSign) {
+        if (aExp) {
+            float_raise(float_flag_invalid STATUS_VAR);

NaNs with the sign bit set will wind up in this case and return 0 rather than largest-unsigned-integer.

Also it seems like this code says "negative inputs return zero if they're denormal or signal Invalid and return 0 if they're not". Are you sure this does the right thing for
(a) values which are not denormal but are close enough to zero to round to it and (b) different rounding modes?

Quoted 14 lines
fpu/softfloat.c +14 -0
+        } else if (aSig) { /* negative denormalized */
+            float_raise(float_flag_inexact STATUS_VAR);
+        }
+        return 0;
+    }
+    shiftCount = 0xBE - aExp;
+    if (aExp) {
+        aSig |= 0x00800000;
+    }
+    if (shiftCount < 0) {
+        float_raise(float_flag_invalid STATUS_VAR);
+        return (int64_t)LIT64(0xFFFFFFFFFFFFFFFF);
+    }
+
Quoted 9 lines

fpu/softfloat.c int64 float32_to_int64( float32 a STATUS_PARAM ) · line 1602

Quoted 5 lines
fpu/softfloat.c +5 -0
+    aSig64 = aSig;
+    aSig64 <<= 40;
+    shift64ExtraRightJamming(aSig64, 0, shiftCount, &aSig64, &aSigExtra);
+    return roundAndPackUint64(aSign, aSig64, aSigExtra STATUS_VAR);
+}

thanks
-- PMM

Peter: I agree ... this still isn't quite right.

author
#7 lore raw

PATCH v4 3/22 softfloat: Fix float64_to_uint64_round_to_zero

In reply to Tom Musta

The float64_to_uint64_round_to_zero routine is incorrect.

For example, the following test pattern:

    46697351FF4AEC29 / 0x1.97351ff4aec29p+103

currently produces 8000000000000000 instead of FFFFFFFFFFFFFFFF.

This patch re-implements the routine to temporarily force the rounding mode and use the float64_to_uint64 routine.

This contribution can be licensed under either the softfloat-2a or -2b license.

---
 fpu/softfloat.c |   12 +++++-------
 1 files changed, 5 insertions(+), 7 deletions(-)
fpu/softfloat.c +5 -7
index 1ff59d0..1b614ae 100644
@@ -6675,13 +6675,11 @@ uint64_t float64_to_uint64(float64 a STATUS_PARAM)
 
 uint64_t float64_to_uint64_round_to_zero (float64 a STATUS_PARAM)
 {
-    int64_t v;
-
-    v = float64_val(int64_to_float64(INT64_MIN STATUS_VAR));
-    v += float64_val(a);
-    v = float64_to_int64_round_to_zero(make_float64(v) STATUS_VAR);
-
-    return v - INT64_MIN;
+    signed char current_rounding_mode = STATUS(float_rounding_mode);
+    set_float_rounding_mode(float_round_to_zero STATUS_VAR);
+    int64_t v = float64_to_uint64(a STATUS_VAR);
+    set_float_rounding_mode(current_rounding_mode STATUS_VAR);
+    return v;
 }
 
 #define COMPARE(s, nan_exp)                                                  \
Signature · 1 line
1.7.1
Reviewed-by on v4 3/22
#8 lore raw

Re: [Qemu-devel] [V4 PATCH 03/22] softfloat: Fix float64_to_uint64_round_to_zero

Quoted 8 lines · Tom Musta

The float64_to_uint64_round_to_zero routine is incorrect.

For example, the following test pattern:

    46697351FF4AEC29 / 0x1.97351ff4aec29p+103

currently produces 8000000000000000 instead of FFFFFFFFFFFFFFFF.

Quoted 7 lines

This patch re-implements the routine to temporarily force the rounding mode and use the float64_to_uint64 routine.

This contribution can be licensed under either the softfloat-2a or -2b license.

The other approach would be to make all the conversion functions explicitly take the rounding mode parameter (and in some ways that might be closer to the set of functionality IEE754-2008 describes), but this is a simple change and saving and restoring rounding mode is very cheap.

thanks
-- PMM

author
#9 lore raw

PATCH v4 4/22 softfloat: Fix float64_to_uint32

In reply to Tom Musta

The float64_to_uint32 has several flaws:

- for numbers between 2**32 and 2**64, the inexact exception flag may get incorrectly set. In this case, only the invalid flag should be set.

       test pattern: 425F81378DC0CD1F / 0x1.f81378dc0cd1fp+38

- for numbers between 2**63 and 2**64, incorrect results may be produced:

       test pattern: 43EAAF73F1F0B8BD / 0x1.aaf73f1f0b8bdp+63

This patch re-implements float64_to_uint32 to re-use the float64_to_uint64 routine (instead of float64_to_int64). For the saturation case, the inexact bit is explicitly cleared before raising the invalid flag, provided that it was not previously set.

V4: Fixed handling of stickiness of the inexact bit per comments from Peter Maydell.

This contribution can be licensed under either the softfloat-2a or -2b license.

---
 fpu/softfloat.c |   15 +++++++--------
 1 files changed, 7 insertions(+), 8 deletions(-)
fpu/softfloat.c +7 -8
index 1b614ae..6110e28 100644
@@ -6578,19 +6578,18 @@ uint_fast16_t float32_to_uint16_round_to_zero(float32 a STATUS_PARAM)
 
 uint32 float64_to_uint32( float64 a STATUS_PARAM )
 {
-    int64_t v;
+    uint64_t v;
     uint32 res;
+    int old_exc_flags = get_float_exception_flags(status);
 
-    v = float64_to_int64(a STATUS_VAR);
-    if (v < 0) {
-        res = 0;
-        float_raise( float_flag_invalid STATUS_VAR);
-    } else if (v > 0xffffffff) {
+    v = float64_to_uint64(a STATUS_VAR);
+    if (v > 0xffffffff) {
         res = 0xffffffff;
-        float_raise( float_flag_invalid STATUS_VAR);
     } else {
-        res = v;
+        return v;
     }
+    set_float_exception_flags(old_exc_flags, status);
+    float_raise(float_flag_invalid STATUS_VAR);
     return res;
 }
 
Signature · 1 line
1.7.1
Reviewed-by on v4 4/22
#10 lore raw

Re: [Qemu-devel] [V4 PATCH 04/22] softfloat: Fix float64_to_uint32

Quoted 18 lines · Tom Musta

The float64_to_uint32 has several flaws:

- for numbers between 2**32 and 2**64, the inexact exception flag may get incorrectly set. In this case, only the invalid flag should be set.

       test pattern: 425F81378DC0CD1F / 0x1.f81378dc0cd1fp+38

- for numbers between 2**63 and 2**64, incorrect results may be produced:

       test pattern: 43EAAF73F1F0B8BD / 0x1.aaf73f1f0b8bdp+63

This patch re-implements float64_to_uint32 to re-use the float64_to_uint64 routine (instead of float64_to_int64). For the saturation case, the inexact bit is explicitly cleared before raising the invalid flag, provided that it was not previously set.

Quoted 7 lines

V4: Fixed handling of stickiness of the inexact bit per comments from Peter Maydell.

This contribution can be licensed under either the softfloat-2a or -2b license.

(though you might tidy up the commit message as per other email).

I have a patch which fixes the remaining float-to-int conversion functions (ie the ones you didn't deal with in this series) to not raise Inexact when they raise Invalid for out of range, and one which fixes a bug in scalbn. I'll send those out shortly.

thanks
-- PMM

author
#11 lore raw

PATCH v4 5/22 softfloat: Fix float64_to_uint32_round_to_zero

In reply to Tom Musta

The float64_to_uint32_round_to_zero routine is incorrect.

For example, the following test pattern:

    425F81378DC0CD1F / 0x1.f81378dc0cd1fp+38

will erroneously set the inexact flag.

This patch re-implements the routine to use the float64_to_uint64_round_to_zero routine. If saturation occurs and the inexact flag was not previously set, it will be cleared.

This contribution can be licensed under either the softfloat-2a or -2b license.

V4: Correct commit commentary. Corrected code to properly handle the stickiness of the inexact flag.

---
 fpu/softfloat.c |   15 +++++++--------
 1 files changed, 7 insertions(+), 8 deletions(-)
fpu/softfloat.c +7 -8
index 6110e28..6112e2a 100644
@@ -6595,19 +6595,18 @@ uint32 float64_to_uint32( float64 a STATUS_PARAM )
 
 uint32 float64_to_uint32_round_to_zero( float64 a STATUS_PARAM )
 {
-    int64_t v;
+    uint64_t v;
     uint32 res;
+    int old_exc_flags = get_float_exception_flags(status);
 
-    v = float64_to_int64_round_to_zero(a STATUS_VAR);
-    if (v < 0) {
-        res = 0;
-        float_raise( float_flag_invalid STATUS_VAR);
-    } else if (v > 0xffffffff) {
+    v = float64_to_uint64_round_to_zero(a STATUS_VAR);
+    if (v > 0xffffffff) {
         res = 0xffffffff;
-        float_raise( float_flag_invalid STATUS_VAR);
     } else {
-        res = v;
+        return v;
     }
+    set_float_exception_flags(old_exc_flags, status);
+    float_raise(float_flag_invalid STATUS_VAR);
     return res;
 }
 
Signature · 1 line
1.7.1
Reviewed-by on v4 5/22
#12 lore raw

Re: [Qemu-devel] [V4 PATCH 05/22] softfloat: Fix float64_to_uint32_round_to_zero

Quoted 11 lines · Tom Musta

The float64_to_uint32_round_to_zero routine is incorrect.

For example, the following test pattern:

    425F81378DC0CD1F / 0x1.f81378dc0cd1fp+38

will erroneously set the inexact flag.

This patch re-implements the routine to use the float64_to_uint64_round_to_zero routine. If saturation occurs and the inexact flag was not previously set, it will be cleared.

Code is OK but you forgot to update this commit message.

Quoted 6 lines

This contribution can be licensed under either the softfloat-2a or -2b license.

V4: Correct commit commentary. Corrected code to properly handle the stickiness of the inexact flag.

These 'changes from previous version' comments should ideally go below the "---" line, by the way. The idea is that the bit above the line goes into the git commit history and should be a self-contained description of the final patch.

Quoted 1 line

If you fix the commit message you can add:

thanks
-- PMM

author
#13 lore raw

PATCH v4 6/22 target-ppc: Add set_fprf Argument to fload_invalid_op_excp()

In reply to Tom Musta

The fload_invalid_op_excp() function sets assorted invalid operation status bits. However, it also implicitly modifies the FPRF field of the PowerPC FPSCR. Many VSX instructions set invalid operation bits but do not alter FPRF. Thus the function is more generally useful if the setting of the FPRF field is made conditional via a parameter.

All invocations of this routine in existing instructions are modified to pass 1 and thus retain their current behavior.

---
 target-ppc/fpu_helper.c |  103 +++++++++++++++++++++++++----------------------
 1 files changed, 55 insertions(+), 48 deletions(-)
target-ppc/fpu_helper.c +55 -48
index 4f60218..f0b0a49 100644
@@ -106,7 +106,8 @@ uint32_t helper_compute_fprf(CPUPPCState *env, uint64_t arg, uint32_t set_fprf)
 }
 
