Skip to contentSkip to conversation

s390x/tcg: Implement Vector enhancements facility and switch to z14

PATCH Superseded David Hildenbrand 3 participants 33 messages Jun 7, 2021

v3 of 4 Superseded Latest is v4 →

lore
Share & tools
lore
#0 lore raw

v3 cover s390x/tcg: Implement Vector enhancements facility and switch to z14

This series adds support for the "Vector enhancements facility" and bumps the qemu CPU model to a stripped-down z14.

I tested most vector FP instructions by generating random instructions and vectors, comparing the result with results on actual hardware. I did not test instructions/instruction variants with (partial) undeterministic behavior and exception handling.

Linux' also seems to boot/work fine with it. Howeever, while testing this series I noticed that Linux checks for the wrong facility bit - see [1]. I tested by temporarily faking availability of the "wrong" facility bit.

[1] https://lkml.kernel.org/r/[email protected]

v2 -> v3:
- "s390x/tcg: Fix FP CONVERT TO (LOGICAL) FIXED NaN handling" -- Keep proper signal handling in the VECTOR variants
- "s390x/tcg: Simplify vop64_2() handling"
-- uint64_t se -> bool se
- "s390x/tcg: Implement VECTOR FP (MAXIMUM|MINIMUM)" -- Drop special cases when both values are infinity -- Simplify cases when both values are zero
-- Simplify dcmask handling
-- uint64_t se -> bool se
- "linux-user: elf: Prepare for Vector enhancements facility" -- Added to properly indicate the new elf capability

v1 -> v2:
- Too much changed to spell it out explicitly. Mostly addressed feedback from Richard, a couple of bugfixes found while testing, and some simplifications/cleanups.
- Rebased on top of Richard's softfloat rework

Cc Cornelia Huck <[email protected]>
Cc Halil Pasic <[email protected]>
Cc Christian Borntraeger <[email protected]>
Cc Thomas Huth <[email protected]>
Cc Richard Henderson <[email protected]>
Cc Laurent Vivier <[email protected]>

David Hildenbrand (26):
s390x/tcg: Fix FP CONVERT TO (LOGICAL) FIXED NaN handling s390x/tcg: Fix instruction name for VECTOR FP LOAD
(LENGTHENED|ROUNDED)
s390x/tcg: Simplify vop64_3() handling
s390x/tcg: Simplify vop64_2() handling
s390x/tcg: Simplify vfc64() handling
s390x/tcg: Simplify vftci64() handling
s390x/tcg: Simplify vfma64() handling
s390x/tcg: Simplify vfll32() handling
s390x/tcg: Simplify vflr64() handling
s390x/tcg: Simplify wfc64() handling
s390x/tcg: Implement VECTOR BIT PERMUTE
s390x/tcg: Implement VECTOR MULTIPLY SUM LOGICAL s390x/tcg: Implement 32/128 bit for VECTOR FP
(ADD|DIVIDE|MULTIPLY|SUBTRACT)
s390x/tcg: Implement 32/128 bit for VECTOR (LOAD FP INTEGER|FP SQUARE
ROOT)
s390x/tcg: Implement 32/128 bit for VECTOR FP COMPARE * s390x/tcg: Implement 32/128 bit for VECTOR FP COMPARE (AND SIGNAL)
SCALAR
s390x/tcg: Implement 64 bit for VECTOR FP LOAD LENGTHENED s390x/tcg: Implement 128 bit for VECTOR FP LOAD ROUNDED s390x/tcg: Implement 32/128 bit for VECTOR FP PERFORM SIGN OPERATION s390x/tcg: Implement 32/128 bit for VECTOR FP TEST DATA CLASS
IMMEDIATE
s390x/tcg: Implement 32/128 bit for VECTOR FP MULTIPLY AND
(ADD|SUBTRACT)
s390x/tcg: Implement VECTOR FP NEGATIVE MULTIPLY AND (ADD|SUBTRACT) s390x/tcg: Implement VECTOR FP (MAXIMUM|MINIMUM)
linux-user: elf: s390x: Prepare for Vector enhancements facility s390x/tcg: We support Vector enhancements facility s390x/cpumodel: Bump up QEMU model to a stripped-down IBM z14 GA2

 hw/s390x/s390-virtio-ccw.c      |    3 +
 include/elf.h                   |    1 +
 linux-user/elfload.c            |    1 +
 target/s390x/cpu_models.c       |    4 +-
 target/s390x/fpu_helper.c       |   41 +-
 target/s390x/gen-features.c     |   14 +-
 target/s390x/helper.h           |   70 +-
 target/s390x/insn-data.def      |   16 +-
 target/s390x/internal.h         |    9 +
 target/s390x/translate_vx.c.inc |  633 ++++++++++++++----
 target/s390x/vec_fpu_helper.c   | 1079 ++++++++++++++++++++++---------
 target/s390x/vec_helper.c       |   22 +
 12 files changed, 1422 insertions(+), 471 deletions(-)
Signature · 1 line
2.31.1
#1 lore raw

PATCH v3 1/26 s390x/tcg: Fix FP CONVERT TO (LOGICAL) FIXED NaN handling

In case we encounter a NaN, we have to return the smallest possible number, corresponding to either 0 or the maximum negative number. This seems to differ from IEEE handling as implemented in softfloat, whereby we return the biggest possible number.

While at it, use float32_to_uint64() in the CLGEB handler.

---
 target/s390x/fpu_helper.c     | 41 +++++++++++++++++++++++++++++++----
 target/s390x/vec_fpu_helper.c |  8 +++++--
 2 files changed, 43 insertions(+), 6 deletions(-)
target/s390x/fpu_helper.c +37 -4
index f155bc048c..13af158748 100644
@@ -509,6 +509,9 @@ uint64_t HELPER(cgeb)(CPUS390XState *env, uint64_t v2, uint32_t m34)
 
     s390_restore_bfp_rounding_mode(env, old_mode);
     handle_exceptions(env, xxc_from_m34(m34), GETPC());
+    if (float32_is_any_nan(v2)) {
+        return INT64_MIN;
+    }
     return ret;
 }
 
@@ -520,6 +523,9 @@ uint64_t HELPER(cgdb)(CPUS390XState *env, uint64_t v2, uint32_t m34)
 
     s390_restore_bfp_rounding_mode(env, old_mode);
     handle_exceptions(env, xxc_from_m34(m34), GETPC());
+    if (float64_is_any_nan(v2)) {
+        return INT64_MIN;
+    }
     return ret;
 }
 
@@ -532,6 +538,9 @@ uint64_t HELPER(cgxb)(CPUS390XState *env, uint64_t h, uint64_t l, uint32_t m34)
 
     s390_restore_bfp_rounding_mode(env, old_mode);
     handle_exceptions(env, xxc_from_m34(m34), GETPC());
+    if (float128_is_any_nan(v2)) {
+        return INT64_MIN;
+    }
     return ret;
 }
 
@@ -543,6 +552,9 @@ uint64_t HELPER(cfeb)(CPUS390XState *env, uint64_t v2, uint32_t m34)
 
     s390_restore_bfp_rounding_mode(env, old_mode);
     handle_exceptions(env, xxc_from_m34(m34), GETPC());
+    if (float32_is_any_nan(v2)) {
+        return INT32_MIN;
+    }
     return ret;
 }
 
@@ -554,6 +566,9 @@ uint64_t HELPER(cfdb)(CPUS390XState *env, uint64_t v2, uint32_t m34)
 
     s390_restore_bfp_rounding_mode(env, old_mode);
     handle_exceptions(env, xxc_from_m34(m34), GETPC());
+    if (float64_is_any_nan(v2)) {
+        return INT32_MIN;
+    }
     return ret;
 }
 
@@ -566,6 +581,9 @@ uint64_t HELPER(cfxb)(CPUS390XState *env, uint64_t h, uint64_t l, uint32_t m34)
 
     s390_restore_bfp_rounding_mode(env, old_mode);
     handle_exceptions(env, xxc_from_m34(m34), GETPC());
+    if (float128_is_any_nan(v2)) {
+        return INT32_MIN;
+    }
     return ret;
 }
 
@@ -573,12 +591,12 @@ uint64_t HELPER(cfxb)(CPUS390XState *env, uint64_t h, uint64_t l, uint32_t m34)
 uint64_t HELPER(clgeb)(CPUS390XState *env, uint64_t v2, uint32_t m34)
 {
     int old_mode = s390_swap_bfp_rounding_mode(env, round_from_m34(m34));
-    uint64_t ret;
-
-    v2 = float32_to_float64(v2, &env->fpu_status);
-    ret = float64_to_uint64(v2, &env->fpu_status);
+    uint64_t ret = float32_to_uint64(v2, &env->fpu_status);
     s390_restore_bfp_rounding_mode(env, old_mode);
     handle_exceptions(env, xxc_from_m34(m34), GETPC());
+    if (float32_is_any_nan(v2)) {
+        return 0;
+    }
     return ret;
 }
 
@@ -590,6 +608,9 @@ uint64_t HELPER(clgdb)(CPUS390XState *env, uint64_t v2, uint32_t m34)
 
     s390_restore_bfp_rounding_mode(env, old_mode);
     handle_exceptions(env, xxc_from_m34(m34), GETPC());
+    if (float64_is_any_nan(v2)) {
+        return 0;
+    }
     return ret;
 }
 
@@ -601,6 +622,9 @@ uint64_t HELPER(clgxb)(CPUS390XState *env, uint64_t h, uint64_t l, uint32_t m34)
 
     s390_restore_bfp_rounding_mode(env, old_mode);
     handle_exceptions(env, xxc_from_m34(m34), GETPC());
+    if (float128_is_any_nan(make_float128(h, l))) {
+        return 0;
+    }
     return ret;
 }
 
@@ -612,6 +636,9 @@ uint64_t HELPER(clfeb)(CPUS390XState *env, uint64_t v2, uint32_t m34)
 
     s390_restore_bfp_rounding_mode(env, old_mode);
     handle_exceptions(env, xxc_from_m34(m34), GETPC());
+    if (float32_is_any_nan(v2)) {
+        return 0;
+    }
     return ret;
 }
 
@@ -623,6 +650,9 @@ uint64_t HELPER(clfdb)(CPUS390XState *env, uint64_t v2, uint32_t m34)
 
     s390_restore_bfp_rounding_mode(env, old_mode);
     handle_exceptions(env, xxc_from_m34(m34), GETPC());
+    if (float64_is_any_nan(v2)) {
+        return 0;
+    }
     return ret;
 }
 
@@ -634,6 +664,9 @@ uint64_t HELPER(clfxb)(CPUS390XState *env, uint64_t h, uint64_t l, uint32_t m34)
 
     s390_restore_bfp_rounding_mode(env, old_mode);
     handle_exceptions(env, xxc_from_m34(m34), GETPC());
+    if (float128_is_any_nan(make_float128(h, l))) {
+        return 0;
+    }
     return ret;
 }
 
target/s390x/vec_fpu_helper.c +6 -2
index c1564e819b..56765918d2 100644
@@ -326,7 +326,9 @@ void HELPER(gvec_vcdlg64s)(void *v1, const void *v2, CPUS390XState *env,
 
 static uint64_t vcgd64(uint64_t a, float_status *s)
 {
-    return float64_to_int64(a, s);
+    const uint64_t tmp = float64_to_int64(a, s);
+
+    return float64_is_any_nan(a) ? INT64_MIN : tmp;
 }
 
 void HELPER(gvec_vcgd64)(void *v1, const void *v2, CPUS390XState *env,
@@ -349,7 +351,9 @@ void HELPER(gvec_vcgd64s)(void *v1, const void *v2, CPUS390XState *env,
 
 static uint64_t vclgd64(uint64_t a, float_status *s)
 {
-    return float64_to_uint64(a, s);
+    const uint64_t tmp = float64_to_uint64(a, s);
+
+    return float64_is_any_nan(a) ? 0 : tmp;
 }
 
 void HELPER(gvec_vclgd64)(void *v1, const void *v2, CPUS390XState *env,
Signature · 1 line
2.31.1
Reviewed-by on v3 1/26
#2 lore raw

Re: [PATCH v3 01/26] s390x/tcg: Fix FP CONVERT TO (LOGICAL) FIXED NaN handling

Quoted 5 lines · David Hildenbrand

In case we encounter a NaN, we have to return the smallest possible number, corresponding to either 0 or the maximum negative number. This seems to differ from IEEE handling as implemented in softfloat, whereby we return the biggest possible number.

Quoted 7 lines

While at it, use float32_to_uint64() in the CLGEB handler.

---
  target/s390x/fpu_helper.c     | 41 +++++++++++++++++++++++++++++++----
  target/s390x/vec_fpu_helper.c |  8 +++++--
  2 files changed, 43 insertions(+), 6 deletions(-)

r~

#3 lore raw

PATCH v3 2/26 s390x/tcg: Fix instruction name for VECTOR FP LOAD (LENGTHENED|ROUNDED)

In reply to David Hildenbrand

Let's use the correct name.

---
 target/s390x/insn-data.def | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
target/s390x/insn-data.def +2 -2
index 0bb1886a2e..35a0086a85 100644
@@ -1245,9 +1245,9 @@
     F(0xe7e5, VFD,     VRR_c, V,   0, 0, 0, 0, vfa, 0, IF_VEC)
 /* VECTOR LOAD FP INTEGER */
     F(0xe7c7, VFI,     VRR_a, V,   0, 0, 0, 0, vcdg, 0, IF_VEC)
-/* VECTOR LOAD LENGTHENED */
+/* VECTOR FP LOAD LENGTHENED */
     F(0xe7c4, VFLL,    VRR_a, V,   0, 0, 0, 0, vfll, 0, IF_VEC)
-/* VECTOR LOAD ROUNDED */
+/* VECTOR FP LOAD ROUNDED */
     F(0xe7c5, VFLR,    VRR_a, V,   0, 0, 0, 0, vcdg, 0, IF_VEC)
 /* VECTOR FP MULTIPLY */
     F(0xe7e7, VFM,     VRR_c, V,   0, 0, 0, 0, vfa, 0, IF_VEC)
Signature · 1 line
2.31.1
#4 lore raw

PATCH v3 3/26 s390x/tcg: Simplify vop64_3() handling

In reply to David Hildenbrand

Let's simplify, reworking our handler generation, passing the whole "m5" register content and not providing specialized handlers for "se", and reading/writing proper float64 values using new helpers.

---
 target/s390x/helper.h           |  4 --
 target/s390x/translate_vx.c.inc | 11 ++--
 target/s390x/vec_fpu_helper.c   | 94 +++++++++------------------------
 3 files changed, 30 insertions(+), 79 deletions(-)
target/s390x/helper.h +0 -4
index d4e4f3388f..2344f81273 100644
@@ -247,7 +247,6 @@ DEF_HELPER_6(gvec_vstrc_cc_rt32, void, ptr, cptr, cptr, cptr, env, i32)
 
 /* === Vector Floating-Point Instructions */
 DEF_HELPER_FLAGS_5(gvec_vfa64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfa64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfc64, void, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfk64, void, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfce64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
@@ -271,7 +270,6 @@ DEF_HELPER_FLAGS_4(gvec_vcgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vclgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vclgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfd64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
@@ -279,7 +277,6 @@ DEF_HELPER_FLAGS_4(gvec_vfll32s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfm64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfma64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
@@ -287,7 +284,6 @@ DEF_HELPER_FLAGS_6(gvec_vfms64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, en
 DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfs64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_vftci64, void, ptr, cptr, env, i32)
 DEF_HELPER_4(gvec_vftci64s, void, ptr, cptr, env, i32)
 
target/s390x/translate_vx.c.inc +5 -6
index eb767f5288..2d3fbdfab2 100644
@@ -2443,7 +2443,6 @@ static DisasJumpType op_vfa(DisasContext *s, DisasOps *o)
 {
     const uint8_t fpf = get_field(s, m4);
     const uint8_t m5 = get_field(s, m5);
-    const bool se = extract32(m5, 3, 1);
     gen_helper_gvec_3_ptr *fn;
 
     if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
@@ -2453,22 +2452,22 @@ static DisasJumpType op_vfa(DisasContext *s, DisasOps *o)
 
     switch (s->fields.op2) {
     case 0xe3:
-        fn = se ? gen_helper_gvec_vfa64s : gen_helper_gvec_vfa64;
+        fn = gen_helper_gvec_vfa64;
         break;
     case 0xe5:
-        fn = se ? gen_helper_gvec_vfd64s : gen_helper_gvec_vfd64;
+        fn = gen_helper_gvec_vfd64;
         break;
     case 0xe7:
-        fn = se ? gen_helper_gvec_vfm64s : gen_helper_gvec_vfm64;
+        fn = gen_helper_gvec_vfm64;
         break;
     case 0xe2:
-        fn = se ? gen_helper_gvec_vfs64s : gen_helper_gvec_vfs64;
+        fn = gen_helper_gvec_vfs64;
         break;
     default:
         g_assert_not_reached();
     }
     gen_gvec_3_ptr(get_field(s, v1), get_field(s, v2),
-                   get_field(s, v3), cpu_env, 0, fn);
+                   get_field(s, v3), cpu_env, m5, fn);
     return DISAS_NEXT;
 }
 
target/s390x/vec_fpu_helper.c +25 -69

139 lines not on this page · raw message

Signature · 1 line
2.31.1
#5 lore raw

PATCH v3 4/26 s390x/tcg: Simplify vop64_2() handling

In reply to David Hildenbrand

Let's rework our macros and simplify. We still need helper functions in most cases due to the different parameters types.

Next, we'll only have 32/128bit variants for vfi and vfsq, so special case the others.

Note that for vfsq, the XxC and erm passed in the simd_data() will never be set, resulting in the same behavior.

---
 target/s390x/helper.h           |   6 -
 target/s390x/translate_vx.c.inc |  18 ++-
 target/s390x/vec_fpu_helper.c   | 190 +++++++++-----------------------
 3 files changed, 58 insertions(+), 156 deletions(-)
target/s390x/helper.h +0 -6
index 2344f81273..4788c1ddaf 100644
@@ -262,16 +262,11 @@ DEF_HELPER_FLAGS_5(gvec_vfche64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i3
 DEF_HELPER_5(gvec_vfche64_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfche64s_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcdg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
-DEF_HELPER_FLAGS_4(gvec_vcdg64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcdlg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
-DEF_HELPER_FLAGS_4(gvec_vcdlg64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
-DEF_HELPER_FLAGS_4(gvec_vcgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vclgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
-DEF_HELPER_FLAGS_4(gvec_vclgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
-DEF_HELPER_FLAGS_4(gvec_vfi64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfll32s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
@@ -282,7 +277,6 @@ DEF_HELPER_FLAGS_6(gvec_vfma64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, en
 DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfms64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
-DEF_HELPER_FLAGS_4(gvec_vfsq64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_vftci64, void, ptr, cptr, env, i32)
 DEF_HELPER_4(gvec_vftci64s, void, ptr, cptr, env, i32)
target/s390x/translate_vx.c.inc +7 -11
index 2d3fbdfab2..280d45bb19 100644
@@ -2558,19 +2558,19 @@ static DisasJumpType op_vcdg(DisasContext *s, DisasOps *o)
 
     switch (s->fields.op2) {
     case 0xc3:
-        fn = se ? gen_helper_gvec_vcdg64s : gen_helper_gvec_vcdg64;
+        fn = gen_helper_gvec_vcdg64;
         break;
     case 0xc1:
-        fn = se ? gen_helper_gvec_vcdlg64s : gen_helper_gvec_vcdlg64;
+        fn = gen_helper_gvec_vcdlg64;
         break;
     case 0xc2:
-        fn = se ? gen_helper_gvec_vcgd64s : gen_helper_gvec_vcgd64;
+        fn = gen_helper_gvec_vcgd64;
         break;
     case 0xc0:
-        fn = se ? gen_helper_gvec_vclgd64s : gen_helper_gvec_vclgd64;
+        fn = gen_helper_gvec_vclgd64;
         break;
     case 0xc7:
-        fn = se ? gen_helper_gvec_vfi64s : gen_helper_gvec_vfi64;
+        fn = gen_helper_gvec_vfi64;
         break;
     case 0xc5:
         fn = se ? gen_helper_gvec_vflr64s : gen_helper_gvec_vflr64;
@@ -2681,18 +2681,14 @@ static DisasJumpType op_vfsq(DisasContext *s, DisasOps *o)
 {
     const uint8_t fpf = get_field(s, m3);
     const uint8_t m4 = get_field(s, m4);
-    gen_helper_gvec_2_ptr *fn = gen_helper_gvec_vfsq64;
 
     if (fpf != FPF_LONG || extract32(m4, 0, 3)) {
         gen_program_exception(s, PGM_SPECIFICATION);
         return DISAS_NORETURN;
     }
 
-    if (extract32(m4, 3, 1)) {
-        fn = gen_helper_gvec_vfsq64s;
-    }
-    gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env,
-                   0, fn);
+    gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, m4,
+                   gen_helper_gvec_vfsq64);
     return DISAS_NEXT;
 }
 
target/s390x/vec_fpu_helper.c +51 -139

221 lines not on this page · raw message

Signature · 1 line
2.31.1
#6 lore raw

PATCH v3 5/26 s390x/tcg: Simplify vfc64() handling

In reply to David Hildenbrand

Pass the m5 field via simd_data() and don't provide specialized handlers for single-element variants.