 /* Floating-point invalid operations exception */
-static inline uint64_t fload_invalid_op_excp(CPUPPCState *env, int op)
+static inline uint64_t fload_invalid_op_excp(CPUPPCState *env, int op,
+                                             int set_fpcc)
 {
     uint64_t ret = 0;
     int ve;
@@ -138,8 +139,10 @@ static inline uint64_t fload_invalid_op_excp(CPUPPCState *env, int op)
     case POWERPC_EXCP_FP_VXVC:
         /* Ordered comparison of NaN */
         env->fpscr |= 1 << FPSCR_VXVC;
-        env->fpscr &= ~(0xF << FPSCR_FPCC);
-        env->fpscr |= 0x11 << FPSCR_FPCC;
+        if (set_fpcc) {
+            env->fpscr &= ~(0xF << FPSCR_FPCC);
+            env->fpscr |= 0x11 << FPSCR_FPCC;
+        }
         /* We must update the target FPR before raising the exception */
         if (ve != 0) {
             env->exception_index = POWERPC_EXCP_PROGRAM;
@@ -158,8 +161,10 @@ static inline uint64_t fload_invalid_op_excp(CPUPPCState *env, int op)
         if (ve == 0) {
             /* Set the result to quiet NaN */
             ret = 0x7FF8000000000000ULL;
-            env->fpscr &= ~(0xF << FPSCR_FPCC);
-            env->fpscr |= 0x11 << FPSCR_FPCC;
+            if (set_fpcc) {
+                env->fpscr &= ~(0xF << FPSCR_FPCC);
+                env->fpscr |= 0x11 << FPSCR_FPCC;
+            }
         }
         break;
     case POWERPC_EXCP_FP_VXCVI:
@@ -169,8 +174,10 @@ static inline uint64_t fload_invalid_op_excp(CPUPPCState *env, int op)
         if (ve == 0) {
             /* Set the result to quiet NaN */
             ret = 0x7FF8000000000000ULL;
-            env->fpscr &= ~(0xF << FPSCR_FPCC);
-            env->fpscr |= 0x11 << FPSCR_FPCC;
+            if (set_fpcc) {
+                env->fpscr &= ~(0xF << FPSCR_FPCC);
+                env->fpscr |= 0x11 << FPSCR_FPCC;
+            }
         }
         break;
     }
@@ -505,12 +512,12 @@ uint64_t helper_fadd(CPUPPCState *env, uint64_t arg1, uint64_t arg2)
     if (unlikely(float64_is_infinity(farg1.d) && float64_is_infinity(farg2.d) &&
                  float64_is_neg(farg1.d) != float64_is_neg(farg2.d))) {
         /* Magnitude subtraction of infinities */
-        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI);
+        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI, 1);
     } else {
         if (unlikely(float64_is_signaling_nan(farg1.d) ||
                      float64_is_signaling_nan(farg2.d))) {
             /* sNaN addition */
-            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
         }
         farg1.d = float64_add(farg1.d, farg2.d, &env->fp_status);
     }
@@ -529,12 +536,12 @@ uint64_t helper_fsub(CPUPPCState *env, uint64_t arg1, uint64_t arg2)
     if (unlikely(float64_is_infinity(farg1.d) && float64_is_infinity(farg2.d) &&
                  float64_is_neg(farg1.d) == float64_is_neg(farg2.d))) {
         /* Magnitude subtraction of infinities */
-        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI);
+        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI, 1);
     } else {
         if (unlikely(float64_is_signaling_nan(farg1.d) ||
                      float64_is_signaling_nan(farg2.d))) {
             /* sNaN subtraction */
-            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
         }
         farg1.d = float64_sub(farg1.d, farg2.d, &env->fp_status);
     }
@@ -553,12 +560,12 @@ uint64_t helper_fmul(CPUPPCState *env, uint64_t arg1, uint64_t arg2)
     if (unlikely((float64_is_infinity(farg1.d) && float64_is_zero(farg2.d)) ||
                  (float64_is_zero(farg1.d) && float64_is_infinity(farg2.d)))) {
         /* Multiplication of zero by infinity */
-        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIMZ);
+        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIMZ, 1);
     } else {
         if (unlikely(float64_is_signaling_nan(farg1.d) ||
                      float64_is_signaling_nan(farg2.d))) {
             /* sNaN multiplication */
-            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
         }
         farg1.d = float64_mul(farg1.d, farg2.d, &env->fp_status);
     }
@@ -577,15 +584,15 @@ uint64_t helper_fdiv(CPUPPCState *env, uint64_t arg1, uint64_t arg2)
     if (unlikely(float64_is_infinity(farg1.d) &&
                  float64_is_infinity(farg2.d))) {
         /* Division of infinity by infinity */
-        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIDI);
+        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIDI, 1);
     } else if (unlikely(float64_is_zero(farg1.d) && float64_is_zero(farg2.d))) {
         /* Division of zero by zero */
-        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXZDZ);
+        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXZDZ, 1);
     } else {
         if (unlikely(float64_is_signaling_nan(farg1.d) ||
                      float64_is_signaling_nan(farg2.d))) {
             /* sNaN division */
-            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
         }
         farg1.d = float64_div(farg1.d, farg2.d, &env->fp_status);
     }
@@ -603,11 +610,11 @@ uint64_t helper_fctiw(CPUPPCState *env, uint64_t arg)
     if (unlikely(float64_is_signaling_nan(farg.d))) {
         /* sNaN conversion */
         farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN |
-                                        POWERPC_EXCP_FP_VXCVI);
+                                        POWERPC_EXCP_FP_VXCVI, 1);
     } else if (unlikely(float64_is_quiet_nan(farg.d) ||
                         float64_is_infinity(farg.d))) {
         /* qNan / infinity conversion */
-        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI);
+        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI, 1);
     } else {
         farg.ll = float64_to_int32(farg.d, &env->fp_status);
         /* XXX: higher bits are not supposed to be significant.
@@ -628,11 +635,11 @@ uint64_t helper_fctiwz(CPUPPCState *env, uint64_t arg)
     if (unlikely(float64_is_signaling_nan(farg.d))) {
         /* sNaN conversion */
         farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN |
-                                        POWERPC_EXCP_FP_VXCVI);
+                                        POWERPC_EXCP_FP_VXCVI, 1);
     } else if (unlikely(float64_is_quiet_nan(farg.d) ||
                         float64_is_infinity(farg.d))) {
         /* qNan / infinity conversion */
-        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI);
+        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI, 1);
     } else {
         farg.ll = float64_to_int32_round_to_zero(farg.d, &env->fp_status);
         /* XXX: higher bits are not supposed to be significant.
@@ -663,11 +670,11 @@ uint64_t helper_fctid(CPUPPCState *env, uint64_t arg)
     if (unlikely(float64_is_signaling_nan(farg.d))) {
         /* sNaN conversion */
         farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN |
-                                        POWERPC_EXCP_FP_VXCVI);
+                                        POWERPC_EXCP_FP_VXCVI, 1);
     } else if (unlikely(float64_is_quiet_nan(farg.d) ||
                         float64_is_infinity(farg.d))) {
         /* qNan / infinity conversion */
-        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI);
+        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI, 1);
     } else {
         farg.ll = float64_to_int64(farg.d, &env->fp_status);
     }
@@ -684,11 +691,11 @@ uint64_t helper_fctidz(CPUPPCState *env, uint64_t arg)
     if (unlikely(float64_is_signaling_nan(farg.d))) {
         /* sNaN conversion */
         farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN |
-                                        POWERPC_EXCP_FP_VXCVI);
+                                        POWERPC_EXCP_FP_VXCVI, 1);
     } else if (unlikely(float64_is_quiet_nan(farg.d) ||
                         float64_is_infinity(farg.d))) {
         /* qNan / infinity conversion */
-        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI);
+        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI, 1);
     } else {
         farg.ll = float64_to_int64_round_to_zero(farg.d, &env->fp_status);
     }
@@ -707,11 +714,11 @@ static inline uint64_t do_fri(CPUPPCState *env, uint64_t arg,
     if (unlikely(float64_is_signaling_nan(farg.d))) {
         /* sNaN round */
         farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN |
-                                        POWERPC_EXCP_FP_VXCVI);
+                                        POWERPC_EXCP_FP_VXCVI, 1);
     } else if (unlikely(float64_is_quiet_nan(farg.d) ||
                         float64_is_infinity(farg.d))) {
         /* qNan / infinity round */
-        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI);
+        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI, 1);
     } else {
         set_float_rounding_mode(rounding_mode, &env->fp_status);
         farg.ll = float64_round_to_int(farg.d, &env->fp_status);
@@ -754,13 +761,13 @@ uint64_t helper_fmadd(CPUPPCState *env, uint64_t arg1, uint64_t arg2,
     if (unlikely((float64_is_infinity(farg1.d) && float64_is_zero(farg2.d)) ||
                  (float64_is_zero(farg1.d) && float64_is_infinity(farg2.d)))) {
         /* Multiplication of zero by infinity */
-        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIMZ);
+        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIMZ, 1);
     } else {
         if (unlikely(float64_is_signaling_nan(farg1.d) ||
                      float64_is_signaling_nan(farg2.d) ||
                      float64_is_signaling_nan(farg3.d))) {
             /* sNaN operation */
-            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
         }
         /* This is the way the PowerPC specification defines it */
         float128 ft0_128, ft1_128;
@@ -772,7 +779,7 @@ uint64_t helper_fmadd(CPUPPCState *env, uint64_t arg1, uint64_t arg2,
                      float64_is_infinity(farg3.d) &&
                      float128_is_neg(ft0_128) != float64_is_neg(farg3.d))) {
             /* Magnitude subtraction of infinities */
-            farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI);
+            farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI, 1);
         } else {
             ft1_128 = float64_to_float128(farg3.d, &env->fp_status);
             ft0_128 = float128_add(ft0_128, ft1_128, &env->fp_status);
@@ -797,13 +804,13 @@ uint64_t helper_fmsub(CPUPPCState *env, uint64_t arg1, uint64_t arg2,
                  (float64_is_zero(farg1.d) &&
                   float64_is_infinity(farg2.d)))) {
         /* Multiplication of zero by infinity */
-        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIMZ);
+        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIMZ, 1);
     } else {
         if (unlikely(float64_is_signaling_nan(farg1.d) ||
                      float64_is_signaling_nan(farg2.d) ||
                      float64_is_signaling_nan(farg3.d))) {
             /* sNaN operation */
-            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
         }
         /* This is the way the PowerPC specification defines it */
         float128 ft0_128, ft1_128;
@@ -815,7 +822,7 @@ uint64_t helper_fmsub(CPUPPCState *env, uint64_t arg1, uint64_t arg2,
                      float64_is_infinity(farg3.d) &&
                      float128_is_neg(ft0_128) == float64_is_neg(farg3.d))) {
             /* Magnitude subtraction of infinities */
-            farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI);
+            farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI, 1);
         } else {
             ft1_128 = float64_to_float128(farg3.d, &env->fp_status);
             ft0_128 = float128_sub(ft0_128, ft1_128, &env->fp_status);
@@ -838,13 +845,13 @@ uint64_t helper_fnmadd(CPUPPCState *env, uint64_t arg1, uint64_t arg2,
     if (unlikely((float64_is_infinity(farg1.d) && float64_is_zero(farg2.d)) ||
                  (float64_is_zero(farg1.d) && float64_is_infinity(farg2.d)))) {
         /* Multiplication of zero by infinity */
-        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIMZ);
+        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIMZ, 1);
     } else {
         if (unlikely(float64_is_signaling_nan(farg1.d) ||
                      float64_is_signaling_nan(farg2.d) ||
                      float64_is_signaling_nan(farg3.d))) {
             /* sNaN operation */
-            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
         }
         /* This is the way the PowerPC specification defines it */
         float128 ft0_128, ft1_128;
@@ -856,7 +863,7 @@ uint64_t helper_fnmadd(CPUPPCState *env, uint64_t arg1, uint64_t arg2,
                      float64_is_infinity(farg3.d) &&
                      float128_is_neg(ft0_128) != float64_is_neg(farg3.d))) {
             /* Magnitude subtraction of infinities */
-            farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI);
+            farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI, 1);
         } else {
             ft1_128 = float64_to_float128(farg3.d, &env->fp_status);
             ft0_128 = float128_add(ft0_128, ft1_128, &env->fp_status);
@@ -883,13 +890,13 @@ uint64_t helper_fnmsub(CPUPPCState *env, uint64_t arg1, uint64_t arg2,
                  (float64_is_zero(farg1.d) &&
                   float64_is_infinity(farg2.d)))) {
         /* Multiplication of zero by infinity */
-        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIMZ);
+        farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIMZ, 1);
     } else {
         if (unlikely(float64_is_signaling_nan(farg1.d) ||
                      float64_is_signaling_nan(farg2.d) ||
                      float64_is_signaling_nan(farg3.d))) {
             /* sNaN operation */
-            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
         }
         /* This is the way the PowerPC specification defines it */
         float128 ft0_128, ft1_128;
@@ -901,7 +908,7 @@ uint64_t helper_fnmsub(CPUPPCState *env, uint64_t arg1, uint64_t arg2,
                      float64_is_infinity(farg3.d) &&
                      float128_is_neg(ft0_128) == float64_is_neg(farg3.d))) {
             /* Magnitude subtraction of infinities */
-            farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI);
+            farg1.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI, 1);
         } else {
             ft1_128 = float64_to_float128(farg3.d, &env->fp_status);
             ft0_128 = float128_sub(ft0_128, ft1_128, &env->fp_status);
@@ -924,7 +931,7 @@ uint64_t helper_frsp(CPUPPCState *env, uint64_t arg)
 
     if (unlikely(float64_is_signaling_nan(farg.d))) {
         /* sNaN square root */
-        fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+        fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
     }
     f32 = float64_to_float32(farg.d, &env->fp_status);
     farg.d = float32_to_float64(f32, &env->fp_status);
@@ -941,11 +948,11 @@ uint64_t helper_fsqrt(CPUPPCState *env, uint64_t arg)
 
     if (unlikely(float64_is_neg(farg.d) && !float64_is_zero(farg.d))) {
         /* Square root of a negative nonzero number */
-        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT);
+        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT, 1);
     } else {
         if (unlikely(float64_is_signaling_nan(farg.d))) {
             /* sNaN square root */
-            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
         }
         farg.d = float64_sqrt(farg.d, &env->fp_status);
     }
@@ -961,7 +968,7 @@ uint64_t helper_fre(CPUPPCState *env, uint64_t arg)
 
     if (unlikely(float64_is_signaling_nan(farg.d))) {
         /* sNaN reciprocal */
-        fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+        fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
     }
     farg.d = float64_div(float64_one, farg.d, &env->fp_status);
     return farg.d;
@@ -977,7 +984,7 @@ uint64_t helper_fres(CPUPPCState *env, uint64_t arg)
 
     if (unlikely(float64_is_signaling_nan(farg.d))) {
         /* sNaN reciprocal */
-        fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+        fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
     }
     farg.d = float64_div(float64_one, farg.d, &env->fp_status);
     f32 = float64_to_float32(farg.d, &env->fp_status);
@@ -996,11 +1003,11 @@ uint64_t helper_frsqrte(CPUPPCState *env, uint64_t arg)
 
     if (unlikely(float64_is_neg(farg.d) && !float64_is_zero(farg.d))) {
         /* Reciprocal square root of a negative nonzero number */
-        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT);
+        farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT, 1);
     } else {
         if (unlikely(float64_is_signaling_nan(farg.d))) {
             /* sNaN reciprocal square root */
-            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
         }
         farg.d = float64_sqrt(farg.d, &env->fp_status);
         farg.d = float64_div(float64_one, farg.d, &env->fp_status);
@@ -1053,7 +1060,7 @@ void helper_fcmpu(CPUPPCState *env, uint64_t arg1, uint64_t arg2,
                  && (float64_is_signaling_nan(farg1.d) ||
                      float64_is_signaling_nan(farg2.d)))) {
         /* sNaN comparison */
-        fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN);
+        fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
     }
 }
 
@@ -1085,10 +1092,10 @@ void helper_fcmpo(CPUPPCState *env, uint64_t arg1, uint64_t arg2,
             float64_is_signaling_nan(farg2.d)) {
             /* sNaN comparison */
             fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN |
-                                  POWERPC_EXCP_FP_VXVC);
+                                  POWERPC_EXCP_FP_VXVC, 1);
         } else {
             /* qNaN comparison */
-            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXVC);
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXVC, 1);
         }
     }
 }
Signature · 1 line
1.7.1
author
#14 lore raw

PATCH v4 7/22 target-ppc: General Support for VSX Helpers

In reply to Tom Musta

This patch adds general support that will be used by the VSX helper routines:

- a union describing the various VSR subfields.
- access routines to get and set VSRs
- VSX decoders
- a general routine to generate a handler that invokes a VSX helper.

---
 target-ppc/fpu_helper.c |   41 +++++++++++++++++++++++++++++++++++++++++
 target-ppc/translate.c  |   14 ++++++++++++++
 2 files changed, 55 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +41 -0
index f0b0a49..cea94ac 100644
@@ -1717,3 +1717,44 @@ uint32_t helper_efdcmpeq(CPUPPCState *env, uint64_t op1, uint64_t op2)
     /* XXX: TODO: test special values (NaN, infinites, ...) */
     return helper_efdtsteq(env, op1, op2);
 }
+
+#define DECODE_SPLIT(opcode, shift1, nb1, shift2, nb2) \
+    (((((opcode) >> (shift1)) & ((1 << (nb1)) - 1)) << nb2) |    \
+     (((opcode) >> (shift2)) & ((1 << (nb2)) - 1)))
+
+#define xT(opcode) DECODE_SPLIT(opcode, 0, 1, 21, 5)
+#define xA(opcode) DECODE_SPLIT(opcode, 2, 1, 16, 5)
+#define xB(opcode) DECODE_SPLIT(opcode, 1, 1, 11, 5)
+#define xC(opcode) DECODE_SPLIT(opcode, 3, 1,  6, 5)
+#define BF(opcode) (((opcode) >> (31-8)) & 7)
+
+typedef union _ppc_vsr_t {
+    uint64_t u64[2];
+    uint32_t u32[4];
+    float32 f32[4];
+    float64 f64[2];
+} ppc_vsr_t;
+
+static void getVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env)
+{
+    if (n < 32) {
+        vsr->f64[0] = env->fpr[n];
+        vsr->u64[1] = env->vsr[n];
+    } else {
+        vsr->u64[0] = env->avr[n-32].u64[0];
+        vsr->u64[1] = env->avr[n-32].u64[1];
+    }
+}
+
+static void putVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env)
+{
+    if (n < 32) {
+        env->fpr[n] = vsr->f64[0];
+        env->vsr[n] = vsr->u64[1];
+    } else {
+        env->avr[n-32].u64[0] = vsr->u64[0];
+        env->avr[n-32].u64[1] = vsr->u64[1];
+    }
+}
+
+#define float64_to_float64(x, env) x
target-ppc/translate.c +14 -0
index ce07a56..0453900 100644
@@ -7280,6 +7280,20 @@ VSX_VECTOR_MOVE(xvnabssp, OP_NABS, SGN_MASK_SP)
 VSX_VECTOR_MOVE(xvnegsp, OP_NEG, SGN_MASK_SP)
 VSX_VECTOR_MOVE(xvcpsgnsp, OP_CPSGN, SGN_MASK_SP)
 
+#define GEN_VSX_HELPER_2(name, op1, op2, inval, type)                         \
+static void gen_##name(DisasContext * ctx)                                    \
+{                                                                             \
+    TCGv_i32 opc;                                                             \
+    if (unlikely(!ctx->vsx_enabled)) {                                        \
+        gen_exception(ctx, POWERPC_EXCP_VSXU);                                \
+        return;                                                               \
+    }                                                                         \
+    /* NIP cannot be restored if the memory exception comes from an helper */ \
+    gen_update_nip(ctx, ctx->nip - 4);                                        \
+    opc = tcg_const_i32(ctx->opcode);                                         \
+    gen_helper_##name(cpu_env, opc);                                          \
+    tcg_temp_free_i32(opc);                                                   \
+}
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
Signature · 1 line
1.7.1
author
#15 lore raw

PATCH v4 8/22 target-ppc: Add VSX ISA2.06 xadd/xsub Instructions

In reply to Tom Musta

This patch adds the floating point addition and subtraction instructions defined by V2.06 of the PowerPC ISA: xssubdp, xvsubdp and xvsubsp.

V2: re-implemented helper macro and combined add and substract.

---
 target-ppc/fpu_helper.c |   51 +++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    9 ++++++++
 target-ppc/translate.c  |   18 ++++++++++++++++
 3 files changed, 78 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +51 -0
index cea94ac..a577d28 100644
@@ -1758,3 +1758,54 @@ static void putVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env)
 }
 
 #define float64_to_float64(x, env) x
+
+
+/* VSX_ADD_SUB - VSX floating point add/subract
+ *   name  - instruction mnemonic
+ *   op    - operation (add or sub)
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   sfprf - set FPRF
+ */
+#define VSX_ADD_SUB(name, op, nels, tp, fld, sfprf)                          \
+void helper_##name(CPUPPCState *env, uint32_t opcode)                        \
+{                                                                            \
+    ppc_vsr_t xt, xa, xb;                                                    \
+    int i;                                                                   \
+                                                                             \
+    getVSR(xA(opcode), &xa, env);                                            \
+    getVSR(xB(opcode), &xb, env);                                            \
+    getVSR(xT(opcode), &xt, env);                                            \
+    helper_reset_fpstatus(env);                                              \
+                                                                             \
+    for (i = 0; i < nels; i++) {                                             \
+        float_status tstat = env->fp_status;                                 \
+        set_float_exception_flags(0, &tstat);                                \
+        xt.fld[i] = tp##_##op(xa.fld[i], xb.fld[i], &tstat);                 \
+        env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
+                                                                             \
+        if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {    \
+            if (tp##_is_infinity(xa.fld[i]) && tp##_is_infinity(xb.fld[i])) {\
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI, sfprf);    \
+            } else if (tp##_is_signaling_nan(xa.fld[i]) ||                   \
+                       tp##_is_signaling_nan(xb.fld[i])) {                   \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, sfprf);   \
+            }                                                                \
+        }                                                                    \
+                                                                             \
+        if (sfprf) {                                                         \
+            helper_compute_fprf(env, xt.fld[i], sfprf);                      \
+        }                                                                    \
+    }                                                                        \
+    putVSR(xT(opcode), &xt, env);                                            \
+    helper_float_check_status(env);                                          \
+}
+
+VSX_ADD_SUB(xsadddp, add, 1, float64, f64, 1)
+VSX_ADD_SUB(xvadddp, add, 2, float64, f64, 0)
+VSX_ADD_SUB(xvaddsp, add, 4, float32, f32, 0)
+VSX_ADD_SUB(xssubdp, sub, 1, float64, f64, 1)
+VSX_ADD_SUB(xvsubdp, sub, 2, float64, f64, 0)
+VSX_ADD_SUB(xvsubsp, sub, 4, float32, f32, 0)
+
target-ppc/helper.h +9 -0
index 6d282bb..966200d 100644
@@ -251,6 +251,15 @@ DEF_HELPER_4(vcfsx, void, env, avr, avr, i32)
 DEF_HELPER_4(vctuxs, void, env, avr, avr, i32)
 DEF_HELPER_4(vctsxs, void, env, avr, avr, i32)
 
+DEF_HELPER_2(xsadddp, void, env, i32)
+DEF_HELPER_2(xssubdp, void, env, i32)
+
+DEF_HELPER_2(xvadddp, void, env, i32)
+DEF_HELPER_2(xvsubdp, void, env, i32)
+
+DEF_HELPER_2(xvaddsp, void, env, i32)
+DEF_HELPER_2(xvsubsp, void, env, i32)
+
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
 DEF_HELPER_2(efscfuf, i32, env, i32)
target-ppc/translate.c +18 -0
index 0453900..d20b269 100644
@@ -7295,6 +7295,15 @@ static void gen_##name(DisasContext * ctx)                                    \
     tcg_temp_free_i32(opc);                                                   \
 }
 
+GEN_VSX_HELPER_2(xsadddp, 0x00, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xssubdp, 0x00, 0x05, 0, PPC2_VSX)
+
+GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
+
+GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
+
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
     {                                                                \
@@ -9977,6 +9986,15 @@ GEN_XX2FORM(xvnabssp, 0x12, 0x1A, PPC2_VSX),
 GEN_XX2FORM(xvnegsp, 0x12, 0x1B, PPC2_VSX),
 GEN_XX3FORM(xvcpsgnsp, 0x00, 0x1A, PPC2_VSX),
 
+GEN_XX3FORM(xsadddp, 0x00, 0x04, PPC2_VSX),
+GEN_XX3FORM(xssubdp, 0x00, 0x05, PPC2_VSX),
+
+GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
+GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
+
+GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
+GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
+
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
 GEN_XX3FORM(name, opc2, opc3, fl2)
Signature · 1 line
1.7.1
author
#16 lore raw

PATCH v4 9/22 target-ppc: Add VSX ISA2.06 xmul Instructions

In reply to Tom Musta

This patch adds the VSX floating point multiply instructions defined by V2.06 of the PowerPC ISA: xsmuldp, xvmuldp, xvmulsp.