---
 target/s390x/helper.h           |  6 ---
 target/s390x/translate_vx.c.inc | 45 +++++-----------
 target/s390x/vec_fpu_helper.c   | 94 +++++++++------------------------
 3 files changed, 38 insertions(+), 107 deletions(-)
target/s390x/helper.h +0 -6
index 4788c1ddaf..02a16924a7 100644
@@ -250,17 +250,11 @@ DEF_HELPER_FLAGS_5(gvec_vfa64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfc64, void, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfk64, void, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfce64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfce64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfce64_cc, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_5(gvec_vfce64s_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfch64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfch64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfch64_cc, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_5(gvec_vfch64s_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfche64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfche64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfche64_cc, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_5(gvec_vfche64s_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcdg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcdlg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
target/s390x/translate_vx.c.inc +14 -31

58 lines not on this page · raw message

target/s390x/vec_fpu_helper.c +24 -70

109 lines not on this page · raw message

Signature · 1 line
2.31.1
#7 lore raw

PATCH v3 6/26 s390x/tcg: Simplify vftci64() handling

In reply to David Hildenbrand
---
 target/s390x/helper.h           |  1 -
 target/s390x/translate_vx.c.inc |  7 ++-----
 target/s390x/vec_fpu_helper.c   | 29 +++++++++++------------------
 3 files changed, 13 insertions(+), 24 deletions(-)
target/s390x/helper.h +0 -1
index 02a16924a7..e832680236 100644
@@ -273,7 +273,6 @@ DEF_HELPER_FLAGS_6(gvec_vfms64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, en
 DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_vftci64, void, ptr, cptr, env, i32)
-DEF_HELPER_4(gvec_vftci64s, void, ptr, cptr, env, i32)
 
 #ifndef CONFIG_USER_ONLY
 DEF_HELPER_3(servc, i32, env, i64, i64)
target/s390x/translate_vx.c.inc +2 -5
index 604ae11024..1404471881 100644
@@ -2680,17 +2680,14 @@ static DisasJumpType op_vftci(DisasContext *s, DisasOps *o)
     const uint16_t i3 = get_field(s, i3);
     const uint8_t fpf = get_field(s, m4);
     const uint8_t m5 = get_field(s, m5);
-    gen_helper_gvec_2_ptr *fn = gen_helper_gvec_vftci64;
 
     if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
         gen_program_exception(s, PGM_SPECIFICATION);
         return DISAS_NORETURN;
     }
 
-    if (extract32(m5, 3, 1)) {
-        fn = gen_helper_gvec_vftci64s;
-    }
-    gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, i3, fn);
+    gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env,
+                   deposit32(m5, 4, 12, i3), gen_helper_gvec_vftci64);
     set_cc_static(s);
     return DISAS_NEXT;
 }
target/s390x/vec_fpu_helper.c +11 -18
index 01ee41d154..2ced6fcfaf 100644
@@ -413,13 +413,15 @@ void HELPER(gvec_vfms64s)(void *v1, const void *v2, const void *v3,
     vfma64(v1, v2, v3, v4, env, true, float_muladd_negate_c, GETPC());
 }
 
-static int vftci64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
-                   bool s, uint16_t i3)
+void HELPER(gvec_vftci64)(void *v1, const void *v2, CPUS390XState *env,
+                          uint32_t desc)
 {
+    const uint16_t i3 = extract32(simd_data(desc), 4, 12);
+    const bool s = extract32(simd_data(desc), 3, 1);
     int i, match = 0;
 
     for (i = 0; i < 2; i++) {
-        float64 a = s390_vec_read_element64(v2, i);
+        const float64 a = s390_vec_read_float64(v2, i);
 
         if (float64_dcmask(env, a) & i3) {
             match++;
@@ -432,20 +434,11 @@ static int vftci64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
         }
     }
 
-    if (match) {
-        return s || match == 2 ? 0 : 1;
+    if (match == 2 || (s && match)) {
+        env->cc_op = 0;
+    } else if (match) {
+        env->cc_op = 1;
+    } else {
+        env->cc_op = 3;
     }
-    return 3;
-}
-
-void HELPER(gvec_vftci64)(void *v1, const void *v2, CPUS390XState *env,
-                          uint32_t desc)
-{
-    env->cc_op = vftci64(v1, v2, env, false, simd_data(desc));
-}
-
-void HELPER(gvec_vftci64s)(void *v1, const void *v2, CPUS390XState *env,
-                           uint32_t desc)
-{
-    env->cc_op = vftci64(v1, v2, env, true, simd_data(desc));
 }
Signature · 1 line
2.31.1
#8 lore raw

PATCH v3 7/26 s390x/tcg: Simplify vfma64() handling

In reply to David Hildenbrand
---
 target/s390x/helper.h           |  2 --
 target/s390x/translate_vx.c.inc |  8 +++----
 target/s390x/vec_fpu_helper.c   | 42 +++++++++++++--------------------
 3 files changed, 20 insertions(+), 32 deletions(-)
target/s390x/helper.h +0 -2
index e832680236..3c87593553 100644
@@ -267,9 +267,7 @@ DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_6(gvec_vfma64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_6(gvec_vfms64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_vftci64, void, ptr, cptr, env, i32)
target/s390x/translate_vx.c.inc +3 -5
index 1404471881..4b5bf0a7e3 100644
@@ -2589,7 +2589,6 @@ static DisasJumpType op_vfma(DisasContext *s, DisasOps *o)
 {
     const uint8_t m5 = get_field(s, m5);
     const uint8_t fpf = get_field(s, m6);
-    const bool se = extract32(m5, 3, 1);
     gen_helper_gvec_4_ptr *fn;
 
     if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
@@ -2598,13 +2597,12 @@ static DisasJumpType op_vfma(DisasContext *s, DisasOps *o)
     }
 
     if (s->fields.op2 == 0x8f) {
-        fn = se ? gen_helper_gvec_vfma64s : gen_helper_gvec_vfma64;
+        fn = gen_helper_gvec_vfma64;
     } else {
-        fn = se ? gen_helper_gvec_vfms64s : gen_helper_gvec_vfms64;
+        fn = gen_helper_gvec_vfms64;
     }
     gen_gvec_4_ptr(get_field(s, v1), get_field(s, v2),
-                   get_field(s, v3), get_field(s, v4), cpu_env,
-                   0, fn);
+                   get_field(s, v3), get_field(s, v4), cpu_env, m5, fn);
     return DISAS_NEXT;
 }
 
target/s390x/vec_fpu_helper.c +17 -25

58 lines not on this page · raw message

Signature · 1 line
2.31.1
#9 lore raw

PATCH v3 8/26 s390x/tcg: Simplify vfll32() handling

In reply to David Hildenbrand
---
 target/s390x/helper.h           |  1 -
 target/s390x/translate_vx.c.inc |  6 +-----
 target/s390x/vec_fpu_helper.c   | 21 +++++----------------
 3 files changed, 6 insertions(+), 22 deletions(-)
target/s390x/helper.h +0 -1
index 3c87593553..63039c8d73 100644
@@ -262,7 +262,6 @@ DEF_HELPER_FLAGS_4(gvec_vclgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
-DEF_HELPER_FLAGS_4(gvec_vfll32s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
target/s390x/translate_vx.c.inc +1 -5
index 4b5bf0a7e3..5ff59984b5 100644
@@ -2570,18 +2570,14 @@ static DisasJumpType op_vfll(DisasContext *s, DisasOps *o)
 {
     const uint8_t fpf = get_field(s, m3);
     const uint8_t m4 = get_field(s, m4);
-    gen_helper_gvec_2_ptr *fn = gen_helper_gvec_vfll32;
 
     if (fpf != FPF_SHORT || extract32(m4, 0, 3)) {
         gen_program_exception(s, PGM_SPECIFICATION);
         return DISAS_NORETURN;
     }
 
-    if (extract32(m4, 3, 1)) {
-        fn = gen_helper_gvec_vfll32s;
-    }
     gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env,
-                   0, fn);
+                   m4, gen_helper_gvec_vfll32);
     return DISAS_NEXT;
 }
 
target/s390x/vec_fpu_helper.c +5 -16
index 23b38df158..7bd3e44acc 100644
@@ -287,9 +287,10 @@ DEF_GVEC_VFC(vfce, eq)
 DEF_GVEC_VFC(vfch, lt)
 DEF_GVEC_VFC(vfche, le)
 