V2: re-implemented VSX_MUL macro.

---
 target-ppc/fpu_helper.c |   46 ++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    3 +++
 target-ppc/translate.c  |    6 ++++++
 3 files changed, 55 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +46 -0
index a577d28..51ca589 100644
@@ -1809,3 +1809,49 @@ VSX_ADD_SUB(xssubdp, sub, 1, float64, f64, 1)
 VSX_ADD_SUB(xvsubdp, sub, 2, float64, f64, 0)
 VSX_ADD_SUB(xvsubsp, sub, 4, float32, f32, 0)
 
+/* VSX_MUL - VSX floating point multiply
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   sfprf - set FPRF
+ */
+#define VSX_MUL(op, nels, tp, fld, sfprf)                                    \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
+{                                                                            \
+    ppc_vsr_t xt, xa, xb;                                                    \
+    int i;                                                                   \
+                                                                             \
+    getVSR(xA(opcode), &xa, env);                                            \
+    getVSR(xB(opcode), &xb, env);                                            \
+    getVSR(xT(opcode), &xt, env);                                            \
+    helper_reset_fpstatus(env);                                              \
+                                                                             \
+    for (i = 0; i < nels; i++) {                                             \
+        float_status tstat = env->fp_status;                                 \
+        set_float_exception_flags(0, &tstat);                                \
+        xt.fld[i] = tp##_mul(xa.fld[i], xb.fld[i], &tstat);                  \
+        env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
+                                                                             \
+        if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {    \
+            if ((tp##_is_infinity(xa.fld[i]) && tp##_is_zero(xb.fld[i])) ||  \
+                (tp##_is_infinity(xb.fld[i]) && tp##_is_zero(xa.fld[i]))) {  \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIMZ, sfprf);    \
+            } else if (tp##_is_signaling_nan(xa.fld[i]) ||                   \
+                       tp##_is_signaling_nan(xb.fld[i])) {                   \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, sfprf);   \
+            }                                                                \
+        }                                                                    \
+                                                                             \
+        if (sfprf) {                                                         \
+            helper_compute_fprf(env, xt.fld[i], sfprf);                      \
+        }                                                                    \
+    }                                                                        \
+                                                                             \
+    putVSR(xT(opcode), &xt, env);                                            \
+    helper_float_check_status(env);                                          \
+}
+
+VSX_MUL(xsmuldp, 1, float64, f64, 1)
+VSX_MUL(xvmuldp, 2, float64, f64, 0)
+VSX_MUL(xvmulsp, 4, float32, f32, 0)
target-ppc/helper.h +3 -0
index 966200d..ecb900f 100644
@@ -253,12 +253,15 @@ DEF_HELPER_4(vctsxs, void, env, avr, avr, i32)
 
 DEF_HELPER_2(xsadddp, void, env, i32)
 DEF_HELPER_2(xssubdp, void, env, i32)
+DEF_HELPER_2(xsmuldp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
+DEF_HELPER_2(xvmuldp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
+DEF_HELPER_2(xvmulsp, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
target-ppc/translate.c +6 -0
index d20b269..1fb21b7 100644
@@ -7297,12 +7297,15 @@ static void gen_##name(DisasContext * ctx)                                    \
 
 GEN_VSX_HELPER_2(xsadddp, 0x00, 0x04, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xssubdp, 0x00, 0x05, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsmuldp, 0x00, 0x06, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvmuldp, 0x00, 0x0E, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvmulsp, 0x00, 0x0A, 0, PPC2_VSX)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -9988,12 +9991,15 @@ GEN_XX3FORM(xvcpsgnsp, 0x00, 0x1A, PPC2_VSX),
 
 GEN_XX3FORM(xsadddp, 0x00, 0x04, PPC2_VSX),
 GEN_XX3FORM(xssubdp, 0x00, 0x05, PPC2_VSX),
+GEN_XX3FORM(xsmuldp, 0x00, 0x06, PPC2_VSX),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
+GEN_XX3FORM(xvmuldp, 0x00, 0x0E, PPC2_VSX),
 
 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
+GEN_XX3FORM(xvmulsp, 0x00, 0x0A, PPC2_VSX),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
Signature · 1 line
1.7.1
author
#17 lore raw

PATCH v4 10/22 target-ppc: Add VSX ISA2.06 xdiv Instructions

In reply to Tom Musta

This patch adds the VSX floating point divide instructions defined by V2.06 of the PowerPC ISA: xsdivdp, xvdivdp, xvdivsp.

V2: re-implemented the VSX_DIV macro.

---
 target-ppc/fpu_helper.c |   49 +++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    3 ++
 target-ppc/translate.c  |    6 +++++
 3 files changed, 58 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +49 -0
index 51ca589..c84f432 100644
@@ -1855,3 +1855,52 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
 VSX_MUL(xsmuldp, 1, float64, f64, 1)
 VSX_MUL(xvmuldp, 2, float64, f64, 0)
 VSX_MUL(xvmulsp, 4, float32, f32, 0)
+
+/* VSX_DIV - VSX floating point divide
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   sfprf - set FPRF
+ */
+#define VSX_DIV(op, nels, tp, fld, sfprf)                                     \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                           \
+{                                                                             \
+    ppc_vsr_t xt, xa, xb;                                                     \
+    int i;                                                                    \
+                                                                              \
+    getVSR(xA(opcode), &xa, env);                                             \
+    getVSR(xB(opcode), &xb, env);                                             \
+    getVSR(xT(opcode), &xt, env);                                             \
+    helper_reset_fpstatus(env);                                               \
+                                                                              \
+    for (i = 0; i < nels; i++) {                                              \
+        float_status tstat = env->fp_status;                                  \
+        set_float_exception_flags(0, &tstat);                                 \
+        xt.fld[i] = tp##_div(xa.fld[i], xb.fld[i], &tstat);                   \
+        env->fp_status.float_exception_flags |= tstat.float_exception_flags;  \
+                                                                              \
+        if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {     \
+            if (tp##_is_infinity(xa.fld[i]) && tp##_is_infinity(xb.fld[i])) { \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXIDI, sfprf);     \
+            } else if (tp##_is_zero(xa.fld[i]) &&                             \
+                tp##_is_zero(xb.fld[i])) {                                    \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXZDZ, sfprf);     \
+            } else if (tp##_is_signaling_nan(xa.fld[i]) ||                    \
+                tp##_is_signaling_nan(xb.fld[i])) {                           \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, sfprf);    \
+            }                                                                 \
+        }                                                                     \
+                                                                              \
+        if (sfprf) {                                                          \
+            helper_compute_fprf(env, xt.fld[i], sfprf);                       \
+        }                                                                     \
+    }                                                                         \
+                                                                              \
+    putVSR(xT(opcode), &xt, env);                                             \
+    helper_float_check_status(env);                                           \
+}
+
+VSX_DIV(xsdivdp, 1, float64, f64, 1)
+VSX_DIV(xvdivdp, 2, float64, f64, 0)
+VSX_DIV(xvdivsp, 4, float32, f32, 0)
target-ppc/helper.h +3 -0
index ecb900f..6ede7ea 100644
@@ -254,14 +254,17 @@ DEF_HELPER_4(vctsxs, void, env, avr, avr, i32)
 DEF_HELPER_2(xsadddp, void, env, i32)
 DEF_HELPER_2(xssubdp, void, env, i32)
 DEF_HELPER_2(xsmuldp, void, env, i32)
+DEF_HELPER_2(xsdivdp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
 DEF_HELPER_2(xvmuldp, void, env, i32)
+DEF_HELPER_2(xvdivdp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
 DEF_HELPER_2(xvmulsp, void, env, i32)
+DEF_HELPER_2(xvdivsp, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
target-ppc/translate.c +6 -0
index 1fb21b7..e77fcde 100644
@@ -7298,14 +7298,17 @@ static void gen_##name(DisasContext * ctx)                                    \
 GEN_VSX_HELPER_2(xsadddp, 0x00, 0x04, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xssubdp, 0x00, 0x05, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsmuldp, 0x00, 0x06, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsdivdp, 0x00, 0x07, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmuldp, 0x00, 0x0E, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvdivdp, 0x00, 0x0F, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmulsp, 0x00, 0x0A, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvdivsp, 0x00, 0x0B, 0, PPC2_VSX)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -9992,14 +9995,17 @@ GEN_XX3FORM(xvcpsgnsp, 0x00, 0x1A, PPC2_VSX),
 GEN_XX3FORM(xsadddp, 0x00, 0x04, PPC2_VSX),
 GEN_XX3FORM(xssubdp, 0x00, 0x05, PPC2_VSX),
 GEN_XX3FORM(xsmuldp, 0x00, 0x06, PPC2_VSX),
+GEN_XX3FORM(xsdivdp, 0x00, 0x07, PPC2_VSX),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
 GEN_XX3FORM(xvmuldp, 0x00, 0x0E, PPC2_VSX),
+GEN_XX3FORM(xvdivdp, 0x00, 0x0F, PPC2_VSX),
 
 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
 GEN_XX3FORM(xvmulsp, 0x00, 0x0A, PPC2_VSX),
+GEN_XX3FORM(xvdivsp, 0x00, 0x0B, PPC2_VSX),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
Signature · 1 line
1.7.1
author
#18 lore raw

PATCH v4 11/22 target-ppc: Add VSX ISA2.06 xre Instructions

In reply to Tom Musta

This patch adds the VSX floating point reciprocal estimate instructions defined by V2.06 of the PowerPC ISA: xsredp, xvredp, xvresp.

---
 target-ppc/fpu_helper.c |   35 +++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    3 +++
 target-ppc/translate.c  |    6 ++++++
 3 files changed, 44 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +35 -0
index c84f432..5908e41 100644
@@ -1904,3 +1904,38 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)                           \
 VSX_DIV(xsdivdp, 1, float64, f64, 1)
 VSX_DIV(xvdivdp, 2, float64, f64, 0)
 VSX_DIV(xvdivsp, 4, float32, f32, 0)
+
+/* VSX_RE  - VSX floating point reciprocal estimate
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   sfprf - set FPRF
+ */
+#define VSX_RE(op, nels, tp, fld, sfprf)                                      \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                           \
+{                                                                             \
+    ppc_vsr_t xt, xb;                                                         \
+    int i;                                                                    \
+                                                                              \
+    getVSR(xB(opcode), &xb, env);                                             \
+    getVSR(xT(opcode), &xt, env);                                             \
+    helper_reset_fpstatus(env);                                               \
+                                                                              \
+    for (i = 0; i < nels; i++) {                                              \
+        if (unlikely(tp##_is_signaling_nan(xb.fld[i]))) {                     \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, sfprf);    \
+        }                                                                     \
+        xt.fld[i] = tp##_div(tp##_one, xb.fld[i], &env->fp_status);           \
+        if (sfprf) {                                                          \
+            helper_compute_fprf(env, xt.fld[0], sfprf);                       \
+        }                                                                     \
+    }                                                                         \
+                                                                              \
+    putVSR(xT(opcode), &xt, env);                                             \
+    helper_float_check_status(env);                                           \
+}
+
+VSX_RE(xsredp, 1, float64, f64, 1)
+VSX_RE(xvredp, 2, float64, f64, 0)
+VSX_RE(xvresp, 4, float32, f32, 0)
target-ppc/helper.h +3 -0
index 6ede7ea..fe5b61c 100644
@@ -255,16 +255,19 @@ DEF_HELPER_2(xsadddp, void, env, i32)
 DEF_HELPER_2(xssubdp, void, env, i32)
 DEF_HELPER_2(xsmuldp, void, env, i32)
 DEF_HELPER_2(xsdivdp, void, env, i32)
+DEF_HELPER_2(xsredp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
 DEF_HELPER_2(xvmuldp, void, env, i32)
 DEF_HELPER_2(xvdivdp, void, env, i32)
+DEF_HELPER_2(xvredp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
 DEF_HELPER_2(xvmulsp, void, env, i32)
 DEF_HELPER_2(xvdivsp, void, env, i32)
+DEF_HELPER_2(xvresp, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
target-ppc/translate.c +6 -0
index e77fcde..d2060b7 100644
@@ -7299,16 +7299,19 @@ GEN_VSX_HELPER_2(xsadddp, 0x00, 0x04, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xssubdp, 0x00, 0x05, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsmuldp, 0x00, 0x06, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsdivdp, 0x00, 0x07, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsredp, 0x14, 0x05, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmuldp, 0x00, 0x0E, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvdivdp, 0x00, 0x0F, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvredp, 0x14, 0x0D, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmulsp, 0x00, 0x0A, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvdivsp, 0x00, 0x0B, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvresp, 0x14, 0x09, 0, PPC2_VSX)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -9996,16 +9999,19 @@ GEN_XX3FORM(xsadddp, 0x00, 0x04, PPC2_VSX),
 GEN_XX3FORM(xssubdp, 0x00, 0x05, PPC2_VSX),
 GEN_XX3FORM(xsmuldp, 0x00, 0x06, PPC2_VSX),
 GEN_XX3FORM(xsdivdp, 0x00, 0x07, PPC2_VSX),
+GEN_XX2FORM(xsredp,  0x14, 0x05, PPC2_VSX),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
 GEN_XX3FORM(xvmuldp, 0x00, 0x0E, PPC2_VSX),
 GEN_XX3FORM(xvdivdp, 0x00, 0x0F, PPC2_VSX),
+GEN_XX2FORM(xvredp,  0x14, 0x0D, PPC2_VSX),
 
 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
 GEN_XX3FORM(xvmulsp, 0x00, 0x0A, PPC2_VSX),
 GEN_XX3FORM(xvdivsp, 0x00, 0x0B, PPC2_VSX),
+GEN_XX2FORM(xvresp, 0x14, 0x09, PPC2_VSX),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
Signature · 1 line
1.7.1
author
#19 lore raw

PATCH v4 12/22 target-ppc: Add VSX ISA2.06 xsqrt Instructions

In reply to Tom Musta

This patch adds the VSX floating point square root instructions defined by V2.06 of the PowerPC ISA: xssqrtdp, xvsqrtdp, xvsqrtsp.

V2: re-implemented the VSX_SQRT macro.