-static void vfll32(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
-                   bool s, uintptr_t retaddr)
+void HELPER(gvec_vfll32)(void *v1, const void *v2, CPUS390XState *env,
+                         uint32_t desc)
 {
+    const bool s = extract32(simd_data(desc), 3, 1);
     uint8_t vxc, vec_exc = 0;
     S390Vector tmp = {};
     int i;
@@ -306,20 +307,8 @@ static void vfll32(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
             break;
         }
     }
-    handle_ieee_exc(env, vxc, vec_exc, retaddr);
-    *v1 = tmp;
-}
-
-void HELPER(gvec_vfll32)(void *v1, const void *v2, CPUS390XState *env,
-                         uint32_t desc)
-{
-    vfll32(v1, v2, env, false, GETPC());
-}
-
-void HELPER(gvec_vfll32s)(void *v1, const void *v2, CPUS390XState *env,
-                          uint32_t desc)
-{
-    vfll32(v1, v2, env, true, GETPC());
+    handle_ieee_exc(env, vxc, vec_exc, GETPC());
+    *(S390Vector *)v1 = tmp;
 }
 
 static void vflr64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
Signature · 1 line
2.31.1
#10 lore raw

PATCH v3 9/26 s390x/tcg: Simplify vflr64() handling

In reply to David Hildenbrand
---
 target/s390x/helper.h           |  1 -
 target/s390x/translate_vx.c.inc |  3 +--
 target/s390x/vec_fpu_helper.c   | 29 +++++++----------------------
 3 files changed, 8 insertions(+), 25 deletions(-)
target/s390x/helper.h +0 -1
index 63039c8d73..0cfb82ee8a 100644
@@ -263,7 +263,6 @@ DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
-DEF_HELPER_FLAGS_4(gvec_vflr64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
target/s390x/translate_vx.c.inc +1 -2
index 5ff59984b5..91e2967c49 100644
@@ -2531,7 +2531,6 @@ static DisasJumpType op_vcdg(DisasContext *s, DisasOps *o)
     const uint8_t fpf = get_field(s, m3);
     const uint8_t m4 = get_field(s, m4);
     const uint8_t erm = get_field(s, m5);
-    const bool se = extract32(m4, 3, 1);
     gen_helper_gvec_2_ptr *fn;
 
     if (fpf != FPF_LONG || extract32(m4, 0, 2) || erm > 7 || erm == 2) {
@@ -2556,7 +2555,7 @@ static DisasJumpType op_vcdg(DisasContext *s, DisasOps *o)
         fn = gen_helper_gvec_vfi64;
         break;
     case 0xc5:
-        fn = se ? gen_helper_gvec_vflr64s : gen_helper_gvec_vflr64;
+        fn = gen_helper_gvec_vflr64;
         break;
     default:
         g_assert_not_reached();
target/s390x/vec_fpu_helper.c +7 -22
index 7bd3e44acc..7ca9c892f7 100644
@@ -311,9 +311,12 @@ void HELPER(gvec_vfll32)(void *v1, const void *v2, CPUS390XState *env,
     *(S390Vector *)v1 = tmp;
 }
 
-static void vflr64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
-                   bool s, bool XxC, uint8_t erm, uintptr_t retaddr)
+void HELPER(gvec_vflr64)(void *v1, const void *v2, CPUS390XState *env,
+                         uint32_t desc)
 {
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool s = extract32(simd_data(desc), 3, 1);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
     uint8_t vxc, vec_exc = 0;
     S390Vector tmp = {};
     int i, old_mode;
@@ -332,26 +335,8 @@ static void vflr64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
         }
     }
     s390_restore_bfp_rounding_mode(env, old_mode);
-    handle_ieee_exc(env, vxc, vec_exc, retaddr);
-    *v1 = tmp;
-}
-
-void HELPER(gvec_vflr64)(void *v1, const void *v2, CPUS390XState *env,
-                         uint32_t desc)
-{
-    const uint8_t erm = extract32(simd_data(desc), 4, 4);
-    const bool XxC = extract32(simd_data(desc), 2, 1);
-
-    vflr64(v1, v2, env, false, XxC, erm, GETPC());
-}
-
-void HELPER(gvec_vflr64s)(void *v1, const void *v2, CPUS390XState *env,
-                          uint32_t desc)
-{
-    const uint8_t erm = extract32(simd_data(desc), 4, 4);
-    const bool XxC = extract32(simd_data(desc), 2, 1);
-
-    vflr64(v1, v2, env, true, XxC, erm, GETPC());
+    handle_ieee_exc(env, vxc, vec_exc, GETPC());
+    *(S390Vector *)v1 = tmp;
 }
 
 static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
Signature · 1 line
2.31.1
#11 lore raw

PATCH v3 10/26 s390x/tcg: Simplify wfc64() handling

In reply to David Hildenbrand

... and prepare for 32/128 bit support.

---
 target/s390x/vec_fpu_helper.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)
target/s390x/vec_fpu_helper.c +12 -11
index 7ca9c892f7..4af59ea66c 100644
@@ -201,8 +201,8 @@ static int wfc64(const S390Vector *v1, const S390Vector *v2,
                  CPUS390XState *env, bool signal, uintptr_t retaddr)
 {
     /* only the zero-indexed elements are compared */
-    const float64 a = s390_vec_read_element64(v1, 0);
-    const float64 b = s390_vec_read_element64(v2, 0);
+    const float64 a = s390_vec_read_float64(v1, 0);
+    const float64 b = s390_vec_read_float64(v2, 0);
     uint8_t vxc, vec_exc = 0;
     int cmp;
 
@@ -217,17 +217,18 @@ static int wfc64(const S390Vector *v1, const S390Vector *v2,
     return float_comp_to_cc(env, cmp);
 }
 
-void HELPER(gvec_wfc64)(const void *v1, const void *v2, CPUS390XState *env,
-                        uint32_t desc)
-{
-    env->cc_op = wfc64(v1, v2, env, false, GETPC());
+#define DEF_GVEC_WFC_B(NAME, SIGNAL, BITS)                                     \
+void HELPER(gvec_##NAME##BITS)(const void *v1, const void *v2,                 \
+                               CPUS390XState *env, uint32_t desc)              \
+{                                                                              \
+    env->cc_op = wfc##BITS(v1, v2, env, SIGNAL, GETPC());                      \
 }
 
-void HELPER(gvec_wfk64)(const void *v1, const void *v2, CPUS390XState *env,
-                        uint32_t desc)
-{
-    env->cc_op = wfc64(v1, v2, env, true, GETPC());
-}
+#define DEF_GVEC_WFC(NAME, SIGNAL)                                             \
+     DEF_GVEC_WFC_B(NAME, SIGNAL, 64)
+
+DEF_GVEC_WFC(wfc, false)
+DEF_GVEC_WFC(wfk, true)
 
 typedef bool (*vfc64_fn)(float64 a, float64 b, float_status *status);
 static int vfc64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
Signature · 1 line
2.31.1
#12 lore raw

PATCH v3 11/26 s390x/tcg: Implement VECTOR BIT PERMUTE

In reply to David Hildenbrand
---
 target/s390x/helper.h           |  1 +
 target/s390x/insn-data.def      |  2 ++
 target/s390x/translate_vx.c.inc |  8 ++++++++
 target/s390x/vec_helper.c       | 22 ++++++++++++++++++++++
 4 files changed, 33 insertions(+)
target/s390x/helper.h +1 -0
index 0cfb82ee8a..e99c9643eb 100644
@@ -126,6 +126,7 @@ DEF_HELPER_FLAGS_1(stck, TCG_CALL_NO_RWG_SE, i64, env)
 DEF_HELPER_FLAGS_3(probe_write_access, TCG_CALL_NO_WG, void, env, i64, i64)
 
 /* === Vector Support Instructions === */
+DEF_HELPER_FLAGS_4(gvec_vbperm, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(vll, TCG_CALL_NO_WG, void, env, ptr, i64, i64)
 DEF_HELPER_FLAGS_4(gvec_vpk16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vpk32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
target/s390x/insn-data.def +2 -0
index 35a0086a85..1634a6bc5a 100644
@@ -989,6 +989,8 @@
 
 /* === Vector Support Instructions === */
 
+/* VECTOR BIT PERMUTE */
+    E(0xe785, VBPERM,  VRR_c, VE,  0, 0, 0, 0, vbperm, 0, 0, IF_VEC)
 /* VECTOR GATHER ELEMENT */
     E(0xe713, VGEF,    VRV,   V,   la2, 0, 0, 0, vge, 0, ES_32, IF_VEC)
     E(0xe712, VGEG,    VRV,   V,   la2, 0, 0, 0, vge, 0, ES_64, IF_VEC)
target/s390x/translate_vx.c.inc +8 -0
index 91e2967c49..96283d4ddb 100644
@@ -327,6 +327,14 @@ static void gen_addi2_i64(TCGv_i64 dl, TCGv_i64 dh, TCGv_i64 al, TCGv_i64 ah,
     tcg_temp_free_i64(bh);
 }
 
+static DisasJumpType op_vbperm(DisasContext *s, DisasOps *o)
+{
+    gen_gvec_3_ool(get_field(s, v1), get_field(s, v2), get_field(s, v3), 0,
+                   gen_helper_gvec_vbperm);
+
+    return DISAS_NEXT;
+}
+
 static DisasJumpType op_vge(DisasContext *s, DisasOps *o)
 {
     const uint8_t es = s->insn->data;
target/s390x/vec_helper.c +22 -0
index 986e7cc825..599bab06bd 100644
@@ -19,6 +19,28 @@
 #include "exec/cpu_ldst.h"
 #include "exec/exec-all.h"
 
+void HELPER(gvec_vbperm)(void *v1, const void *v2, const void *v3,
+                         uint32_t desc)
+{
+    S390Vector tmp = {};
+    uint16_t result = 0;
+    int i;
+
+    for (i = 0; i < 16; i++) {
+        const uint8_t bit_nr = s390_vec_read_element8(v3, i);
+        uint16_t bit;
+
+        if (bit_nr >= 128) {
+            continue;
+        }
+        bit = (s390_vec_read_element8(v2, bit_nr / 8)
+               >> (7 - (bit_nr % 8))) & 1;
+        result |= (bit << (15 - i));
+    }
+    s390_vec_write_element16(&tmp, 3, result);
+    *(S390Vector *)v1 = tmp;
+}
+
 void HELPER(vll)(CPUS390XState *env, void *v1, uint64_t addr, uint64_t bytes)
 {
     if (likely(bytes >= 16)) {
Signature · 1 line
2.31.1
#13 lore raw

PATCH v3 12/26 s390x/tcg: Implement VECTOR MULTIPLY SUM LOGICAL

In reply to David Hildenbrand

Fortunately, we only need the Doubleword implementation.

---
 target/s390x/insn-data.def      |  2 ++
 target/s390x/translate_vx.c.inc | 50 +++++++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+)
target/s390x/insn-data.def +2 -0
index 1634a6bc5a..1a3ae7e7e7 100644
@@ -1151,6 +1151,8 @@
     F(0xe7a7, VMO,     VRR_c, V,   0, 0, 0, 0, vm, 0, IF_VEC)
 /* VECTOR MULTIPLY LOGICAL ODD */
     F(0xe7a5, VMLO,    VRR_c, V,   0, 0, 0, 0, vm, 0, IF_VEC)
+/* VECTOR MULTIPLY SUM LOGICAL */
+    F(0xe7b8, VMSL,    VRR_d, VE,  0, 0, 0, 0, vmsl, 0, IF_VEC)
 /* VECTOR NAND */
     F(0xe76e, VNN,     VRR_c, VE,  0, 0, 0, 0, vnn, 0, IF_VEC)
 /* VECTOR NOR */
target/s390x/translate_vx.c.inc +50 -0

56 lines not on this page · raw message

Signature · 1 line
2.31.1
#14 lore raw

PATCH v3 13/26 s390x/tcg: Implement 32/128 bit for VECTOR FP (ADD|DIVIDE|MULTIPLY|SUBTRACT)

In reply to David Hildenbrand

In case of 128bit, we always have a single element. Add new helpers for reading/writing 32/128 bit floats.

---
 target/s390x/helper.h           |  8 ++++
 target/s390x/translate_vx.c.inc | 85 +++++++++++++++++++++++++++++----
 target/s390x/vec_fpu_helper.c   | 74 ++++++++++++++++++++++++++--
 3 files changed, 153 insertions(+), 14 deletions(-)
target/s390x/helper.h +8 -0
index e99c9643eb..2d5e382e61 100644
@@ -247,7 +247,9 @@ DEF_HELPER_6(gvec_vstrc_cc_rt16, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_6(gvec_vstrc_cc_rt32, void, ptr, cptr, cptr, cptr, env, i32)
 
 /* === Vector Floating-Point Instructions */
+DEF_HELPER_FLAGS_5(gvec_vfa32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfa64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfa128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfc64, void, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfk64, void, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfce64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
@@ -260,15 +262,21 @@ DEF_HELPER_FLAGS_4(gvec_vcdg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcdlg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vclgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfd32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfd128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfm32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfm128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfs32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfs128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_vftci64, void, ptr, cptr, env, i32)
 
 #ifndef CONFIG_USER_ONLY
target/s390x/translate_vx.c.inc +75 -10

104 lines not on this page · raw message

target/s390x/vec_fpu_helper.c +70 -4

107 lines not on this page · raw message

Signature · 1 line
2.31.1
#15 lore raw

PATCH v3 14/26 s390x/tcg: Implement 32/128 bit for VECTOR (LOAD FP INTEGER|FP SQUARE ROOT)

In reply to David Hildenbrand
---
 target/s390x/helper.h           |  4 ++
 target/s390x/translate_vx.c.inc | 74 ++++++++++++++++++++++++++-------
 target/s390x/vec_fpu_helper.c   | 46 +++++++++++++++++++-
 3 files changed, 109 insertions(+), 15 deletions(-)
target/s390x/helper.h +4 -0
index 2d5e382e61..28797a6ccc 100644
@@ -265,7 +265,9 @@ DEF_HELPER_FLAGS_4(gvec_vclgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfi32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfi128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
@@ -273,7 +275,9 @@ DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfsq32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfsq128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
target/s390x/translate_vx.c.inc +60 -14

109 lines not on this page · raw message

target/s390x/vec_fpu_helper.c +45 -1

64 lines not on this page · raw message

Signature · 1 line
2.31.1
#16 lore raw

PATCH v3 15/26 s390x/tcg: Implement 32/128 bit for VECTOR FP COMPARE *

In reply to David Hildenbrand

In addition to 32/128bit variants, we also have to support the "Signal-on-QNaN (SQ)" bit.

---
 target/s390x/helper.h           | 12 +++++++
 target/s390x/translate_vx.c.inc | 57 ++++++++++++++++++++++++-----
 target/s390x/vec_fpu_helper.c   | 64 +++++++++++++++++++++++++++++++--
 3 files changed, 121 insertions(+), 12 deletions(-)
target/s390x/helper.h +12 -0
index 28797a6ccc..146836126c 100644
@@ -252,12 +252,24 @@ DEF_HELPER_FLAGS_5(gvec_vfa64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfa128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfc64, void, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfk64, void, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfce32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfce32_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfce64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfce64_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfce128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfce128_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfch32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfch32_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfch64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfch64_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfch128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfch128_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfche32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfche32_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfche64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfche64_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfche128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfche128_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcdg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcdlg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
target/s390x/translate_vx.c.inc +48 -9

74 lines not on this page · raw message

target/s390x/vec_fpu_helper.c +61 -3

92 lines not on this page · raw message

Signature · 1 line
2.31.1
#17 lore raw

PATCH v3 16/26 s390x/tcg: Implement 32/128 bit for VECTOR FP COMPARE (AND SIGNAL) SCALAR

In reply to David Hildenbrand
---
 target/s390x/helper.h           |  4 +++
 target/s390x/translate_vx.c.inc | 38 ++++++++++++++++++++++------
 target/s390x/vec_fpu_helper.c   | 44 ++++++++++++++++++++++++++++++++-
 3 files changed, 77 insertions(+), 9 deletions(-)
target/s390x/helper.h +4 -0
index 146836126c..dca436f710 100644
@@ -250,8 +250,12 @@ DEF_HELPER_6(gvec_vstrc_cc_rt32, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfa32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfa64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfa128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_4(gvec_wfc32, void, cptr, cptr, env, i32)
+DEF_HELPER_4(gvec_wfk32, void, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfc64, void, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfk64, void, cptr, cptr, env, i32)
+DEF_HELPER_4(gvec_wfc128, void, cptr, cptr, env, i32)
+DEF_HELPER_4(gvec_wfk128, void, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfce32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfce32_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfce64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
target/s390x/translate_vx.c.inc +30 -8
index 6f6ef6b6b8..822a9d0513 100644
@@ -2598,19 +2598,41 @@ static DisasJumpType op_wfc(DisasContext *s, DisasOps *o)
 {
     const uint8_t fpf = get_field(s, m3);
     const uint8_t m4 = get_field(s, m4);
+    gen_helper_gvec_2_ptr *fn = NULL;
 
-    if (fpf != FPF_LONG || m4) {
+    switch (fpf) {
+    case FPF_SHORT:
+        if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+            fn = gen_helper_gvec_wfk32;
+            if (s->fields.op2 == 0xcb) {
+                fn = gen_helper_gvec_wfc32;
+            }
+        }
+        break;
+    case FPF_LONG:
+        fn = gen_helper_gvec_wfk64;
+        if (s->fields.op2 == 0xcb) {
+            fn = gen_helper_gvec_wfc64;
+        }
+        break;
+    case FPF_EXT:
+        if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+            fn = gen_helper_gvec_wfk128;
+            if (s->fields.op2 == 0xcb) {
+                fn = gen_helper_gvec_wfc128;
+            }
+        }
+        break;
+    default:
+        break;
+    };
+
+    if (!fn || m4) {
         gen_program_exception(s, PGM_SPECIFICATION);
         return DISAS_NORETURN;
     }
 
-    if (s->fields.op2 == 0xcb) {
-        gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2),
-                       cpu_env, 0, gen_helper_gvec_wfc64);
-    } else {
-        gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2),
-                       cpu_env, 0, gen_helper_gvec_wfk64);
-    }
+    gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, 0, fn);
     set_cc_static(s);
     return DISAS_NEXT;
 }
target/s390x/vec_fpu_helper.c +43 -1

62 lines not on this page · raw message

Signature · 1 line
2.31.1
#18 lore raw

PATCH v3 17/26 s390x/tcg: Implement 64 bit for VECTOR FP LOAD LENGTHENED

In reply to David Hildenbrand

64 bit -> 128 bit, there is only a single final element.

---
 target/s390x/helper.h           |  1 +
 target/s390x/translate_vx.c.inc | 19 ++++++++++++++++---
 target/s390x/vec_fpu_helper.c   | 13 +++++++++++++
 3 files changed, 30 insertions(+), 3 deletions(-)
target/s390x/helper.h +1 -0
index dca436f710..b5ba159402 100644
@@ -285,6 +285,7 @@ DEF_HELPER_FLAGS_4(gvec_vfi32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfll64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
target/s390x/translate_vx.c.inc +16 -3
index 822a9d0513..472afca45e 100644
@@ -2781,14 +2781,27 @@ static DisasJumpType op_vfll(DisasContext *s, DisasOps *o)
 {
     const uint8_t fpf = get_field(s, m3);
     const uint8_t m4 = get_field(s, m4);
+    gen_helper_gvec_2_ptr *fn = NULL;
 
-    if (fpf != FPF_SHORT || extract32(m4, 0, 3)) {
+    switch (fpf) {
+    case FPF_SHORT:
+        fn = gen_helper_gvec_vfll32;
+        break;
+    case FPF_LONG:
+        if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+            fn = gen_helper_gvec_vfll64;
+        }
+        break;
+    default:
+        break;
+    }
+
+    if (!fn || extract32(m4, 0, 3)) {
         gen_program_exception(s, PGM_SPECIFICATION);
         return DISAS_NORETURN;
     }
 
-    gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env,
-                   m4, gen_helper_gvec_vfll32);
+    gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, m4, fn);
     return DISAS_NEXT;
 }
 
target/s390x/vec_fpu_helper.c +13 -0
index fba5261ac4..75e3212582 100644
@@ -522,6 +522,19 @@ void HELPER(gvec_vfll32)(void *v1, const void *v2, CPUS390XState *env,
     *(S390Vector *)v1 = tmp;
 }
 
+void HELPER(gvec_vfll64)(void *v1, const void *v2, CPUS390XState *env,
+                         uint32_t desc)
+{
+    /* load from even element */
+    const float128 ret = float64_to_float128(s390_vec_read_float64(v2, 0),
+                                             &env->fpu_status);
+    uint8_t vxc, vec_exc = 0;
+
+    vxc = check_ieee_exc(env, 0, false, &vec_exc);
+    handle_ieee_exc(env, vxc, vec_exc, GETPC());
+    s390_vec_write_float128(v1, ret);
+}
+
 void HELPER(gvec_vflr64)(void *v1, const void *v2, CPUS390XState *env,
                          uint32_t desc)
 {
Signature · 1 line
2.31.1
#19 lore raw

PATCH v3 18/26 s390x/tcg: Implement 128 bit for VECTOR FP LOAD ROUNDED

In reply to David Hildenbrand

128 bit -> 64 bit, there is only a single element to process.