---
 target-ppc/fpu_helper.c |   44 ++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    3 +++
 target-ppc/translate.c  |    6 ++++++
 3 files changed, 53 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +44 -0
index 5908e41..060e6a0 100644
@@ -1939,3 +1939,47 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)                           \
 VSX_RE(xsredp, 1, float64, f64, 1)
 VSX_RE(xvredp, 2, float64, f64, 0)
 VSX_RE(xvresp, 4, float32, f32, 0)
+
+/* VSX_SQRT - VSX floating point square root
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   sfprf - set FPRF
+ */
+#define VSX_SQRT(op, nels, tp, fld, sfprf)                                   \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
+{                                                                            \
+    ppc_vsr_t xt, xb;                                                        \
+    int i;                                                                   \
+                                                                             \
+    getVSR(xB(opcode), &xb, env);                                            \
+    getVSR(xT(opcode), &xt, env);                                            \
+    helper_reset_fpstatus(env);                                              \
+                                                                             \
+    for (i = 0; i < nels; i++) {                                             \
+        float_status tstat = env->fp_status;                                 \
+        set_float_exception_flags(0, &tstat);                                \
+        xt.fld[i] = tp##_sqrt(xb.fld[i], &tstat);                            \
+        env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
+                                                                             \
+        if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {    \
+            if (tp##_is_neg(xb.fld[i]) && !tp##_is_zero(xb.fld[i])) {        \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT, sfprf);   \
+            } else if (tp##_is_signaling_nan(xb.fld[i])) {                   \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, sfprf);   \
+            }                                                                \
+        }                                                                    \
+                                                                             \
+        if (sfprf) {                                                         \
+            helper_compute_fprf(env, xt.fld[i], sfprf);                      \
+        }                                                                    \
+    }                                                                        \
+                                                                             \
+    putVSR(xT(opcode), &xt, env);                                            \
+    helper_float_check_status(env);                                          \
+}
+
+VSX_SQRT(xssqrtdp, 1, float64, f64, 1)
+VSX_SQRT(xvsqrtdp, 2, float64, f64, 0)
+VSX_SQRT(xvsqrtsp, 4, float32, f32, 0)
target-ppc/helper.h +3 -0
index fe5b61c..a6e7e62 100644
@@ -256,18 +256,21 @@ DEF_HELPER_2(xssubdp, void, env, i32)
 DEF_HELPER_2(xsmuldp, void, env, i32)
 DEF_HELPER_2(xsdivdp, void, env, i32)
 DEF_HELPER_2(xsredp, void, env, i32)
+DEF_HELPER_2(xssqrtdp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
 DEF_HELPER_2(xvmuldp, void, env, i32)
 DEF_HELPER_2(xvdivdp, void, env, i32)
 DEF_HELPER_2(xvredp, void, env, i32)
+DEF_HELPER_2(xvsqrtdp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
 DEF_HELPER_2(xvmulsp, void, env, i32)
 DEF_HELPER_2(xvdivsp, void, env, i32)
 DEF_HELPER_2(xvresp, void, env, i32)
+DEF_HELPER_2(xvsqrtsp, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
target-ppc/translate.c +6 -0
index d2060b7..c5c97ba 100644
@@ -7300,18 +7300,21 @@ GEN_VSX_HELPER_2(xssubdp, 0x00, 0x05, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsmuldp, 0x00, 0x06, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsdivdp, 0x00, 0x07, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsredp, 0x14, 0x05, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmuldp, 0x00, 0x0E, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvdivdp, 0x00, 0x0F, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvredp, 0x14, 0x0D, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvsqrtdp, 0x16, 0x0C, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmulsp, 0x00, 0x0A, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvdivsp, 0x00, 0x0B, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvresp, 0x14, 0x09, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvsqrtsp, 0x16, 0x08, 0, PPC2_VSX)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -10000,18 +10003,21 @@ GEN_XX3FORM(xssubdp, 0x00, 0x05, PPC2_VSX),
 GEN_XX3FORM(xsmuldp, 0x00, 0x06, PPC2_VSX),
 GEN_XX3FORM(xsdivdp, 0x00, 0x07, PPC2_VSX),
 GEN_XX2FORM(xsredp,  0x14, 0x05, PPC2_VSX),
+GEN_XX2FORM(xssqrtdp,  0x16, 0x04, PPC2_VSX),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
 GEN_XX3FORM(xvmuldp, 0x00, 0x0E, PPC2_VSX),
 GEN_XX3FORM(xvdivdp, 0x00, 0x0F, PPC2_VSX),
 GEN_XX2FORM(xvredp,  0x14, 0x0D, PPC2_VSX),
+GEN_XX2FORM(xvsqrtdp,  0x16, 0x0C, PPC2_VSX),
 
 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
 GEN_XX3FORM(xvmulsp, 0x00, 0x0A, PPC2_VSX),
 GEN_XX3FORM(xvdivsp, 0x00, 0x0B, PPC2_VSX),
 GEN_XX2FORM(xvresp, 0x14, 0x09, PPC2_VSX),
+GEN_XX2FORM(xvsqrtsp, 0x16, 0x08, PPC2_VSX),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
Signature · 1 line
1.7.1
author
#20 lore raw

PATCH v4 13/22 target-ppc: Add VSX ISA2.06 xrsqrte Instructions

In reply to Tom Musta

This patch adds the VSX floating point reciprocal square root estimate instructions defined by V2.06 of the PowerPC ISA: xsrsqrtedp, xvrsqrtedp, xvrsqrtesp.

V2: re-implemented VSX_RSQRTE macro.

---
 target-ppc/fpu_helper.c |   45 +++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    3 +++
 target-ppc/translate.c  |    6 ++++++
 3 files changed, 54 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +45 -0
index 060e6a0..31669f1 100644
@@ -1983,3 +1983,48 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
 VSX_SQRT(xssqrtdp, 1, float64, f64, 1)
 VSX_SQRT(xvsqrtdp, 2, float64, f64, 0)
 VSX_SQRT(xvsqrtsp, 4, float32, f32, 0)
+
+/* VSX_RSQRTE - VSX floating point reciprocal square root estimate
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   sfprf - set FPRF
+ */
+#define VSX_RSQRTE(op, nels, tp, fld, sfprf)                                 \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
+{                                                                            \
+    ppc_vsr_t xt, xb;                                                        \
+    int i;                                                                   \
+                                                                             \
+    getVSR(xB(opcode), &xb, env);                                            \
+    getVSR(xT(opcode), &xt, env);                                            \
+    helper_reset_fpstatus(env);                                              \
+                                                                             \
+    for (i = 0; i < nels; i++) {                                             \
+        float_status tstat = env->fp_status;                                 \
+        set_float_exception_flags(0, &tstat);                                \
+        xt.fld[i] = tp##_sqrt(xb.fld[i], &tstat);                            \
+        xt.fld[i] = tp##_div(tp##_one, xt.fld[i], &tstat);                   \
+        env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
+                                                                             \
+        if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {    \
+            if (tp##_is_neg(xb.fld[i]) && !tp##_is_zero(xb.fld[i])) {        \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT, sfprf);   \
+            } else if (tp##_is_signaling_nan(xb.fld[i])) {                   \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, sfprf);   \
+            }                                                                \
+        }                                                                    \
+                                                                             \
+        if (sfprf) {                                                         \
+            helper_compute_fprf(env, xt.fld[i], sfprf);                      \
+        }                                                                    \
+    }                                                                        \
+                                                                             \
+    putVSR(xT(opcode), &xt, env);                                            \
+    helper_float_check_status(env);                                          \
+}
+
+VSX_RSQRTE(xsrsqrtedp, 1, float64, f64, 1)
+VSX_RSQRTE(xvrsqrtedp, 2, float64, f64, 0)
+VSX_RSQRTE(xvrsqrtesp, 4, float32, f32, 0)
target-ppc/helper.h +3 -0
index a6e7e62..4d5e31b 100644
@@ -257,6 +257,7 @@ DEF_HELPER_2(xsmuldp, void, env, i32)
 DEF_HELPER_2(xsdivdp, void, env, i32)
 DEF_HELPER_2(xsredp, void, env, i32)
 DEF_HELPER_2(xssqrtdp, void, env, i32)
+DEF_HELPER_2(xsrsqrtedp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
@@ -264,6 +265,7 @@ DEF_HELPER_2(xvmuldp, void, env, i32)
 DEF_HELPER_2(xvdivdp, void, env, i32)
 DEF_HELPER_2(xvredp, void, env, i32)
 DEF_HELPER_2(xvsqrtdp, void, env, i32)
+DEF_HELPER_2(xvrsqrtedp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -271,6 +273,7 @@ DEF_HELPER_2(xvmulsp, void, env, i32)
 DEF_HELPER_2(xvdivsp, void, env, i32)
 DEF_HELPER_2(xvresp, void, env, i32)
 DEF_HELPER_2(xvsqrtsp, void, env, i32)
+DEF_HELPER_2(xvrsqrtesp, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
target-ppc/translate.c +6 -0
index c5c97ba..287b924 100644
@@ -7301,6 +7301,7 @@ GEN_VSX_HELPER_2(xsmuldp, 0x00, 0x06, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsdivdp, 0x00, 0x07, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsredp, 0x14, 0x05, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -7308,6 +7309,7 @@ GEN_VSX_HELPER_2(xvmuldp, 0x00, 0x0E, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvdivdp, 0x00, 0x0F, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvredp, 0x14, 0x0D, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsqrtdp, 0x16, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrsqrtedp, 0x14, 0x0C, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
@@ -7315,6 +7317,7 @@ GEN_VSX_HELPER_2(xvmulsp, 0x00, 0x0A, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvdivsp, 0x00, 0x0B, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvresp, 0x14, 0x09, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsqrtsp, 0x16, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrsqrtesp, 0x14, 0x08, 0, PPC2_VSX)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -10004,6 +10007,7 @@ GEN_XX3FORM(xsmuldp, 0x00, 0x06, PPC2_VSX),
 GEN_XX3FORM(xsdivdp, 0x00, 0x07, PPC2_VSX),
 GEN_XX2FORM(xsredp,  0x14, 0x05, PPC2_VSX),
 GEN_XX2FORM(xssqrtdp,  0x16, 0x04, PPC2_VSX),
+GEN_XX2FORM(xsrsqrtedp,  0x14, 0x04, PPC2_VSX),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
@@ -10011,6 +10015,7 @@ GEN_XX3FORM(xvmuldp, 0x00, 0x0E, PPC2_VSX),
 GEN_XX3FORM(xvdivdp, 0x00, 0x0F, PPC2_VSX),
 GEN_XX2FORM(xvredp,  0x14, 0x0D, PPC2_VSX),
 GEN_XX2FORM(xvsqrtdp,  0x16, 0x0C, PPC2_VSX),
+GEN_XX2FORM(xvrsqrtedp,  0x14, 0x0C, PPC2_VSX),
 
 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
@@ -10018,6 +10023,7 @@ GEN_XX3FORM(xvmulsp, 0x00, 0x0A, PPC2_VSX),
 GEN_XX3FORM(xvdivsp, 0x00, 0x0B, PPC2_VSX),
 GEN_XX2FORM(xvresp, 0x14, 0x09, PPC2_VSX),
 GEN_XX2FORM(xvsqrtsp, 0x16, 0x08, PPC2_VSX),
+GEN_XX2FORM(xvrsqrtesp, 0x14, 0x08, PPC2_VSX),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
Signature · 1 line
1.7.1
author
#21 lore raw

PATCH v4 14/22 target-ppc: Add VSX ISA2.06 xtdiv Instructions

In reply to Tom Musta

This patch adds the VSX floating point test for software divide instructions defined by V2.06 of the PowerPC ISA: xstdivdp, xvtdivdp, and xvtdivsp.

V2: added ppc_float*_get_unbiased_exp() routines (pulled back from softfloat). Eliminated dependency on float*_is_denormalized() routines.

---
 target-ppc/fpu_helper.c |   67 +++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    3 ++
 target-ppc/translate.c  |    6 ++++
 3 files changed, 76 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +67 -0
index 31669f1..ee03942 100644
@@ -2028,3 +2028,70 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
 VSX_RSQRTE(xsrsqrtedp, 1, float64, f64, 1)
 VSX_RSQRTE(xvrsqrtedp, 2, float64, f64, 0)
 VSX_RSQRTE(xvrsqrtesp, 4, float32, f32, 0)
+
+static inline int ppc_float32_get_unbiased_exp(float32 f)
+{
+    return ((f >> 23) & 0xFF) - 127;
+}
+
+static inline int ppc_float64_get_unbiased_exp(float64 f)
+{
+    return ((f >> 52) & 0x7FF) - 1023;
+}
+
+/* VSX_TDIV - VSX floating point test for divide
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   emin  - minimum unbiased exponent
+ *   emax  - maximum unbiased exponent
+ *   nbits - number of fraction bits
+ */
+#define VSX_TDIV(op, nels, tp, fld, emin, emax, nbits)                  \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                     \
+{                                                                       \
+    ppc_vsr_t xa, xb;                                                   \
+    int i;                                                              \
+    int fe_flag = 0;                                                    \
+    int fg_flag = 0;                                                    \
+                                                                        \
+    getVSR(xA(opcode), &xa, env);                                       \
+    getVSR(xB(opcode), &xb, env);                                       \
+                                                                        \
+    for (i = 0; i < nels; i++) {                                        \
+        if (unlikely(tp##_is_infinity(xa.fld[i]) ||                     \
+                     tp##_is_infinity(xb.fld[i]) ||                     \
+                     tp##_is_zero(xb.fld[i]))) {                        \
+            fe_flag = 1;                                                \
+            fg_flag = 1;                                                \
+        } else {                                                        \
+            int e_a = ppc_##tp##_get_unbiased_exp(xa.fld[i]);           \
+            int e_b = ppc_##tp##_get_unbiased_exp(xb.fld[i]);           \
+                                                                        \
+            if (unlikely(tp##_is_any_nan(xa.fld[i]) ||                  \
+                         tp##_is_any_nan(xb.fld[i]))) {                 \
+                fe_flag = 1;                                            \
+            } else if ((e_b <= emin) || (e_b >= (emax-2))) {            \
+                fe_flag = 1;                                            \
+            } else if (!tp##_is_zero(xa.fld[i]) &&                      \
+                       (((e_a - e_b) >= emax) ||                        \
+                        ((e_a - e_b) <= (emin+1)) ||                    \
+                         (e_a <= (emin+nbits)))) {                      \
+                fe_flag = 1;                                            \
+            }                                                           \
+                                                                        \
+            if (unlikely(tp##_is_zero_or_denormal(xb.fld[i]))) {        \
+                /* XB is not zero because of the above check and */     \
+                /* so must be denormalized.                      */     \
+                fg_flag = 1;                                            \
+            }                                                           \
+        }                                                               \
+    }                                                                   \
+                                                                        \
+    env->crf[BF(opcode)] = 0x8 | (fg_flag ? 4 : 0) | (fe_flag ? 2 : 0); \
+}
+
+VSX_TDIV(xstdivdp, 1, float64, f64, -1022, 1023, 52)
+VSX_TDIV(xvtdivdp, 2, float64, f64, -1022, 1023, 52)
+VSX_TDIV(xvtdivsp, 4, float32, f32, -126, 127, 23)
target-ppc/helper.h +3 -0
index 4d5e31b..80cffc9 100644
@@ -258,6 +258,7 @@ DEF_HELPER_2(xsdivdp, void, env, i32)
 DEF_HELPER_2(xsredp, void, env, i32)
 DEF_HELPER_2(xssqrtdp, void, env, i32)
 DEF_HELPER_2(xsrsqrtedp, void, env, i32)
+DEF_HELPER_2(xstdivdp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
@@ -266,6 +267,7 @@ DEF_HELPER_2(xvdivdp, void, env, i32)
 DEF_HELPER_2(xvredp, void, env, i32)
 DEF_HELPER_2(xvsqrtdp, void, env, i32)
 DEF_HELPER_2(xvrsqrtedp, void, env, i32)
+DEF_HELPER_2(xvtdivdp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -274,6 +276,7 @@ DEF_HELPER_2(xvdivsp, void, env, i32)
 DEF_HELPER_2(xvresp, void, env, i32)
 DEF_HELPER_2(xvsqrtsp, void, env, i32)
 DEF_HELPER_2(xvrsqrtesp, void, env, i32)
+DEF_HELPER_2(xvtdivsp, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
target-ppc/translate.c +6 -0
index 287b924..9a0b36c 100644
@@ -7302,6 +7302,7 @@ GEN_VSX_HELPER_2(xsdivdp, 0x00, 0x07, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsredp, 0x14, 0x05, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xstdivdp, 0x14, 0x07, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -7310,6 +7311,7 @@ GEN_VSX_HELPER_2(xvdivdp, 0x00, 0x0F, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvredp, 0x14, 0x0D, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsqrtdp, 0x16, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvrsqrtedp, 0x14, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvtdivdp, 0x14, 0x0F, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
@@ -7318,6 +7320,7 @@ GEN_VSX_HELPER_2(xvdivsp, 0x00, 0x0B, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvresp, 0x14, 0x09, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsqrtsp, 0x16, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvrsqrtesp, 0x14, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvtdivsp, 0x14, 0x0B, 0, PPC2_VSX)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -10008,6 +10011,7 @@ GEN_XX3FORM(xsdivdp, 0x00, 0x07, PPC2_VSX),
 GEN_XX2FORM(xsredp,  0x14, 0x05, PPC2_VSX),
 GEN_XX2FORM(xssqrtdp,  0x16, 0x04, PPC2_VSX),
 GEN_XX2FORM(xsrsqrtedp,  0x14, 0x04, PPC2_VSX),
+GEN_XX3FORM(xstdivdp,  0x14, 0x07, PPC2_VSX),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
@@ -10016,6 +10020,7 @@ GEN_XX3FORM(xvdivdp, 0x00, 0x0F, PPC2_VSX),
 GEN_XX2FORM(xvredp,  0x14, 0x0D, PPC2_VSX),
 GEN_XX2FORM(xvsqrtdp,  0x16, 0x0C, PPC2_VSX),
 GEN_XX2FORM(xvrsqrtedp,  0x14, 0x0C, PPC2_VSX),
+GEN_XX3FORM(xvtdivdp, 0x14, 0x0F, PPC2_VSX),
 
 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
@@ -10024,6 +10029,7 @@ GEN_XX3FORM(xvdivsp, 0x00, 0x0B, PPC2_VSX),
 GEN_XX2FORM(xvresp, 0x14, 0x09, PPC2_VSX),
 GEN_XX2FORM(xvsqrtsp, 0x16, 0x08, PPC2_VSX),
 GEN_XX2FORM(xvrsqrtesp, 0x14, 0x08, PPC2_VSX),
+GEN_XX3FORM(xvtdivsp, 0x14, 0x0B, PPC2_VSX),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
Signature · 1 line
1.7.1
author
#22 lore raw

PATCH v4 15/22 target-ppc: Add VSX ISA2.06 xtsqrt Instructions

In reply to Tom Musta

This patch adds the VSX floating point test for software square root instructions defined by V2.06 of the PowerPC ISA: xstsqrtdp, xvtsqrtdp, xvtsqrtsp.