---
 target/s390x/helper.h           |  1 +
 target/s390x/translate_vx.c.inc | 11 ++++++++++-
 target/s390x/vec_fpu_helper.c   | 19 +++++++++++++++++++
 3 files changed, 30 insertions(+), 1 deletion(-)
target/s390x/helper.h +1 -0
index b5ba159402..02e6967ae6 100644
@@ -287,6 +287,7 @@ DEF_HELPER_FLAGS_4(gvec_vfi128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfll64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vflr128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
target/s390x/translate_vx.c.inc +10 -1
index 472afca45e..e94c9f9d86 100644
@@ -2759,8 +2759,17 @@ static DisasJumpType op_vcdg(DisasContext *s, DisasOps *o)
         }
         break;
     case 0xc5:
-        if (fpf == FPF_LONG) {
+        switch (fpf) {
+        case FPF_LONG:
             fn = gen_helper_gvec_vflr64;
+            break;
+        case FPF_EXT:
+            if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+                fn = gen_helper_gvec_vflr128;
+            }
+            break;
+        default:
+            break;
         }
         break;
     default:
target/s390x/vec_fpu_helper.c +19 -0
index 75e3212582..0fb82bd18f 100644
@@ -563,6 +563,25 @@ void HELPER(gvec_vflr64)(void *v1, const void *v2, CPUS390XState *env,
     *(S390Vector *)v1 = tmp;
 }
 
+void HELPER(gvec_vflr128)(void *v1, const void *v2, CPUS390XState *env,
+                          uint32_t desc)
+{
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
+    uint8_t vxc, vec_exc = 0;
+    int old_mode;
+    float64 ret;
+
+    old_mode = s390_swap_bfp_rounding_mode(env, erm);
+    ret = float128_to_float64(s390_vec_read_float128(v2), &env->fpu_status);
+    vxc = check_ieee_exc(env, 0, XxC, &vec_exc);
+    s390_restore_bfp_rounding_mode(env, old_mode);
+    handle_ieee_exc(env, vxc, vec_exc, GETPC());
+
+    /* place at even element, odd element is unpredictable */
+    s390_vec_write_float64(v1, 0, ret);
+}
+
 static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
                    const S390Vector *v4, CPUS390XState *env, bool s, int flags,
                    uintptr_t retaddr)
Signature · 1 line
2.31.1
#20 lore raw

PATCH v3 19/26 s390x/tcg: Implement 32/128 bit for VECTOR FP PERFORM SIGN OPERATION

In reply to David Hildenbrand
---
 target/s390x/translate_vx.c.inc | 106 ++++++++++++++++++++++----------
 1 file changed, 73 insertions(+), 33 deletions(-)
target/s390x/translate_vx.c.inc +73 -33
index e94c9f9d86..4d1ccb4159 100644
@@ -2842,48 +2842,88 @@ static DisasJumpType op_vfpso(DisasContext *s, DisasOps *o)
     const uint8_t fpf = get_field(s, m3);
     const uint8_t m4 = get_field(s, m4);
     const uint8_t m5 = get_field(s, m5);
+    const bool se = extract32(m4, 3, 1);
     TCGv_i64 tmp;
 
-    if (fpf != FPF_LONG || extract32(m4, 0, 3) || m5 > 2) {
+    if ((fpf != FPF_LONG && !s390_has_feat(S390_FEAT_VECTOR_ENH)) ||
+        extract32(m4, 0, 3) || m5 > 2) {
         gen_program_exception(s, PGM_SPECIFICATION);
         return DISAS_NORETURN;
     }
 
-    if (extract32(m4, 3, 1)) {
-        tmp = tcg_temp_new_i64();
-        read_vec_element_i64(tmp, v2, 0, ES_64);
-        switch (m5) {
-        case 0:
-            /* sign bit is inverted (complement) */
-            tcg_gen_xori_i64(tmp, tmp, 1ull << 63);
-            break;
-        case 1:
-            /* sign bit is set to one (negative) */
-            tcg_gen_ori_i64(tmp, tmp, 1ull << 63);
-            break;
-        case 2:
-            /* sign bit is set to zero (positive) */
-            tcg_gen_andi_i64(tmp, tmp, (1ull << 63) - 1);
-            break;
+    switch (fpf) {
+    case FPF_SHORT:
+        if (!se) {
+            switch (m5) {
+            case 0:
+                /* sign bit is inverted (complement) */
+                gen_gvec_fn_2i(xori, ES_32, v1, v2, 1ull << 31);
+                break;
+            case 1:
+                /* sign bit is set to one (negative) */
+                gen_gvec_fn_2i(ori, ES_32, v1, v2, 1ull << 31);
+                break;
+            case 2:
+                /* sign bit is set to zero (positive) */
+                gen_gvec_fn_2i(andi, ES_32, v1, v2, (1ull << 31) - 1);
+                break;
+            }
+            return DISAS_NEXT;
         }
-        write_vec_element_i64(tmp, v1, 0, ES_64);
-        tcg_temp_free_i64(tmp);
-    } else {
-        switch (m5) {
-        case 0:
-            /* sign bit is inverted (complement) */
-            gen_gvec_fn_2i(xori, ES_64, v1, v2, 1ull << 63);
-            break;
-        case 1:
-            /* sign bit is set to one (negative) */
-            gen_gvec_fn_2i(ori, ES_64, v1, v2, 1ull << 63);
-            break;
-        case 2:
-            /* sign bit is set to zero (positive) */
-            gen_gvec_fn_2i(andi, ES_64, v1, v2, (1ull << 63) - 1);
-            break;
+        break;
+    case FPF_LONG:
+        if (!se) {
+            switch (m5) {
+            case 0:
+                /* sign bit is inverted (complement) */
+                gen_gvec_fn_2i(xori, ES_64, v1, v2, 1ull << 63);
+                break;
+            case 1:
+                /* sign bit is set to one (negative) */
+                gen_gvec_fn_2i(ori, ES_64, v1, v2, 1ull << 63);
+                break;
+            case 2:
+                /* sign bit is set to zero (positive) */
+                gen_gvec_fn_2i(andi, ES_64, v1, v2, (1ull << 63) - 1);
+                break;
+            }
+            return DISAS_NEXT;
         }
+        break;
+    case FPF_EXT:
+        /* Only a single element. */
+        break;
+    default:
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
     }
+
+    /* With a single element, we are only interested in bit 0. */
+    tmp = tcg_temp_new_i64();
+    read_vec_element_i64(tmp, v2, 0, ES_64);
+    switch (m5) {
+    case 0:
+        /* sign bit is inverted (complement) */
+        tcg_gen_xori_i64(tmp, tmp, 1ull << 63);
+        break;
+    case 1:
+        /* sign bit is set to one (negative) */
+        tcg_gen_ori_i64(tmp, tmp, 1ull << 63);
+        break;
+    case 2:
+        /* sign bit is set to zero (positive) */
+        tcg_gen_andi_i64(tmp, tmp, (1ull << 63) - 1);
+        break;
+    }
+    write_vec_element_i64(tmp, v1, 0, ES_64);
+
+    if (fpf == FPF_EXT) {
+        read_vec_element_i64(tmp, v2, 1, ES_64);
+        write_vec_element_i64(tmp, v1, 1, ES_64);
+    }
+
+    tcg_temp_free_i64(tmp);
+
     return DISAS_NEXT;
 }
 
Signature · 1 line
2.31.1
#21 lore raw

PATCH v3 20/26 s390x/tcg: Implement 32/128 bit for VECTOR FP TEST DATA CLASS IMMEDIATE

In reply to David Hildenbrand
---
 target/s390x/helper.h           |  2 ++
 target/s390x/translate_vx.c.inc | 23 ++++++++++++++--
 target/s390x/vec_fpu_helper.c   | 47 +++++++++++++++++++++++++++++++++
 3 files changed, 70 insertions(+), 2 deletions(-)
target/s390x/helper.h +2 -0
index 02e6967ae6..bae73b9a56 100644
@@ -299,7 +299,9 @@ DEF_HELPER_FLAGS_4(gvec_vfsq128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_4(gvec_vftci32, void, ptr, cptr, env, i32)
 DEF_HELPER_4(gvec_vftci64, void, ptr, cptr, env, i32)
+DEF_HELPER_4(gvec_vftci128, void, ptr, cptr, env, i32)
 
 #ifndef CONFIG_USER_ONLY
 DEF_HELPER_3(servc, i32, env, i64, i64)
target/s390x/translate_vx.c.inc +21 -2
index 4d1ccb4159..765f75df9c 100644
@@ -2965,14 +2965,33 @@ static DisasJumpType op_vftci(DisasContext *s, DisasOps *o)
     const uint16_t i3 = get_field(s, i3);
     const uint8_t fpf = get_field(s, m4);
     const uint8_t m5 = get_field(s, m5);
+    gen_helper_gvec_2_ptr *fn = NULL;
 
-    if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
+    switch (fpf) {
+    case FPF_SHORT:
+        if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+            fn = gen_helper_gvec_vftci32;
+        }
+        break;
+    case FPF_LONG:
+        fn = gen_helper_gvec_vftci64;
+        break;
+    case FPF_EXT:
+        if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+            fn = gen_helper_gvec_vftci128;
+        }
+        break;
+    default:
+        break;
+    }
+
+    if (!fn || extract32(m5, 0, 3)) {
         gen_program_exception(s, PGM_SPECIFICATION);
         return DISAS_NORETURN;
     }
 
     gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env,
-                   deposit32(m5, 4, 12, i3), gen_helper_gvec_vftci64);
+                   deposit32(m5, 4, 12, i3), fn);
     set_cc_static(s);
     return DISAS_NEXT;
 }
target/s390x/vec_fpu_helper.c +47 -0