V2: (a) using locally implemented ppc_float*_get_unbiased_exp routines (b) eliminated dependency on float*_is_denormal().

---
 target-ppc/fpu_helper.c |   54 +++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    3 ++
 target-ppc/translate.c  |    6 +++++
 3 files changed, 63 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +54 -0
index ee03942..73227b7 100644
@@ -2095,3 +2095,57 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)                     \
 VSX_TDIV(xstdivdp, 1, float64, f64, -1022, 1023, 52)
 VSX_TDIV(xvtdivdp, 2, float64, f64, -1022, 1023, 52)
 VSX_TDIV(xvtdivsp, 4, float32, f32, -126, 127, 23)
+
+/* VSX_TSQRT - VSX floating point test for square root
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   emin  - minimum unbiased exponent
+ *   emax  - maximum unbiased exponent
+ *   nbits - number of fraction bits
+ */
+#define VSX_TSQRT(op, nels, tp, fld, emin, nbits)                       \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                     \
+{                                                                       \
+    ppc_vsr_t xa, xb;                                                   \
+    int i;                                                              \
+    int fe_flag = 0;                                                    \
+    int fg_flag = 0;                                                    \
+                                                                        \
+    getVSR(xA(opcode), &xa, env);                                       \
+    getVSR(xB(opcode), &xb, env);                                       \
+                                                                        \
+    for (i = 0; i < nels; i++) {                                        \
+        if (unlikely(tp##_is_infinity(xb.fld[i]) ||                     \
+                     tp##_is_zero(xb.fld[i]))) {                        \
+            fe_flag = 1;                                                \
+            fg_flag = 1;                                                \
+        } else {                                                        \
+            int e_b = ppc_##tp##_get_unbiased_exp(xb.fld[i]);           \
+                                                                        \
+            if (unlikely(tp##_is_any_nan(xb.fld[i]))) {                 \
+                fe_flag = 1;                                            \
+            } else if (unlikely(tp##_is_zero(xb.fld[i]))) {             \
+                fe_flag = 1;                                            \
+            } else if (unlikely(tp##_is_neg(xb.fld[i]))) {              \
+                fe_flag = 1;                                            \
+            } else if (!tp##_is_zero(xb.fld[i]) &&                      \
+                      (e_b <= (emin+nbits))) {                          \
+                fe_flag = 1;                                            \
+            }                                                           \
+                                                                        \
+            if (unlikely(tp##_is_zero_or_denormal(xb.fld[i]))) {        \
+                /* XB is not zero because of the above check and */     \
+                /* therefore must be denormalized.               */     \
+                fg_flag = 1;                                            \
+            }                                                           \
+        }                                                               \
+    }                                                                   \
+                                                                        \
+    env->crf[BF(opcode)] = 0x8 | (fg_flag ? 4 : 0) | (fe_flag ? 2 : 0); \
+}
+
+VSX_TSQRT(xstsqrtdp, 1, float64, f64, -1022, 52)
+VSX_TSQRT(xvtsqrtdp, 2, float64, f64, -1022, 52)
+VSX_TSQRT(xvtsqrtsp, 4, float32, f32, -126, 23)
target-ppc/helper.h +3 -0
index 80cffc9..c413c98 100644
@@ -259,6 +259,7 @@ DEF_HELPER_2(xsredp, void, env, i32)
 DEF_HELPER_2(xssqrtdp, void, env, i32)
 DEF_HELPER_2(xsrsqrtedp, void, env, i32)
 DEF_HELPER_2(xstdivdp, void, env, i32)
+DEF_HELPER_2(xstsqrtdp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
@@ -268,6 +269,7 @@ DEF_HELPER_2(xvredp, void, env, i32)
 DEF_HELPER_2(xvsqrtdp, void, env, i32)
 DEF_HELPER_2(xvrsqrtedp, void, env, i32)
 DEF_HELPER_2(xvtdivdp, void, env, i32)
+DEF_HELPER_2(xvtsqrtdp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -277,6 +279,7 @@ DEF_HELPER_2(xvresp, void, env, i32)
 DEF_HELPER_2(xvsqrtsp, void, env, i32)
 DEF_HELPER_2(xvrsqrtesp, void, env, i32)
 DEF_HELPER_2(xvtdivsp, void, env, i32)
+DEF_HELPER_2(xvtsqrtsp, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
target-ppc/translate.c +6 -0
index 9a0b36c..f1935c7 100644
@@ -7303,6 +7303,7 @@ GEN_VSX_HELPER_2(xsredp, 0x14, 0x05, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xstdivdp, 0x14, 0x07, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xstsqrtdp, 0x14, 0x06, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -7312,6 +7313,7 @@ GEN_VSX_HELPER_2(xvredp, 0x14, 0x0D, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsqrtdp, 0x16, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvrsqrtedp, 0x14, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvtdivdp, 0x14, 0x0F, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvtsqrtdp, 0x14, 0x0E, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
@@ -7321,6 +7323,7 @@ GEN_VSX_HELPER_2(xvresp, 0x14, 0x09, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsqrtsp, 0x16, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvrsqrtesp, 0x14, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvtdivsp, 0x14, 0x0B, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvtsqrtsp, 0x14, 0x0A, 0, PPC2_VSX)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -10012,6 +10015,7 @@ GEN_XX2FORM(xsredp,  0x14, 0x05, PPC2_VSX),
 GEN_XX2FORM(xssqrtdp,  0x16, 0x04, PPC2_VSX),
 GEN_XX2FORM(xsrsqrtedp,  0x14, 0x04, PPC2_VSX),
 GEN_XX3FORM(xstdivdp,  0x14, 0x07, PPC2_VSX),
+GEN_XX2FORM(xstsqrtdp,  0x14, 0x06, PPC2_VSX),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
@@ -10021,6 +10025,7 @@ GEN_XX2FORM(xvredp,  0x14, 0x0D, PPC2_VSX),
 GEN_XX2FORM(xvsqrtdp,  0x16, 0x0C, PPC2_VSX),
 GEN_XX2FORM(xvrsqrtedp,  0x14, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvtdivdp, 0x14, 0x0F, PPC2_VSX),
+GEN_XX2FORM(xvtsqrtdp, 0x14, 0x0E, PPC2_VSX),
 
 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
@@ -10030,6 +10035,7 @@ GEN_XX2FORM(xvresp, 0x14, 0x09, PPC2_VSX),
 GEN_XX2FORM(xvsqrtsp, 0x16, 0x08, PPC2_VSX),
 GEN_XX2FORM(xvrsqrtesp, 0x14, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvtdivsp, 0x14, 0x0B, PPC2_VSX),
+GEN_XX2FORM(xvtsqrtsp, 0x14, 0x0A, PPC2_VSX),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
Signature · 1 line
1.7.1
author
#23 lore raw

PATCH v4 16/22 target-ppc: Add VSX ISA2.06 Multiply Add Instructions

In reply to Tom Musta

This patch adds the VSX floating point multiply/add instructions defined by V2.06 of the PowerPC ISA:

  - xsmaddadp,  xvmaddadp,  xvmaddasp
  - xsmaddmdp,  xvmaddmdp,  xvmaddmsp
  - xsmsubadp,  xvmsubadp,  xvmsubasp
  - xsmsubmdp,  xvmsubmdp,  xvmsubmsp

- xsnmaddadp, xvnmaddadp, xvnmaddasp
- xsnmaddmdp, xvnmaddmdp, xvnmaddmsp
- xsnmsubadp, xvnmsubadp, xvnmsubasp
- xsnmsubmdp, xvnmsubmdp, xvnmsubmsp

V2: reworked implementation per comments from Richard Henderson and Peter Maydell.

---
 target-ppc/fpu_helper.c |  100 +++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |   24 +++++++++++
 target-ppc/translate.c  |   48 ++++++++++++++++++++++
 3 files changed, 172 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +100 -0
index 73227b7..54c47c8 100644
@@ -2149,3 +2149,103 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)                     \
 VSX_TSQRT(xstsqrtdp, 1, float64, f64, -1022, 52)
 VSX_TSQRT(xvtsqrtdp, 2, float64, f64, -1022, 52)
 VSX_TSQRT(xvtsqrtsp, 4, float32, f32, -126, 23)
+
+/* VSX_MADD - VSX floating point muliply/add variations
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   maddflgs - flags for the float*muladd routine that control the
+ *           various forms (madd, msub, nmadd, nmsub)
+ *   afrm  - A form (1=A, 0=M)
+ *   sfprf - set FPRF
+ */
+#define VSX_MADD(op, nels, tp, fld, maddflgs, afrm, sfprf)                    \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                           \
+{                                                                             \
+    ppc_vsr_t xt_in, xa, xb, xt_out;                                          \
+    ppc_vsr_t *b, *c;                                                         \
+    int i;                                                                    \
+                                                                              \
+    if (afrm) { /* AxB + T */                                                 \
+        b = &xb;                                                              \
+        c = &xt_in;                                                           \
+    } else { /* AxT + B */                                                    \
+        b = &xt_in;                                                           \
+        c = &xb;                                                              \
+    }                                                                         \
+                                                                              \
+    getVSR(xA(opcode), &xa, env);                                             \
+    getVSR(xB(opcode), &xb, env);                                             \
+    getVSR(xT(opcode), &xt_in, env);                                          \
+                                                                              \
+    xt_out = xt_in;                                                           \
+                                                                              \
+    helper_reset_fpstatus(env);                                               \
+                                                                              \
+    for (i = 0; i < nels; i++) {                                              \
+        float_status tstat = env->fp_status;                                  \
+        set_float_exception_flags(0, &tstat);                                 \
+        xt_out.fld[i] = tp##_muladd(xa.fld[i], b->fld[i], c->fld[i],          \
+                                     maddflgs, &tstat);                       \
+        env->fp_status.float_exception_flags |= tstat.float_exception_flags;  \
+                                                                              \
+        if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {     \
+            if (tp##_is_signaling_nan(xa.fld[i]) ||                           \
+                tp##_is_signaling_nan(b->fld[i]) ||                           \
+                tp##_is_signaling_nan(c->fld[i])) {                           \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, sfprf);    \
+                tstat.float_exception_flags &= ~float_flag_invalid;           \
+            }                                                                 \
+            if ((tp##_is_infinity(xa.fld[i]) && tp##_is_zero(b->fld[i])) ||   \
+                (tp##_is_zero(xa.fld[i]) && tp##_is_infinity(b->fld[i]))) {   \
+                xt_out.fld[i] = float64_to_##tp(fload_invalid_op_excp(env,    \
+                    POWERPC_EXCP_FP_VXIMZ, sfprf), &env->fp_status);          \
+                tstat.float_exception_flags &= ~float_flag_invalid;           \
+            }                                                                 \
+            if ((tstat.float_exception_flags & float_flag_invalid) &&         \
+                ((tp##_is_infinity(xa.fld[i]) ||                              \
+                  tp##_is_infinity(b->fld[i])) &&                             \
+                  tp##_is_infinity(c->fld[i]))) {                             \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI, sfprf);     \
+            }                                                                 \
+        }                                                                     \
+        if (sfprf) {                                                          \
+            helper_compute_fprf(env, xt_out.fld[i], sfprf);                   \
+        }                                                                     \
+    }                                                                         \
+    putVSR(xT(opcode), &xt_out, env);                                         \
+    helper_float_check_status(env);                                           \
+}
+
+#define MADD_FLGS 0
+#define MSUB_FLGS float_muladd_negate_c
+#define NMADD_FLGS float_muladd_negate_result
+#define NMSUB_FLGS (float_muladd_negate_c | float_muladd_negate_result)
+
+VSX_MADD(xsmaddadp, 1, float64, f64, MADD_FLGS, 1, 1)
+VSX_MADD(xsmaddmdp, 1, float64, f64, MADD_FLGS, 0, 1)
+VSX_MADD(xsmsubadp, 1, float64, f64, MSUB_FLGS, 1, 1)
+VSX_MADD(xsmsubmdp, 1, float64, f64, MSUB_FLGS, 0, 1)
+VSX_MADD(xsnmaddadp, 1, float64, f64, NMADD_FLGS, 1, 1)
+VSX_MADD(xsnmaddmdp, 1, float64, f64, NMADD_FLGS, 0, 1)
+VSX_MADD(xsnmsubadp, 1, float64, f64, NMSUB_FLGS, 1, 1)
+VSX_MADD(xsnmsubmdp, 1, float64, f64, NMSUB_FLGS, 0, 1)
+
+VSX_MADD(xvmaddadp, 2, float64, f64, MADD_FLGS, 1, 0)
+VSX_MADD(xvmaddmdp, 2, float64, f64, MADD_FLGS, 0, 0)
+VSX_MADD(xvmsubadp, 2, float64, f64, MSUB_FLGS, 1, 0)
+VSX_MADD(xvmsubmdp, 2, float64, f64, MSUB_FLGS, 0, 0)
+VSX_MADD(xvnmaddadp, 2, float64, f64, NMADD_FLGS, 1, 0)
+VSX_MADD(xvnmaddmdp, 2, float64, f64, NMADD_FLGS, 0, 0)
+VSX_MADD(xvnmsubadp, 2, float64, f64, NMSUB_FLGS, 1, 0)
+VSX_MADD(xvnmsubmdp, 2, float64, f64, NMSUB_FLGS, 0, 0)
+
+VSX_MADD(xvmaddasp, 4, float32, f32, MADD_FLGS, 1, 0)
+VSX_MADD(xvmaddmsp, 4, float32, f32, MADD_FLGS, 0, 0)
+VSX_MADD(xvmsubasp, 4, float32, f32, MSUB_FLGS, 1, 0)
+VSX_MADD(xvmsubmsp, 4, float32, f32, MSUB_FLGS, 0, 0)
+VSX_MADD(xvnmaddasp, 4, float32, f32, NMADD_FLGS, 1, 0)
+VSX_MADD(xvnmaddmsp, 4, float32, f32, NMADD_FLGS, 0, 0)
+VSX_MADD(xvnmsubasp, 4, float32, f32, NMSUB_FLGS, 1, 0)
+VSX_MADD(xvnmsubmsp, 4, float32, f32, NMSUB_FLGS, 0, 0)
target-ppc/helper.h +24 -0
index c413c98..7368908 100644
@@ -260,6 +260,14 @@ DEF_HELPER_2(xssqrtdp, void, env, i32)
 DEF_HELPER_2(xsrsqrtedp, void, env, i32)
 DEF_HELPER_2(xstdivdp, void, env, i32)
 DEF_HELPER_2(xstsqrtdp, void, env, i32)
+DEF_HELPER_2(xsmaddadp, void, env, i32)
+DEF_HELPER_2(xsmaddmdp, void, env, i32)
+DEF_HELPER_2(xsmsubadp, void, env, i32)
+DEF_HELPER_2(xsmsubmdp, void, env, i32)
+DEF_HELPER_2(xsnmaddadp, void, env, i32)
+DEF_HELPER_2(xsnmaddmdp, void, env, i32)
+DEF_HELPER_2(xsnmsubadp, void, env, i32)
+DEF_HELPER_2(xsnmsubmdp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
@@ -270,6 +278,14 @@ DEF_HELPER_2(xvsqrtdp, void, env, i32)
 DEF_HELPER_2(xvrsqrtedp, void, env, i32)
 DEF_HELPER_2(xvtdivdp, void, env, i32)
 DEF_HELPER_2(xvtsqrtdp, void, env, i32)
+DEF_HELPER_2(xvmaddadp, void, env, i32)
+DEF_HELPER_2(xvmaddmdp, void, env, i32)
+DEF_HELPER_2(xvmsubadp, void, env, i32)
+DEF_HELPER_2(xvmsubmdp, void, env, i32)
+DEF_HELPER_2(xvnmaddadp, void, env, i32)
+DEF_HELPER_2(xvnmaddmdp, void, env, i32)
+DEF_HELPER_2(xvnmsubadp, void, env, i32)
+DEF_HELPER_2(xvnmsubmdp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -280,6 +296,14 @@ DEF_HELPER_2(xvsqrtsp, void, env, i32)
 DEF_HELPER_2(xvrsqrtesp, void, env, i32)
 DEF_HELPER_2(xvtdivsp, void, env, i32)
 DEF_HELPER_2(xvtsqrtsp, void, env, i32)
+DEF_HELPER_2(xvmaddasp, void, env, i32)
+DEF_HELPER_2(xvmaddmsp, void, env, i32)
+DEF_HELPER_2(xvmsubasp, void, env, i32)
+DEF_HELPER_2(xvmsubmsp, void, env, i32)
+DEF_HELPER_2(xvnmaddasp, void, env, i32)
+DEF_HELPER_2(xvnmaddmsp, void, env, i32)
+DEF_HELPER_2(xvnmsubasp, void, env, i32)
+DEF_HELPER_2(xvnmsubmsp, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
target-ppc/translate.c +48 -0

84 lines not on this page · raw message

Signature · 1 line
1.7.1
author
#24 lore raw

PATCH v4 17/22 target-ppc: Add VSX xscmp*dp Instructions

In reply to Tom Musta

This patch adds the VSX scalar floating point compare ordered and unordered instructions.

---
 target-ppc/fpu_helper.c |   39 +++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    2 ++
 target-ppc/translate.c  |    4 ++++
 3 files changed, 45 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +39 -0
index 54c47c8..eb5d878 100644
@@ -2249,3 +2249,42 @@ VSX_MADD(xvnmaddasp, 4, float32, f32, NMADD_FLGS, 1, 0)
 VSX_MADD(xvnmaddmsp, 4, float32, f32, NMADD_FLGS, 0, 0)
 VSX_MADD(xvnmsubasp, 4, float32, f32, NMSUB_FLGS, 1, 0)
 VSX_MADD(xvnmsubmsp, 4, float32, f32, NMSUB_FLGS, 0, 0)
+
+#define VSX_SCALAR_CMP(op, ordered)                                      \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                      \
+{                                                                        \
+    ppc_vsr_t xa, xb;                                                    \
+    uint32_t cc = 0;                                                     \
+                                                                         \
+    getVSR(xA(opcode), &xa, env);                                        \
+    getVSR(xB(opcode), &xb, env);                                        \
+                                                                         \
+    if (unlikely(float64_is_any_nan(xa.f64[0]) ||                        \
+                 float64_is_any_nan(xb.f64[0]))) {                       \
+        if (float64_is_signaling_nan(xa.f64[0]) ||                       \
+            float64_is_signaling_nan(xb.f64[0])) {                       \
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);       \
+        }                                                                \
+        if (ordered) {                                                   \
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXVC, 0);         \
+        }                                                                \
+        cc = 1;                                                          \
+    } else {                                                             \
+        if (float64_lt(xa.f64[0], xb.f64[0], &env->fp_status)) {         \
+            cc = 8;                                                      \
+        } else if (!float64_le(xa.f64[0], xb.f64[0], &env->fp_status)) { \
+            cc = 4;                                                      \
+        } else {                                                         \
+            cc = 2;                                                      \
+        }                                                                \
+    }                                                                    \
+                                                                         \
+    env->fpscr &= ~(0x0F << FPSCR_FPRF);                                 \
+    env->fpscr |= cc << FPSCR_FPRF;                                      \
+    env->crf[BF(opcode)] = cc;                                           \
+                                                                         \
+    helper_float_check_status(env);                                      \
+}
+
+VSX_SCALAR_CMP(xscmpodp, 1)
+VSX_SCALAR_CMP(xscmpudp, 0)
target-ppc/helper.h +2 -0
index 7368908..cd72388 100644
@@ -268,6 +268,8 @@ DEF_HELPER_2(xsnmaddadp, void, env, i32)
 DEF_HELPER_2(xsnmaddmdp, void, env, i32)
 DEF_HELPER_2(xsnmsubadp, void, env, i32)
 DEF_HELPER_2(xsnmsubmdp, void, env, i32)
+DEF_HELPER_2(xscmpodp, void, env, i32)
+DEF_HELPER_2(xscmpudp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
target-ppc/translate.c +4 -0
index 3a62125..a2a4e2d 100644
@@ -7312,6 +7312,8 @@ GEN_VSX_HELPER_2(xsnmaddadp, 0x04, 0x14, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsnmaddmdp, 0x04, 0x15, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsnmsubadp, 0x04, 0x16, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsnmsubmdp, 0x04, 0x17, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xscmpodp, 0x0C, 0x05, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xscmpudp, 0x0C, 0x04, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -10048,6 +10050,8 @@ GEN_XX3FORM(xsnmaddadp, 0x04, 0x14, PPC2_VSX),
 GEN_XX3FORM(xsnmaddmdp, 0x04, 0x15, PPC2_VSX),
 GEN_XX3FORM(xsnmsubadp, 0x04, 0x16, PPC2_VSX),
 GEN_XX3FORM(xsnmsubmdp, 0x04, 0x17, PPC2_VSX),
+GEN_XX2FORM(xscmpodp,  0x0C, 0x05, PPC2_VSX),
+GEN_XX2FORM(xscmpudp,  0x0C, 0x04, PPC2_VSX),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
Signature · 1 line
1.7.1
author
#25 lore raw

PATCH v4 18/22 target-ppc: Add VSX xmax/xmin Instructions

In reply to Tom Musta

This patch adds the VSX floating point maximum and minimum instructions:

- xsmaxdp, xvmaxdp, xvmaxsp
- xsmindp, xvmindp, xvminsp

Because of the Power ISA definitions of maximum and minimum on various boundary cases, the standard softfloat comparison routines (e.g. float64_lt) do not work as well as one might think. Therefore specific routines for comparing 64 and 32 bit floating point numbers are implemented in the PowerPC helper code.

V2: consolidated into a single macro, using the softfloat float*_max/float*_min routines.

---
 target-ppc/fpu_helper.c |   50 +++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    6 +++++
 target-ppc/translate.c  |   12 +++++++++++
 3 files changed, 68 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +50 -0
index eb5d878..b90541c 100644
@@ -2288,3 +2288,53 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)                      \
 
 VSX_SCALAR_CMP(xscmpodp, 1)
 VSX_SCALAR_CMP(xscmpudp, 0)
+
+#define float64_snan_to_qnan(x) ((x) | 0x0008000000000000ul)
+#define float32_snan_to_qnan(x) ((x) | 0x00400000)
+
+/* VSX_MAX_MIN - VSX floating point maximum/minimum
+ *   name  - instruction mnemonic
+ *   op    - operation (max or min)
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ */
+#define VSX_MAX_MIN(name, op, nels, tp, fld)                                  \
+void helper_##name(CPUPPCState *env, uint32_t opcode)                         \
+{                                                                             \
+    ppc_vsr_t xt, xa, xb;                                                     \
+    int i;                                                                    \
+                                                                              \
+    getVSR(xA(opcode), &xa, env);                                             \
+    getVSR(xB(opcode), &xb, env);                                             \
+    getVSR(xT(opcode), &xt, env);                                             \
+                                                                              \
+    for (i = 0; i < nels; i++) {                                              \
+        if (unlikely(tp##_is_any_nan(xa.fld[i]) ||                            \
+                     tp##_is_any_nan(xb.fld[i]))) {                           \
+            if (tp##_is_signaling_nan(xa.fld[i])) {                           \
+                xt.fld[i] = tp##_snan_to_qnan(xa.fld[i]);                     \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);        \
+            } else if (tp##_is_signaling_nan(xb.fld[i])) {                    \
+                xt.fld[i] = tp##_snan_to_qnan(xb.fld[i]);                     \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);        \
+            } else if (tp##_is_quiet_nan(xb.fld[i])) {                        \
+                xt.fld[i] = xa.fld[i];                                        \
+            } else { /* XA is QNaN */                                         \
+                xt.fld[i] = xb.fld[i];                                        \
+            }                                                                 \
+        } else {                                                              \
+            xt.fld[i] = tp##_##op(xa.fld[i], xb.fld[i], &env->fp_status);     \
+        }                                                                     \
+    }                                                                         \
+                                                                              \
+    putVSR(xT(opcode), &xt, env);                                             \
+    helper_float_check_status(env);                                           \
+}
+
+VSX_MAX_MIN(xsmaxdp, max, 1, float64, f64)
+VSX_MAX_MIN(xvmaxdp, max, 2, float64, f64)
+VSX_MAX_MIN(xvmaxsp, max, 4, float32, f32)
+VSX_MAX_MIN(xsmindp, min, 1, float64, f64)
+VSX_MAX_MIN(xvmindp, min, 2, float64, f64)
+VSX_MAX_MIN(xvminsp, min, 4, float32, f32)
target-ppc/helper.h +6 -0
index cd72388..4a65d39 100644
@@ -270,6 +270,8 @@ DEF_HELPER_2(xsnmsubadp, void, env, i32)
 DEF_HELPER_2(xsnmsubmdp, void, env, i32)
 DEF_HELPER_2(xscmpodp, void, env, i32)
 DEF_HELPER_2(xscmpudp, void, env, i32)
+DEF_HELPER_2(xsmaxdp, void, env, i32)
+DEF_HELPER_2(xsmindp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
@@ -288,6 +290,8 @@ DEF_HELPER_2(xvnmaddadp, void, env, i32)
 DEF_HELPER_2(xvnmaddmdp, void, env, i32)
 DEF_HELPER_2(xvnmsubadp, void, env, i32)
 DEF_HELPER_2(xvnmsubmdp, void, env, i32)
+DEF_HELPER_2(xvmaxdp, void, env, i32)
+DEF_HELPER_2(xvmindp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -306,6 +310,8 @@ DEF_HELPER_2(xvnmaddasp, void, env, i32)
 DEF_HELPER_2(xvnmaddmsp, void, env, i32)
 DEF_HELPER_2(xvnmsubasp, void, env, i32)
 DEF_HELPER_2(xvnmsubmsp, void, env, i32)
+DEF_HELPER_2(xvmaxsp, void, env, i32)
+DEF_HELPER_2(xvminsp, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
target-ppc/translate.c +12 -0
index a2a4e2d..10c238a 100644
@@ -7314,6 +7314,8 @@ GEN_VSX_HELPER_2(xsnmsubadp, 0x04, 0x16, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsnmsubmdp, 0x04, 0x17, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xscmpodp, 0x0C, 0x05, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xscmpudp, 0x0C, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsmaxdp, 0x00, 0x14, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsmindp, 0x00, 0x15, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -7332,6 +7334,8 @@ GEN_VSX_HELPER_2(xvnmaddadp, 0x04, 0x1C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvnmaddmdp, 0x04, 0x1D, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvnmsubadp, 0x04, 0x1E, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvnmsubmdp, 0x04, 0x1F, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvmaxdp, 0x00, 0x1C, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvmindp, 0x00, 0x1D, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
@@ -7350,6 +7354,8 @@ GEN_VSX_HELPER_2(xvnmaddasp, 0x04, 0x18, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvnmaddmsp, 0x04, 0x19, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvnmsubasp, 0x04, 0x1A, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvnmsubmsp, 0x04, 0x1B, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvmaxsp, 0x00, 0x18, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvminsp, 0x00, 0x19, 0, PPC2_VSX)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -10052,6 +10058,8 @@ GEN_XX3FORM(xsnmsubadp, 0x04, 0x16, PPC2_VSX),
 GEN_XX3FORM(xsnmsubmdp, 0x04, 0x17, PPC2_VSX),
 GEN_XX2FORM(xscmpodp,  0x0C, 0x05, PPC2_VSX),
 GEN_XX2FORM(xscmpudp,  0x0C, 0x04, PPC2_VSX),
+GEN_XX3FORM(xsmaxdp, 0x00, 0x14, PPC2_VSX),
+GEN_XX3FORM(xsmindp, 0x00, 0x15, PPC2_VSX),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
@@ -10070,6 +10078,8 @@ GEN_XX3FORM(xvnmaddadp, 0x04, 0x1C, PPC2_VSX),
 GEN_XX3FORM(xvnmaddmdp, 0x04, 0x1D, PPC2_VSX),
 GEN_XX3FORM(xvnmsubadp, 0x04, 0x1E, PPC2_VSX),
 GEN_XX3FORM(xvnmsubmdp, 0x04, 0x1F, PPC2_VSX),
+GEN_XX3FORM(xvmaxdp, 0x00, 0x1C, PPC2_VSX),
+GEN_XX3FORM(xvmindp, 0x00, 0x1D, PPC2_VSX),
 
 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
@@ -10088,6 +10098,8 @@ GEN_XX3FORM(xvnmaddasp, 0x04, 0x18, PPC2_VSX),
 GEN_XX3FORM(xvnmaddmsp, 0x04, 0x19, PPC2_VSX),
 GEN_XX3FORM(xvnmsubasp, 0x04, 0x1A, PPC2_VSX),
 GEN_XX3FORM(xvnmsubmsp, 0x04, 0x1B, PPC2_VSX),
+GEN_XX3FORM(xvmaxsp, 0x00, 0x18, PPC2_VSX),
+GEN_XX3FORM(xvminsp, 0x00, 0x19, PPC2_VSX),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
Signature · 1 line
1.7.1
#26 lore raw

Re: [Qemu-devel] [V4 PATCH 18/22] target-ppc: Add VSX xmax/xmin Instructions

Quoted 6 lines · Tom Musta
target-ppc/fpu_helper.c +6 -0
+        if (unlikely(tp##_is_any_nan(xa.fld[i]) ||                            \
+                     tp##_is_any_nan(xb.fld[i]))) {                           \
+            if (tp##_is_signaling_nan(xa.fld[i])) {                           \
+                xt.fld[i] = tp##_snan_to_qnan(xa.fld[i]);                     \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);        \
+            } else if (tp##_is_signaling_nan(xb.fld[i])) {                    \

target-ppc/fpu_helper.c void helper_##op(CPUPPCState *env, uint32_t opcode) \ · line 2328

Quoted 10 lines
target-ppc/fpu_helper.c +10 -0
+                xt.fld[i] = tp##_snan_to_qnan(xb.fld[i]);                     \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);        \
+            } else if (tp##_is_quiet_nan(xb.fld[i])) {                        \
+                xt.fld[i] = xa.fld[i];                                        \
+            } else { /* XA is QNaN */                                         \
+                xt.fld[i] = xb.fld[i];                                        \
+            }                                                                 \
+        } else {                                                              \
+            xt.fld[i] = tp##_##op(xa.fld[i], xb.fld[i], &env->fp_status);     \
+        }                                                                     \

We have minnum/maxnum now.

r~

author
#27 lore raw

PATCH v4 19/22 target-ppc: Add VSX Vector Compare Instructions

In reply to Tom Musta

This patch adds the VSX floating point compare vector instructions:

- xvcmpeqdp[.], xvcmpgedp[.], xvcmpgtdp[.]
- xvcmpeqsp[.], xvcmpgesp[.], xvcmpgtsp[.]