56 lines not on this page · raw message

Signature · 1 line
2.31.1
#22 lore raw

PATCH v3 21/26 s390x/tcg: Implement 32/128 bit for VECTOR FP MULTIPLY AND (ADD|SUBTRACT)

In reply to David Hildenbrand
---
 target/s390x/helper.h           |  4 +++
 target/s390x/translate_vx.c.inc | 47 ++++++++++++++++++++++++++++-----
 target/s390x/vec_fpu_helper.c   | 44 +++++++++++++++++++++++++++++-
 3 files changed, 87 insertions(+), 8 deletions(-)
target/s390x/helper.h +4 -0
index bae73b9a56..2366756063 100644
@@ -291,8 +291,12 @@ DEF_HELPER_FLAGS_4(gvec_vflr128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfma32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfma128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfms32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfms128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
target/s390x/translate_vx.c.inc +40 -7

58 lines not on this page · raw message

target/s390x/vec_fpu_helper.c +43 -1

62 lines not on this page · raw message

Signature · 1 line
2.31.1
#23 lore raw

PATCH v3 22/26 s390x/tcg: Implement VECTOR FP NEGATIVE MULTIPLY AND (ADD|SUBTRACT)

In reply to David Hildenbrand
---
 target/s390x/helper.h           |  6 +++++
 target/s390x/insn-data.def      |  4 ++++
 target/s390x/translate_vx.c.inc | 39 +++++++++++++++++++++++++++++++--
 target/s390x/vec_fpu_helper.c   |  2 ++
 4 files changed, 49 insertions(+), 2 deletions(-)
target/s390x/helper.h +6 -0
index 2366756063..913967ce4e 100644
@@ -297,6 +297,12 @@ DEF_HELPER_FLAGS_6(gvec_vfma128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, en
 DEF_HELPER_FLAGS_6(gvec_vfms32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfms128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfnma32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfnma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfnma128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfnms32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfnms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfnms128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
target/s390x/insn-data.def +4 -0
index 1a3ae7e7e7..19b02dffca 100644
@@ -1259,6 +1259,10 @@
     F(0xe78f, VFMA,    VRR_e, V,   0, 0, 0, 0, vfma, 0, IF_VEC)
 /* VECTOR FP MULTIPLY AND SUBTRACT */
     F(0xe78e, VFMS,    VRR_e, V,   0, 0, 0, 0, vfma, 0, IF_VEC)
+/* VECTOR FP NEGATIVE MULTIPLY AND ADD */
+    F(0xe79f, VFNMA,   VRR_e, VE,  0, 0, 0, 0, vfma, 0, IF_VEC)
+/* VECTOR FP NEGATIVE MULTIPLY AND SUBTRACT */
+    F(0xe79e, VFNMS,   VRR_e, VE,   0, 0, 0, 0, vfma, 0, IF_VEC)
 /* VECTOR FP PERFORM SIGN OPERATION */
     F(0xe7cc, VFPSO,   VRR_a, V,   0, 0, 0, 0, vfpso, 0, IF_VEC)
 /* VECTOR FP SQUARE ROOT */
target/s390x/translate_vx.c.inc +37 -2
index 17d41b178f..200d83e783 100644
@@ -2820,7 +2820,8 @@ static DisasJumpType op_vfma(DisasContext *s, DisasOps *o)
     const uint8_t fpf = get_field(s, m6);
     gen_helper_gvec_4_ptr *fn = NULL;
 
-    if (s->fields.op2 == 0x8f) {
+    switch (s->fields.op2) {
+    case 0x8f:
         switch (fpf) {
         case FPF_SHORT:
             if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
@@ -2838,7 +2839,8 @@ static DisasJumpType op_vfma(DisasContext *s, DisasOps *o)
         default:
             break;
         }
-    } else {
+        break;
+    case 0x8e:
         switch (fpf) {
         case FPF_SHORT:
             if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
@@ -2856,6 +2858,39 @@ static DisasJumpType op_vfma(DisasContext *s, DisasOps *o)
         default:
             break;
         }
+        break;
+    case 0x9f:
+        switch (fpf) {
+        case FPF_SHORT:
+            fn = gen_helper_gvec_vfnma32;
+            break;
+        case FPF_LONG:
+            fn = gen_helper_gvec_vfnma64;
+            break;
+        case FPF_EXT:
+            fn = gen_helper_gvec_vfnma128;
+            break;
+        default:
+            break;
+        }
+        break;
+    case 0x9e:
+        switch (fpf) {
+        case FPF_SHORT:
+            fn = gen_helper_gvec_vfnms32;
+            break;
+        case FPF_LONG:
+            fn = gen_helper_gvec_vfnms64;
+            break;
+        case FPF_EXT:
+            fn = gen_helper_gvec_vfnms128;
+            break;
+        default:
+            break;
+        }
+        break;
+    default:
+        g_assert_not_reached();
     }
 
     if (!fn || extract32(m5, 0, 3)) {
target/s390x/vec_fpu_helper.c +2 -0
index 29ccc608dc..dc9bcc90a7 100644
@@ -663,6 +663,8 @@ void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, const void *v3,       \
 
 DEF_GVEC_VFMA(vfma, 0)
 DEF_GVEC_VFMA(vfms, float_muladd_negate_c)
+DEF_GVEC_VFMA(vfnma, float_muladd_negate_result)
+DEF_GVEC_VFMA(vfnms, float_muladd_negate_c | float_muladd_negate_result)
 
 void HELPER(gvec_vftci32)(void *v1, const void *v2, CPUS390XState *env,
                           uint32_t desc)
Signature · 1 line
2.31.1
#24 lore raw

PATCH v3 23/26 s390x/tcg: Implement VECTOR FP (MAXIMUM|MINIMUM)

In reply to David Hildenbrand

For IEEE functions, we can reuse the softfloat implementations. For the other functions, implement it generically for 32bit/64bit/128bit - carefully taking care of all weird special cases according to the tables defined in the PoP.

---
 target/s390x/helper.h           |   6 +
 target/s390x/insn-data.def      |   4 +
 target/s390x/internal.h         |   9 +
 target/s390x/translate_vx.c.inc |  44 +++++
 target/s390x/vec_fpu_helper.c   | 328 ++++++++++++++++++++++++++++++++
 5 files changed, 391 insertions(+)
target/s390x/helper.h +6 -0
index 913967ce4e..ba045f559d 100644
@@ -291,6 +291,12 @@ DEF_HELPER_FLAGS_4(gvec_vflr128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfmax32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfmax64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfmax128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfmin32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfmin64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfmin128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfma32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfma128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
target/s390x/insn-data.def +4 -0
index 19b02dffca..3e5594210c 100644
@@ -1253,6 +1253,10 @@
     F(0xe7c4, VFLL,    VRR_a, V,   0, 0, 0, 0, vfll, 0, IF_VEC)
 /* VECTOR FP LOAD ROUNDED */
     F(0xe7c5, VFLR,    VRR_a, V,   0, 0, 0, 0, vcdg, 0, IF_VEC)
+/* VECTOR FP MAXIMUM */
+    F(0xe7ef, VFMAX,   VRR_c, VE,  0, 0, 0, 0, vfmax, 0, IF_VEC)
+/* VECTOR FP MINIMUM */
+    F(0xe7ee, VFMIN,   VRR_c, VE,  0, 0, 0, 0, vfmax, 0, IF_VEC)
 /* VECTOR FP MULTIPLY */
     F(0xe7e7, VFM,     VRR_c, V,   0, 0, 0, 0, vfa, 0, IF_VEC)
 /* VECTOR FP MULTIPLY AND ADD */
target/s390x/internal.h +9 -0
index 11515bb617..d62dfc4dc6 100644
@@ -288,6 +288,15 @@ uint8_t s390_softfloat_exc_to_ieee(unsigned int exc);
 int s390_swap_bfp_rounding_mode(CPUS390XState *env, int m3);
 void s390_restore_bfp_rounding_mode(CPUS390XState *env, int old_mode);
 int float_comp_to_cc(CPUS390XState *env, int float_compare);
+
+#define DCMASK_ZERO             0x0c00
+#define DCMASK_NORMAL           0x0300
+#define DCMASK_SUBNORMAL        0x00c0
+#define DCMASK_INFINITY         0x0030
+#define DCMASK_QUIET_NAN        0x000c
+#define DCMASK_SIGNALING_NAN    0x0003
+#define DCMASK_NAN              0x000f
+#define DCMASK_NEGATIVE         0x0555
 uint16_t float32_dcmask(CPUS390XState *env, float32 f1);
 uint16_t float64_dcmask(CPUS390XState *env, float64 f1);
 uint16_t float128_dcmask(CPUS390XState *env, float128 f1);
target/s390x/translate_vx.c.inc +44 -0

50 lines not on this page · raw message

target/s390x/vec_fpu_helper.c +328 -0

331 lines not on this page · raw message

Signature · 1 line
2.31.1
Reviewed-by on v3 23/26
#25 lore raw

Re: [PATCH v3 23/26] s390x/tcg: Implement VECTOR FP (MAXIMUM|MINIMUM)

target/s390x/vec_fpu_helper.c void HELPER(gvec_vftci128)(void *v1, const void *v2, CPUS390XState *env, · line 765

Quoted 4 lines · David Hildenbrand
target/s390x/vec_fpu_helper.c +4 -0
+static S390MinMaxRes vfmin_res(uint16_t dcmask_a, uint16_t dcmask_b,
+                               S390MinMaxType type, float_status *s)
+{
+    const bool neg_a = dcmask_a & DCMASK_NEGATIVE;

Minor nits:
Only used in the zero block.