---
 target-ppc/fpu_helper.c |   57 +++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    6 +++++
 target-ppc/translate.c  |   23 +++++++++++++++++++
 3 files changed, 86 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +57 -0
index b90541c..ec1df4f 100644
@@ -2338,3 +2338,60 @@ VSX_MAX_MIN(xvmaxsp, max, 4, float32, f32)
 VSX_MAX_MIN(xsmindp, min, 1, float64, f64)
 VSX_MAX_MIN(xvmindp, min, 2, float64, f64)
 VSX_MAX_MIN(xvminsp, min, 4, float32, f32)
+
+/* VSX_CMP - VSX floating point compare
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   cmp   - comparison operation
+ *   svxvc - set VXVC bit
+ */
+#define VSX_CMP(op, nels, tp, fld, cmp, svxvc)                            \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                       \
+{                                                                         \
+    ppc_vsr_t xt, xa, xb;                                                 \
+    int i;                                                                \
+    int all_true = 1;                                                     \
+    int all_false = 1;                                                    \
+                                                                          \
+    getVSR(xA(opcode), &xa, env);                                         \
+    getVSR(xB(opcode), &xb, env);                                         \
+    getVSR(xT(opcode), &xt, env);                                         \
+                                                                          \
+    for (i = 0; i < nels; i++) {                                          \
+        if (unlikely(tp##_is_any_nan(xa.fld[i]) ||                        \
+                     tp##_is_any_nan(xb.fld[i]))) {                       \
+            if (tp##_is_signaling_nan(xa.fld[i]) ||                       \
+                tp##_is_signaling_nan(xb.fld[i])) {                       \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);    \
+            }                                                             \
+            if (svxvc) {                                                  \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXVC, 0);      \
+            }                                                             \
+            xt.fld[i] = 0;                                                \
+            all_true = 0;                                                 \
+        } else {                                                          \
+            if (tp##_##cmp(xb.fld[i], xa.fld[i], &env->fp_status) == 1) { \
+                xt.fld[i] = -1;                                           \
+                all_false = 0;                                            \
+            } else {                                                      \
+                xt.fld[i] = 0;                                            \
+                all_true = 0;                                             \
+            }                                                             \
+        }                                                                 \
+    }                                                                     \
+                                                                          \
+    putVSR(xT(opcode), &xt, env);                                         \
+    if ((opcode >> (31-21)) & 1) {                                        \
+        env->crf[6] = (all_true ? 0x8 : 0) | (all_false ? 0x2 : 0);       \
+    }                                                                     \
+    helper_float_check_status(env);                                       \
+ }
+
+VSX_CMP(xvcmpeqdp, 2, float64, f64, eq, 0)
+VSX_CMP(xvcmpgedp, 2, float64, f64, le, 1)
+VSX_CMP(xvcmpgtdp, 2, float64, f64, lt, 1)
+VSX_CMP(xvcmpeqsp, 4, float32, f32, eq, 0)
+VSX_CMP(xvcmpgesp, 4, float32, f32, le, 1)
+VSX_CMP(xvcmpgtsp, 4, float32, f32, lt, 1)
target-ppc/helper.h +6 -0
index 4a65d39..35389c5 100644
@@ -292,6 +292,9 @@ DEF_HELPER_2(xvnmsubadp, void, env, i32)
 DEF_HELPER_2(xvnmsubmdp, void, env, i32)
 DEF_HELPER_2(xvmaxdp, void, env, i32)
 DEF_HELPER_2(xvmindp, void, env, i32)
+DEF_HELPER_2(xvcmpeqdp, void, env, i32)
+DEF_HELPER_2(xvcmpgedp, void, env, i32)
+DEF_HELPER_2(xvcmpgtdp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -312,6 +315,9 @@ DEF_HELPER_2(xvnmsubasp, void, env, i32)
 DEF_HELPER_2(xvnmsubmsp, void, env, i32)
 DEF_HELPER_2(xvmaxsp, void, env, i32)
 DEF_HELPER_2(xvminsp, void, env, i32)
+DEF_HELPER_2(xvcmpeqsp, void, env, i32)
+DEF_HELPER_2(xvcmpgesp, void, env, i32)
+DEF_HELPER_2(xvcmpgtsp, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
target-ppc/translate.c +23 -0
index 10c238a..377a482 100644
@@ -7336,6 +7336,9 @@ GEN_VSX_HELPER_2(xvnmsubadp, 0x04, 0x1E, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvnmsubmdp, 0x04, 0x1F, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmaxdp, 0x00, 0x1C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmindp, 0x00, 0x1D, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcmpeqdp, 0x0C, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcmpgtdp, 0x0C, 0x0D, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcmpgedp, 0x0C, 0x0E, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
@@ -7356,6 +7359,9 @@ GEN_VSX_HELPER_2(xvnmsubasp, 0x04, 0x1A, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvnmsubmsp, 0x04, 0x1B, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmaxsp, 0x00, 0x18, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvminsp, 0x00, 0x19, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcmpeqsp, 0x0C, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcmpgtsp, 0x0C, 0x09, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcmpgesp, 0x0C, 0x0A, 0, PPC2_VSX)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -10006,6 +10012,17 @@ GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 1, opc3, 0, PPC_NONE, fl2), \
 GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 2, opc3, 0, PPC_NONE, fl2), \
 GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 3, opc3, 0, PPC_NONE, fl2)
 
+#undef GEN_XX3_RC_FORM
+#define GEN_XX3_RC_FORM(name, opc2, opc3, fl2)                          \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x00, opc3 | 0x00, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x01, opc3 | 0x00, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x02, opc3 | 0x00, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x03, opc3 | 0x00, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x00, opc3 | 0x10, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x01, opc3 | 0x10, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x02, opc3 | 0x10, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x03, opc3 | 0x10, 0, PPC_NONE, fl2)
+
 #undef GEN_XX3FORM_DM
 #define GEN_XX3FORM_DM(name, opc2, opc3) \
 GEN_HANDLER2_E(name, #name, 0x3C, opc2|0x00, opc3|0x00, 0, PPC_NONE, PPC2_VSX),\
@@ -10080,6 +10097,9 @@ GEN_XX3FORM(xvnmsubadp, 0x04, 0x1E, PPC2_VSX),
 GEN_XX3FORM(xvnmsubmdp, 0x04, 0x1F, PPC2_VSX),
 GEN_XX3FORM(xvmaxdp, 0x00, 0x1C, PPC2_VSX),
 GEN_XX3FORM(xvmindp, 0x00, 0x1D, PPC2_VSX),
+GEN_XX3_RC_FORM(xvcmpeqdp, 0x0C, 0x0C, PPC2_VSX),
+GEN_XX3_RC_FORM(xvcmpgtdp, 0x0C, 0x0D, PPC2_VSX),
+GEN_XX3_RC_FORM(xvcmpgedp, 0x0C, 0x0E, PPC2_VSX),
 
 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
@@ -10100,6 +10120,9 @@ GEN_XX3FORM(xvnmsubasp, 0x04, 0x1A, PPC2_VSX),
 GEN_XX3FORM(xvnmsubmsp, 0x04, 0x1B, PPC2_VSX),
 GEN_XX3FORM(xvmaxsp, 0x00, 0x18, PPC2_VSX),
 GEN_XX3FORM(xvminsp, 0x00, 0x19, PPC2_VSX),
+GEN_XX3_RC_FORM(xvcmpeqsp, 0x0C, 0x08, PPC2_VSX),
+GEN_XX3_RC_FORM(xvcmpgtsp, 0x0C, 0x09, PPC2_VSX),
+GEN_XX3_RC_FORM(xvcmpgesp, 0x0C, 0x0A, PPC2_VSX),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
Signature · 1 line
1.7.1
author
#28 lore raw

PATCH v4 20/22 target-ppc: Add VSX Floating Point to Floating Point Conversion Instructions

In reply to Tom Musta

This patch adds the VSX instructions that convert between floating point formats: xscvdpsp, xscvspdp, xvcvdpsp, xvcvspdp.

---
 target-ppc/fpu_helper.c |   46 ++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    4 ++++
 target-ppc/translate.c  |    8 ++++++++
 3 files changed, 58 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +46 -0
index ec1df4f..c9fb59f 100644
@@ -2395,3 +2395,49 @@ VSX_CMP(xvcmpgtdp, 2, float64, f64, lt, 1)
 VSX_CMP(xvcmpeqsp, 4, float32, f32, eq, 0)
 VSX_CMP(xvcmpgesp, 4, float32, f32, le, 1)
 VSX_CMP(xvcmpgtsp, 4, float32, f32, lt, 1)
+
+#if defined(HOST_WORDS_BIGENDIAN)
+#define JOFFSET 0
+#else
+#define JOFFSET 1
+#endif
+
+/* VSX_CVT_FP_TO_FP - VSX floating point/floating point conversion
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   stp   - source type (float32 or float64)
+ *   ttp   - target type (float32 or float64)
+ *   sfld  - source vsr_t field
+ *   tfld  - target vsr_t field (f32 or f64)
+ *   sfprf - set FPRF
+ */
+#define VSX_CVT_FP_TO_FP(op, nels, stp, ttp, sfld, tfld, sfprf)    \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                \
+{                                                                  \
+    ppc_vsr_t xt, xb;                                              \
+    int i;                                                         \
+                                                                   \
+    getVSR(xB(opcode), &xb, env);                                  \
+    getVSR(xT(opcode), &xt, env);                                  \
+                                                                   \
+    for (i = 0; i < nels; i++) {                                   \
+        int j = 2*i + JOFFSET;                                     \
+        xt.tfld = stp##_to_##ttp(xb.sfld, &env->fp_status);        \
+        if (unlikely(stp##_is_signaling_nan(xb.sfld))) {           \
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0); \
+            xt.tfld = ttp##_snan_to_qnan(xt.tfld);                 \
+        }                                                          \
+        if (sfprf) {                                               \
+            helper_compute_fprf(env, ttp##_to_float64(xt.tfld,     \
+                                &env->fp_status), sfprf);          \
+        }                                                          \
+    }                                                              \
+                                                                   \
+    putVSR(xT(opcode), &xt, env);                                  \
+    helper_float_check_status(env);                                \
+}
+
+VSX_CVT_FP_TO_FP(xscvdpsp, 1, float64, float32, f64[i], f32[j], 1)
+VSX_CVT_FP_TO_FP(xscvspdp, 1, float32, float64, f32[j], f64[i], 1)
+VSX_CVT_FP_TO_FP(xvcvdpsp, 2, float64, float32, f64[i], f32[j], 0)
+VSX_CVT_FP_TO_FP(xvcvspdp, 2, float32, float64, f32[j], f64[i], 0)
target-ppc/helper.h +4 -0
index 35389c5..dd9518c 100644
@@ -272,6 +272,8 @@ DEF_HELPER_2(xscmpodp, void, env, i32)
 DEF_HELPER_2(xscmpudp, void, env, i32)
 DEF_HELPER_2(xsmaxdp, void, env, i32)
 DEF_HELPER_2(xsmindp, void, env, i32)
+DEF_HELPER_2(xscvdpsp, void, env, i32)
+DEF_HELPER_2(xscvspdp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
@@ -295,6 +297,7 @@ DEF_HELPER_2(xvmindp, void, env, i32)
 DEF_HELPER_2(xvcmpeqdp, void, env, i32)
 DEF_HELPER_2(xvcmpgedp, void, env, i32)
 DEF_HELPER_2(xvcmpgtdp, void, env, i32)
+DEF_HELPER_2(xvcvdpsp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -318,6 +321,7 @@ DEF_HELPER_2(xvminsp, void, env, i32)
 DEF_HELPER_2(xvcmpeqsp, void, env, i32)
 DEF_HELPER_2(xvcmpgesp, void, env, i32)
 DEF_HELPER_2(xvcmpgtsp, void, env, i32)
+DEF_HELPER_2(xvcvspdp, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
target-ppc/translate.c +8 -0
index 377a482..1366ced 100644
@@ -7316,6 +7316,8 @@ GEN_VSX_HELPER_2(xscmpodp, 0x0C, 0x05, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xscmpudp, 0x0C, 0x04, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsmaxdp, 0x00, 0x14, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsmindp, 0x00, 0x15, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xscvdpsp, 0x12, 0x10, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xscvspdp, 0x12, 0x14, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -7339,6 +7341,7 @@ GEN_VSX_HELPER_2(xvmindp, 0x00, 0x1D, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvcmpeqdp, 0x0C, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvcmpgtdp, 0x0C, 0x0D, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvcmpgedp, 0x0C, 0x0E, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvdpsp, 0x12, 0x18, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
@@ -7362,6 +7365,7 @@ GEN_VSX_HELPER_2(xvminsp, 0x00, 0x19, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvcmpeqsp, 0x0C, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvcmpgtsp, 0x0C, 0x09, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvcmpgesp, 0x0C, 0x0A, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvspdp, 0x12, 0x1C, 0, PPC2_VSX)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -10077,6 +10081,8 @@ GEN_XX2FORM(xscmpodp,  0x0C, 0x05, PPC2_VSX),
 GEN_XX2FORM(xscmpudp,  0x0C, 0x04, PPC2_VSX),
 GEN_XX3FORM(xsmaxdp, 0x00, 0x14, PPC2_VSX),
 GEN_XX3FORM(xsmindp, 0x00, 0x15, PPC2_VSX),
+GEN_XX2FORM(xscvdpsp, 0x12, 0x10, PPC2_VSX),
+GEN_XX2FORM(xscvspdp, 0x12, 0x14, PPC2_VSX),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
@@ -10100,6 +10106,7 @@ GEN_XX3FORM(xvmindp, 0x00, 0x1D, PPC2_VSX),
 GEN_XX3_RC_FORM(xvcmpeqdp, 0x0C, 0x0C, PPC2_VSX),
 GEN_XX3_RC_FORM(xvcmpgtdp, 0x0C, 0x0D, PPC2_VSX),
 GEN_XX3_RC_FORM(xvcmpgedp, 0x0C, 0x0E, PPC2_VSX),
+GEN_XX2FORM(xvcvdpsp, 0x12, 0x18, PPC2_VSX),
 
 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
@@ -10123,6 +10130,7 @@ GEN_XX3FORM(xvminsp, 0x00, 0x19, PPC2_VSX),
 GEN_XX3_RC_FORM(xvcmpeqsp, 0x0C, 0x08, PPC2_VSX),
 GEN_XX3_RC_FORM(xvcmpgtsp, 0x0C, 0x09, PPC2_VSX),
 GEN_XX3_RC_FORM(xvcmpgesp, 0x0C, 0x0A, PPC2_VSX),
+GEN_XX2FORM(xvcvspdp, 0x12, 0x1C, PPC2_VSX),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
Signature · 1 line
1.7.1
author
#29 lore raw

PATCH v4 21/22 target-ppc: Add VSX ISA2.06 Integer Conversion Instructions

In reply to Tom Musta

This patch adds the VSX Integer Conversion instructions defined by V2.06 of the PowerPC ISA:

- xscvdpsxds, xscvdpsxws, xscvdpuxds, xscvdpuxws
- xvcvdpsxds, xvcvdpsxws, xvcvdpuxds, xvcvdpuxws
- xvcvspsxds, xvcvspsxws, xvcvspuxds, xvcvspuxws
- xscvsxddp, xscvuxddp
- xvcvsxddp, xscvsxwdp, xvcvuxddp, xvcvuxwdp
- xvcvsxdsp, xscvsxwsp, xvcvuxdsp, xvcvuxwsp

---
 target-ppc/fpu_helper.c |  107 +++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |   22 ++++++++++
 target-ppc/translate.c  |   44 +++++++++++++++++++
 3 files changed, 173 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +107 -0
index c9fb59f..f913ad7 100644
@@ -2441,3 +2441,110 @@ VSX_CVT_FP_TO_FP(xscvdpsp, 1, float64, float32, f64[i], f32[j], 1)
 VSX_CVT_FP_TO_FP(xscvspdp, 1, float32, float64, f32[j], f64[i], 1)
 VSX_CVT_FP_TO_FP(xvcvdpsp, 2, float64, float32, f64[i], f32[j], 0)
 VSX_CVT_FP_TO_FP(xvcvspdp, 2, float32, float64, f32[j], f64[i], 0)
+
+/* VSX_CVT_FP_TO_INT - VSX floating point to integer conversion
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   stp   - source type (float32 or float64)
+ *   ttp   - target type (int32, uint32, int64 or uint64)
+ *   sfld  - source vsr_t field
+ *   tfld  - target vsr_t field
+ *   jdef  - definition of the j index (i or 2*i)
+ *   rnan  - resulting NaN
+ */
+#define VSX_CVT_FP_TO_INT(op, nels, stp, ttp, sfld, tfld, jdef, rnan)        \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
+{                                                                            \
+    ppc_vsr_t xt, xb;                                                        \
+    int i;                                                                   \
+                                                                             \
+    getVSR(xB(opcode), &xb, env);                                            \
+    getVSR(xT(opcode), &xt, env);                                            \
+                                                                             \
+    for (i = 0; i < nels; i++) {                                             \
+        int j = jdef;                                                        \
+        if (unlikely(stp##_is_any_nan(xb.sfld))) {                           \
+            if (stp##_is_signaling_nan(xb.sfld)) {                           \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);       \
+            }                                                                \
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI, 0);            \
+            xt.tfld = rnan;                                                  \
+        } else {                                                             \
+            xt.tfld = stp##_to_##ttp(xb.sfld, &env->fp_status);              \
+            if (env->fp_status.float_exception_flags & float_flag_invalid) { \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI, 0);        \
+            }                                                                \
+        }                                                                    \
+    }                                                                        \
+                                                                             \
+    putVSR(xT(opcode), &xt, env);                                            \
+    helper_float_check_status(env);                                          \
+}
+
+VSX_CVT_FP_TO_INT(xscvdpsxds, 1, float64, int64, f64[j], u64[i], i, \
+                  0x8000000000000000ul)
+VSX_CVT_FP_TO_INT(xscvdpsxws, 1, float64, int32, f64[i], u32[j], \
+                  2*i + JOFFSET, 0x80000000l)
+VSX_CVT_FP_TO_INT(xscvdpuxds, 1, float64, uint64, f64[j], u64[i], i, 0ul)
+VSX_CVT_FP_TO_INT(xscvdpuxws, 1, float64, uint32, f64[i], u32[j], \
+                  2*i + JOFFSET, 0)
+VSX_CVT_FP_TO_INT(xvcvdpsxds, 2, float64, int64, f64[j], u64[i], i, \
+                  0x8000000000000000ul)
+VSX_CVT_FP_TO_INT(xvcvdpsxws, 2, float64, int32, f64[i], u32[j], \
+                  2*i + JOFFSET, 0x80000000l)
+VSX_CVT_FP_TO_INT(xvcvdpuxds, 2, float64, uint64, f64[j], u64[i], i, 0ul)
+VSX_CVT_FP_TO_INT(xvcvdpuxws, 2, float64, uint32, f64[i], u32[j], \
+                  2*i + JOFFSET, 0)
+VSX_CVT_FP_TO_INT(xvcvspsxds, 2, float32, int64, f32[j], u64[i], \
+                  2*i + JOFFSET, 0x8000000000000000ul)
+VSX_CVT_FP_TO_INT(xvcvspsxws, 4, float32, int32, f32[j], u32[j], i, \
+                  0x80000000l)
+VSX_CVT_FP_TO_INT(xvcvspuxds, 2, float32, uint64, f32[j], u64[i], \
+                  2*i + JOFFSET, 0ul)
+VSX_CVT_FP_TO_INT(xvcvspuxws, 4, float32, uint32, f32[j], u32[i], i, 0)
+
+/* VSX_CVT_INT_TO_FP - VSX integer to floating point conversion
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   stp   - source type (int32, uint32, int64 or uint64)
+ *   ttp   - target type (float32 or float64)
+ *   sfld  - source vsr_t field
+ *   tfld  - target vsr_t field
+ *   jdef  - definition of the j index (i or 2*i)
+ *   sfprf - set FPRF
+ */
+#define VSX_CVT_INT_TO_FP(op, nels, stp, ttp, sfld, tfld, jdef, sfprf)  \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                     \
+{                                                                       \
+    ppc_vsr_t xt, xb;                                                   \
+    int i;                                                              \
+                                                                        \
+    getVSR(xB(opcode), &xb, env);                                       \
+    getVSR(xT(opcode), &xt, env);                                       \
+                                                                        \
+    for (i = 0; i < nels; i++) {                                        \
+        int j = jdef;                                                   \
+        xt.tfld = stp##_to_##ttp(xb.sfld, &env->fp_status);             \
+        if (sfprf) {                                                    \
+            helper_compute_fprf(env, xt.tfld, sfprf);                   \
+        }                                                               \
+    }                                                                   \
+                                                                        \
+    putVSR(xT(opcode), &xt, env);                                       \
+    helper_float_check_status(env);                                     \
+}
+
+VSX_CVT_INT_TO_FP(xscvsxddp, 1, int64, float64, u64[j], f64[i], i, 1)
+VSX_CVT_INT_TO_FP(xscvuxddp, 1, uint64, float64, u64[j], f64[i], i, 1)
+VSX_CVT_INT_TO_FP(xvcvsxddp, 2, int64, float64, u64[j], f64[i], i, 0)
+VSX_CVT_INT_TO_FP(xvcvuxddp, 2, uint64, float64, u64[j], f64[i], i, 0)
+VSX_CVT_INT_TO_FP(xvcvsxwdp, 2, int32, float64, u32[j], f64[i], \
+                  2*i + JOFFSET, 0)
+VSX_CVT_INT_TO_FP(xvcvuxwdp, 2, uint64, float64, u32[j], f64[i], \
+                  2*i + JOFFSET, 0)
+VSX_CVT_INT_TO_FP(xvcvsxdsp, 2, int64, float32, u64[i], f32[j], \
+                  2*i + JOFFSET, 0)
+VSX_CVT_INT_TO_FP(xvcvuxdsp, 2, uint64, float32, u64[i], f32[j], \
+                  2*i + JOFFSET, 0)
+VSX_CVT_INT_TO_FP(xvcvsxwsp, 4, int32, float32, u32[j], f32[i], i, 0)
+VSX_CVT_INT_TO_FP(xvcvuxwsp, 4, uint32, float32, u32[j], f32[i], i, 0)
target-ppc/helper.h +22 -0
index dd9518c..de46b6f 100644
@@ -274,6 +274,12 @@ DEF_HELPER_2(xsmaxdp, void, env, i32)
 DEF_HELPER_2(xsmindp, void, env, i32)
 DEF_HELPER_2(xscvdpsp, void, env, i32)
 DEF_HELPER_2(xscvspdp, void, env, i32)
+DEF_HELPER_2(xscvdpsxds, void, env, i32)
+DEF_HELPER_2(xscvdpsxws, void, env, i32)
+DEF_HELPER_2(xscvdpuxds, void, env, i32)
+DEF_HELPER_2(xscvdpuxws, void, env, i32)
+DEF_HELPER_2(xscvsxddp, void, env, i32)
+DEF_HELPER_2(xscvuxddp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
@@ -298,6 +304,14 @@ DEF_HELPER_2(xvcmpeqdp, void, env, i32)
 DEF_HELPER_2(xvcmpgedp, void, env, i32)
 DEF_HELPER_2(xvcmpgtdp, void, env, i32)
 DEF_HELPER_2(xvcvdpsp, void, env, i32)
+DEF_HELPER_2(xvcvdpsxds, void, env, i32)
+DEF_HELPER_2(xvcvdpsxws, void, env, i32)
+DEF_HELPER_2(xvcvdpuxds, void, env, i32)
+DEF_HELPER_2(xvcvdpuxws, void, env, i32)
+DEF_HELPER_2(xvcvsxddp, void, env, i32)
+DEF_HELPER_2(xvcvuxddp, void, env, i32)
+DEF_HELPER_2(xvcvsxwdp, void, env, i32)
+DEF_HELPER_2(xvcvuxwdp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -322,6 +336,14 @@ DEF_HELPER_2(xvcmpeqsp, void, env, i32)
 DEF_HELPER_2(xvcmpgesp, void, env, i32)
 DEF_HELPER_2(xvcmpgtsp, void, env, i32)
 DEF_HELPER_2(xvcvspdp, void, env, i32)
+DEF_HELPER_2(xvcvspsxds, void, env, i32)
+DEF_HELPER_2(xvcvspsxws, void, env, i32)
+DEF_HELPER_2(xvcvspuxds, void, env, i32)
+DEF_HELPER_2(xvcvspuxws, void, env, i32)
+DEF_HELPER_2(xvcvsxdsp, void, env, i32)
+DEF_HELPER_2(xvcvuxdsp, void, env, i32)
+DEF_HELPER_2(xvcvsxwsp, void, env, i32)
+DEF_HELPER_2(xvcvuxwsp, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
target-ppc/translate.c +44 -0

80 lines not on this page · raw message

Signature · 1 line
1.7.1
author
#30 lore raw

PATCH v4 22/22 target-ppc: Add VSX Rounding Instructions

In reply to Tom Musta

This patch adds the VSX Round to Floating Point Integer instructions:

- xsrdpi, xsrdpic, xsrdpim, xsrdpip, xsrdpiz
- xvrdpi, xvrdpic, xvrdpim, xvrdpip, xvrdpiz
- xvrspi, xvrspic, xvrspim, xvrspip, xvrspiz

---
 target-ppc/fpu_helper.c |   68 +++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |   15 ++++++++++
 target-ppc/translate.c  |   30 ++++++++++++++++++++
 3 files changed, 113 insertions(+), 0 deletions(-)
target-ppc/fpu_helper.c +68 -0
index f913ad7..f3d02cc 100644
@@ -2548,3 +2548,71 @@ VSX_CVT_INT_TO_FP(xvcvuxdsp, 2, uint64, float32, u64[i], f32[j], \
                   2*i + JOFFSET, 0)
 VSX_CVT_INT_TO_FP(xvcvsxwsp, 4, int32, float32, u32[j], f32[i], i, 0)
 VSX_CVT_INT_TO_FP(xvcvuxwsp, 4, uint32, float32, u32[j], f32[i], i, 0)
+
+/* For "use current rounding mode", define a value that will not be one of
+ * the existing rounding model enums.
+ */
+#define FLOAT_ROUND_CURRENT (float_round_nearest_even + float_round_down + \
+  float_round_up + float_round_to_zero)
+
+/* VSX_ROUND - VSX floating point round
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   rmode - rounding mode
+ *   sfprf - set FPRF
+ */
+#define VSX_ROUND(op, nels, tp, fld, rmode, sfprf)                     \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                    \
+{                                                                      \
+    ppc_vsr_t xt, xb;                                                  \
+    int i;                                                             \
+    getVSR(xB(opcode), &xb, env);                                      \
+    getVSR(xT(opcode), &xt, env);                                      \
+                                                                       \
+    if (rmode != FLOAT_ROUND_CURRENT) {                                \
+        set_float_rounding_mode(rmode, &env->fp_status);               \
+    }                                                                  \
+                                                                       \
+    for (i = 0; i < nels; i++) {                                       \
+        if (unlikely(tp##_is_signaling_nan(xb.fld[i]))) {              \
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);     \
+            xt.fld[i] = tp##_snan_to_qnan(xb.fld[i]);                  \
+        } else {                                                       \
+            xt.fld[i] = tp##_round_to_int(xb.fld[i], &env->fp_status); \
+        }                                                              \
+        if (sfprf) {                                                   \
+            helper_compute_fprf(env, xt.fld[i], sfprf);                \
+        }                                                              \
+    }                                                                  \
+                                                                       \
+    /* If this is not a "use current rounding mode" instruction,       \
+     * then inhibit setting of the XX bit and restore rounding         \
+     * mode from FPSCR */                                              \
+    if (rmode != FLOAT_ROUND_CURRENT) {                                \
+        fpscr_set_rounding_mode(env);                                  \
+        env->fp_status.float_exception_flags &= ~float_flag_inexact;   \
+    }                                                                  \
+                                                                       \
+    putVSR(xT(opcode), &xt, env);                                      \
+    helper_float_check_status(env);                                    \
+}
+
+VSX_ROUND(xsrdpi, 1, float64, f64, float_round_nearest_even, 1)
+VSX_ROUND(xsrdpic, 1, float64, f64, FLOAT_ROUND_CURRENT, 1)
+VSX_ROUND(xsrdpim, 1, float64, f64, float_round_down, 1)
+VSX_ROUND(xsrdpip, 1, float64, f64, float_round_up, 1)
+VSX_ROUND(xsrdpiz, 1, float64, f64, float_round_to_zero, 1)
+
+VSX_ROUND(xvrdpi, 2, float64, f64, float_round_nearest_even, 0)
+VSX_ROUND(xvrdpic, 2, float64, f64, FLOAT_ROUND_CURRENT, 0)
+VSX_ROUND(xvrdpim, 2, float64, f64, float_round_down, 0)
+VSX_ROUND(xvrdpip, 2, float64, f64, float_round_up, 0)
+VSX_ROUND(xvrdpiz, 2, float64, f64, float_round_to_zero, 0)
+
+VSX_ROUND(xvrspi, 4, float32, f32, float_round_nearest_even, 0)
+VSX_ROUND(xvrspic, 4, float32, f32, FLOAT_ROUND_CURRENT, 0)
+VSX_ROUND(xvrspim, 4, float32, f32, float_round_down, 0)
+VSX_ROUND(xvrspip, 4, float32, f32, float_round_up, 0)
+VSX_ROUND(xvrspiz, 4, float32, f32, float_round_to_zero, 0)
target-ppc/helper.h +15 -0
index de46b6f..0276b02 100644
@@ -280,6 +280,11 @@ DEF_HELPER_2(xscvdpuxds, void, env, i32)
 DEF_HELPER_2(xscvdpuxws, void, env, i32)
 DEF_HELPER_2(xscvsxddp, void, env, i32)
 DEF_HELPER_2(xscvuxddp, void, env, i32)
+DEF_HELPER_2(xsrdpi, void, env, i32)
+DEF_HELPER_2(xsrdpic, void, env, i32)
+DEF_HELPER_2(xsrdpim, void, env, i32)
+DEF_HELPER_2(xsrdpip, void, env, i32)
+DEF_HELPER_2(xsrdpiz, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
@@ -312,6 +317,11 @@ DEF_HELPER_2(xvcvsxddp, void, env, i32)
 DEF_HELPER_2(xvcvuxddp, void, env, i32)
 DEF_HELPER_2(xvcvsxwdp, void, env, i32)
 DEF_HELPER_2(xvcvuxwdp, void, env, i32)
+DEF_HELPER_2(xvrdpi, void, env, i32)
+DEF_HELPER_2(xvrdpic, void, env, i32)
+DEF_HELPER_2(xvrdpim, void, env, i32)
+DEF_HELPER_2(xvrdpip, void, env, i32)
+DEF_HELPER_2(xvrdpiz, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -344,6 +354,11 @@ DEF_HELPER_2(xvcvsxdsp, void, env, i32)
 DEF_HELPER_2(xvcvuxdsp, void, env, i32)
 DEF_HELPER_2(xvcvsxwsp, void, env, i32)
 DEF_HELPER_2(xvcvuxwsp, void, env, i32)
+DEF_HELPER_2(xvrspi, void, env, i32)
+DEF_HELPER_2(xvrspic, void, env, i32)
+DEF_HELPER_2(xvrspim, void, env, i32)
+DEF_HELPER_2(xvrspip, void, env, i32)
+DEF_HELPER_2(xvrspiz, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
target-ppc/translate.c +30 -0
index bb36e8f..52d7165 100644
@@ -7324,6 +7324,11 @@ GEN_VSX_HELPER_2(xscvdpuxds, 0x10, 0x14, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xscvdpuxws, 0x10, 0x04, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xscvsxddp, 0x10, 0x17, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xscvuxddp, 0x10, 0x16, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsrdpi, 0x12, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsrdpic, 0x16, 0x06, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsrdpim, 0x12, 0x07, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsrdpip, 0x12, 0x06, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsrdpiz, 0x12, 0x05, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -7356,6 +7361,11 @@ GEN_VSX_HELPER_2(xvcvsxddp, 0x10, 0x1F, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvcvuxddp, 0x10, 0x1E, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvcvsxwdp, 0x10, 0x0F, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvcvuxwdp, 0x10, 0x0E, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrdpi, 0x12, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrdpic, 0x16, 0x0E, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrdpim, 0x12, 0x0F, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrdpip, 0x12, 0x0E, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrdpiz, 0x12, 0x0D, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
@@ -7388,6 +7398,11 @@ GEN_VSX_HELPER_2(xvcvsxdsp, 0x10, 0x1B, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvcvuxdsp, 0x10, 0x1A, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvcvsxwsp, 0x10, 0x0B, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvcvuxwsp, 0x10, 0x0A, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrspi, 0x12, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrspic, 0x16, 0x0A, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrspim, 0x12, 0x0B, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrspip, 0x12, 0x0A, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrspiz, 0x12, 0x09, 0, PPC2_VSX)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -10111,6 +10126,11 @@ GEN_XX2FORM(xscvdpuxds, 0x10, 0x14, PPC2_VSX),
 GEN_XX2FORM(xscvdpuxws, 0x10, 0x04, PPC2_VSX),
 GEN_XX2FORM(xscvsxddp, 0x10, 0x17, PPC2_VSX),
 GEN_XX2FORM(xscvuxddp, 0x10, 0x16, PPC2_VSX),
+GEN_XX2FORM(xsrdpi, 0x12, 0x04, PPC2_VSX),
+GEN_XX2FORM(xsrdpic, 0x16, 0x06, PPC2_VSX),
+GEN_XX2FORM(xsrdpim, 0x12, 0x07, PPC2_VSX),
+GEN_XX2FORM(xsrdpip, 0x12, 0x06, PPC2_VSX),
+GEN_XX2FORM(xsrdpiz, 0x12, 0x05, PPC2_VSX),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
@@ -10143,6 +10163,11 @@ GEN_XX2FORM(xvcvsxddp, 0x10, 0x1F, PPC2_VSX),
 GEN_XX2FORM(xvcvuxddp, 0x10, 0x1E, PPC2_VSX),
 GEN_XX2FORM(xvcvsxwdp, 0x10, 0x0F, PPC2_VSX),
 GEN_XX2FORM(xvcvuxwdp, 0x10, 0x0E, PPC2_VSX),
+GEN_XX2FORM(xvrdpi, 0x12, 0x0C, PPC2_VSX),
+GEN_XX2FORM(xvrdpic, 0x16, 0x0E, PPC2_VSX),
+GEN_XX2FORM(xvrdpim, 0x12, 0x0F, PPC2_VSX),
+GEN_XX2FORM(xvrdpip, 0x12, 0x0E, PPC2_VSX),
+GEN_XX2FORM(xvrdpiz, 0x12, 0x0D, PPC2_VSX),
 
 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
@@ -10175,6 +10200,11 @@ GEN_XX2FORM(xvcvsxdsp, 0x10, 0x1B, PPC2_VSX),
 GEN_XX2FORM(xvcvuxdsp, 0x10, 0x1A, PPC2_VSX),
 GEN_XX2FORM(xvcvsxwsp, 0x10, 0x0B, PPC2_VSX),
 GEN_XX2FORM(xvcvuxwsp, 0x10, 0x0A, PPC2_VSX),
+GEN_XX2FORM(xvrspi, 0x12, 0x08, PPC2_VSX),
+GEN_XX2FORM(xvrspic, 0x16, 0x0A, PPC2_VSX),
+GEN_XX2FORM(xvrspim, 0x12, 0x0B, PPC2_VSX),
+GEN_XX2FORM(xvrspip, 0x12, 0x0A, PPC2_VSX),
+GEN_XX2FORM(xvrspiz, 0x12, 0x09, PPC2_VSX),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
Signature · 1 line
1.7.1