Review

Quoted 2 lines
(quoted diff) +2 -0
+    const bool nan_a = dcmask_a & DCMASK_NAN;
+    const bool nan_b = dcmask_b & DCMASK_NAN;

Only used in the nan block.

r~

#26 lore raw

Re: [PATCH v3 23/26] s390x/tcg: Implement VECTOR FP (MAXIMUM|MINIMUM)

Quoted 9 lines · Richard Henderson

target/s390x/vec_fpu_helper.c void HELPER(gvec_vftci128)(void *v1, const void *v2, CPUS390XState *env, · line 765

Quoted 4 lines · David Hildenbrand
target/s390x/vec_fpu_helper.c +4 -0
+static S390MinMaxRes vfmin_res(uint16_t dcmask_a, uint16_t dcmask_b,
+                               S390MinMaxType type, float_status *s)
+{
+    const bool neg_a = dcmask_a & DCMASK_NEGATIVE;

Minor nits:
Only used in the zero block.

Quoted 9 lines

Review

Quoted 2 lines
(quoted diff) +2 -0
+    const bool nan_a = dcmask_a & DCMASK_NAN;
+    const bool nan_b = dcmask_b & DCMASK_NAN;

Only used in the nan block.

r~

Indeed, will move these into the blocks -- thanks!

Signature · 3 lines
Thanks,

David / dhildenb
#27 lore raw

PATCH v3 24/26 linux-user: elf: s390x: Prepare for Vector enhancements facility

In reply to David Hildenbrand

Let's check for S390_FEAT_VECTOR_ENH and set HWCAP_S390_VXRS_EXT accordingly.

---
 include/elf.h        | 1 +
 linux-user/elfload.c | 1 +
 2 files changed, 2 insertions(+)
include/elf.h +1 -0
index 033bcc9576..0049d5a318 100644
@@ -605,6 +605,7 @@ typedef struct {
 #define HWCAP_S390_HIGH_GPRS    512
 #define HWCAP_S390_TE           1024
 #define HWCAP_S390_VXRS         2048
+#define HWCAP_S390_VXRS_EXT     8192
 
 /* M68K specific definitions. */
 /* We use the top 24 bits to encode information about the
linux-user/elfload.c +1 -0
index 17ab06f612..4b0172339e 100644
@@ -1376,6 +1376,7 @@ static uint32_t get_elf_hwcap(void)
         hwcap |= HWCAP_S390_ETF3EH;
     }
     GET_FEATURE(S390_FEAT_VECTOR, HWCAP_S390_VXRS);
+    GET_FEATURE(S390_FEAT_VECTOR_ENH, HWCAP_S390_VXRS_EXT);
 
     return hwcap;
 }
Signature · 1 line
2.31.1
Acked-by on v3 24/26
#28 lore raw

Re: [PATCH v3 24/26] linux-user: elf: s390x: Prepare for Vector enhancements facility

Le 07/06/2021 à 13:03, David Hildenbrand a écrit :

Quoted 28 lines

Let's check for S390_FEAT_VECTOR_ENH and set HWCAP_S390_VXRS_EXT accordingly.

---
 include/elf.h        | 1 +
 linux-user/elfload.c | 1 +
 2 files changed, 2 insertions(+)
include/elf.h +1 -0
index 033bcc9576..0049d5a318 100644
@@ -605,6 +605,7 @@ typedef struct {
 #define HWCAP_S390_HIGH_GPRS    512
 #define HWCAP_S390_TE           1024
 #define HWCAP_S390_VXRS         2048
+#define HWCAP_S390_VXRS_EXT     8192
 
 /* M68K specific definitions. */
 /* We use the top 24 bits to encode information about the
linux-user/elfload.c +0 -0
index 17ab06f612..4b0172339e 100644

linux-user/elfload.c static uint32_t get_elf_hwcap(void) · line 1382

Quoted 7 lines
linux-user/elfload.c +1 -0
@@ -1376,6 +1376,7 @@ static uint32_t get_elf_hwcap(void)
         hwcap |= HWCAP_S390_ETF3EH;
     }
     GET_FEATURE(S390_FEAT_VECTOR, HWCAP_S390_VXRS);
+    GET_FEATURE(S390_FEAT_VECTOR_ENH, HWCAP_S390_VXRS_EXT);
 
     return hwcap;
 }
#29 lore raw

Re: [PATCH v3 24/26] linux-user: elf: s390x: Prepare for Vector enhancements facility

In reply to David Hildenbrand

include/elf.h typedef struct { · line 608

Quoted 6 lines · David Hildenbrand

+++ b/include/elf.h

include/elf.h +1 -0
@@ -605,6 +605,7 @@ typedef struct {
  #define HWCAP_S390_HIGH_GPRS    512
  #define HWCAP_S390_TE           1024
  #define HWCAP_S390_VXRS         2048
+#define HWCAP_S390_VXRS_EXT     8192

Probably best to fill in all of the values, even if we don't use them right now. Also, not the fault of this patch, but I don't think this belongs in include/elf.h. This is linux specific, not some part of the elf specification.

r~

#30 lore raw

Re: [PATCH v3 24/26] linux-user: elf: s390x: Prepare for Vector enhancements facility

Quoted 12 lines · Richard Henderson

include/elf.h typedef struct { · line 608

Quoted 6 lines · David Hildenbrand

+++ b/include/elf.h

include/elf.h +1 -0
@@ -605,6 +605,7 @@ typedef struct {
   #define HWCAP_S390_HIGH_GPRS    512
   #define HWCAP_S390_TE           1024
   #define HWCAP_S390_VXRS         2048
+#define HWCAP_S390_VXRS_EXT     8192

Probably best to fill in all of the values, even if we don't use them right now. Also, not the fault of this patch, but I don't think this belongs in include/elf.h. This is linux specific, not some part of the elf specification.

I can most certainly add all currently defined ones for s390x.

We do have the same defines "misplaced" for other archs as well. I'd like to avoid cleaning that up as part of this series. Thanks!

Signature · 3 lines
Thanks,

David / dhildenb
#31 lore raw

PATCH v3 25/26 s390x/tcg: We support Vector enhancements facility

In reply to David Hildenbrand

Everything is wired up and all new instructions are implemented.

---
 target/s390x/gen-features.c | 1 +
 1 file changed, 1 insertion(+)
target/s390x/gen-features.c +1 -0
index a6ec918e90..219b1f9420 100644
@@ -720,6 +720,7 @@ static uint16_t qemu_MAX[] = {
     S390_FEAT_INSTRUCTION_EXEC_PROT,
     S390_FEAT_MISC_INSTRUCTION_EXT2,
     S390_FEAT_MSA_EXT_8,
+    S390_FEAT_VECTOR_ENH,
 };
 
 /****** END FEATURE DEFS ******/
Signature · 1 line
2.31.1
#32 lore raw

PATCH v3 26/26 s390x/cpumodel: Bump up QEMU model to a stripped-down IBM z14 GA2

In reply to David Hildenbrand

TCG implements everything we need to run basic z14 OS+software.

---
 hw/s390x/s390-virtio-ccw.c  |  3 +++
 target/s390x/cpu_models.c   |  4 ++--
 target/s390x/gen-features.c | 15 +++++++++------
 3 files changed, 14 insertions(+), 8 deletions(-)
hw/s390x/s390-virtio-ccw.c +3 -0
index 7af27ca305..e4b18aef49 100644
@@ -802,7 +802,10 @@ DEFINE_CCW_MACHINE(6_1, "6.1", true);
 
 static void ccw_machine_6_0_instance_options(MachineState *machine)
 {
+    static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_0 };
+
     ccw_machine_6_1_instance_options(machine);
+    s390_set_qemu_cpu_model(0x2964, 13, 2, qemu_cpu_feat);
 }
 
 static void ccw_machine_6_0_class_options(MachineClass *mc)
target/s390x/cpu_models.c +2 -2
index 050dcf2d42..94090a6e22 100644
@@ -90,8 +90,8 @@ static S390CPUDef s390_cpu_defs[] = {
     CPUDEF_INIT(0x8562, 15, 1, 47, 0x08000000U, "gen15b", "IBM z15 T02 GA1"),
 };
 
-#define QEMU_MAX_CPU_TYPE 0x2964
-#define QEMU_MAX_CPU_GEN 13
+#define QEMU_MAX_CPU_TYPE 0x3906
+#define QEMU_MAX_CPU_GEN 14
 #define QEMU_MAX_CPU_EC_GA 2
 static const S390FeatInit qemu_max_cpu_feat_init = { S390_FEAT_LIST_QEMU_MAX };
 static S390FeatBitmap qemu_max_cpu_feat;
target/s390x/gen-features.c +9 -6
index 219b1f9420..242c95ede4 100644
@@ -706,23 +706,25 @@ static uint16_t qemu_V4_1[] = {
     S390_FEAT_VECTOR,
 };
 
-static uint16_t qemu_LATEST[] = {
+static uint16_t qemu_V6_0[] = {
     S390_FEAT_ACCESS_EXCEPTION_FS_INDICATION,
     S390_FEAT_SIDE_EFFECT_ACCESS_ESOP2,
     S390_FEAT_ESOP,
 };
 
-/* add all new definitions before this point */
-static uint16_t qemu_MAX[] = {
-    /* generates a dependency warning, leave it out for now */
-    S390_FEAT_MSA_EXT_5,
-    /* features introduced after the z13 */
+static uint16_t qemu_LATEST[] = {
     S390_FEAT_INSTRUCTION_EXEC_PROT,
     S390_FEAT_MISC_INSTRUCTION_EXT2,
     S390_FEAT_MSA_EXT_8,
     S390_FEAT_VECTOR_ENH,
 };
 
+/* add all new definitions before this point */
+static uint16_t qemu_MAX[] = {
+    /* generates a dependency warning, leave it out for now */
+    S390_FEAT_MSA_EXT_5,
+};
+
 /****** END FEATURE DEFS ******/
 
 #define _YEARS  "2016"
@@ -839,6 +841,7 @@ static FeatGroupDefSpec QemuFeatDef[] = {
     QEMU_FEAT_INITIALIZER(V3_1),
     QEMU_FEAT_INITIALIZER(V4_0),
     QEMU_FEAT_INITIALIZER(V4_1),
+    QEMU_FEAT_INITIALIZER(V6_0),
     QEMU_FEAT_INITIALIZER(LATEST),
     QEMU_FEAT_INITIALIZER(MAX),
 };
Signature · 1 line
2.31.1