Skip to contentSkip to conversation

target/s390x: Use TCGv_i128

PATCH In review Richard Henderson 3 participants 25 messages Nov 11, 2022 – Nov 29, 2022

lore
Share & tools
lore
#0 lore raw

v2 cover target/s390x: Use TCGv_i128

Changes for v2:
* Fix the div bugs found by Ilya.
* Convert CDSG
* Improve CC resolution for CDSG+IPM.

Turned out the best testing so far for TCGv_i128 was CDSG, especially for 32-bit x86 host, where we have only 6 regs available for 13 parameters. Whee!

r~

Based-on: [email protected] ("tcg: Support for Int128 with helpers")

Ilya Leoshkevich (2):
tests/tcg/s390x: Add div.c
tests/tcg/s390x: Add clst.c

Richard Henderson (11):
tests/tcg/s390x: Add long-double.c target/s390x: Use a single return for helper_divs32/u32 target/s390x: Use a single return for helper_divs64/u64 target/s390x: Use Int128 for return from CLST target/s390x: Use Int128 for return from CKSM target/s390x: Use Int128 for return from TRE target/s390x: Copy wout_x1 to wout_x1_P target/s390x: Use Int128 for returning float128 target/s390x: Use Int128 for passing float128 target/s390x: Use tcg_gen_atomic_cmpxchg_i128 for CDSG target/s390x: Implement CC_OP_NZ in gen_op_calc_cc

 target/s390x/helper.h            |  54 ++++----
 target/s390x/tcg/fpu_helper.c    | 103 +++++++--------
 target/s390x/tcg/int_helper.c    |  64 ++++-----
 target/s390x/tcg/mem_helper.c    |  77 ++---------
 target/s390x/tcg/translate.c     | 217 +++++++++++++++++++++----------
 tests/tcg/s390x/clst.c           |  82 ++++++++++++
 tests/tcg/s390x/div.c            |  75 +++++++++++
 tests/tcg/s390x/long-double.c    |  24 ++++
 target/s390x/tcg/insn-data.h.inc |  60 ++++-----
 tests/tcg/s390x/Makefile.target  |   3 +
 10 files changed, 462 insertions(+), 297 deletions(-)
 create mode 100644 tests/tcg/s390x/clst.c
 create mode 100644 tests/tcg/s390x/div.c
 create mode 100644 tests/tcg/s390x/long-double.c
Signature · 1 line
2.34.1
#1 lore raw

PATCH v2 1/13 tests/tcg/s390x: Add div.c

From: Ilya Leoshkevich <[email protected]>

Add a basic test to prevent regressions.

Message-Id: <[email protected]>

---
 tests/tcg/s390x/div.c           | 40 +++++++++++++++++++++++++++++++++
 tests/tcg/s390x/Makefile.target |  1 +
 2 files changed, 41 insertions(+)
 create mode 100644 tests/tcg/s390x/div.c
tests/tcg/s390x/div.c new file +40 -0
new file mode 100644
index 0000000000..5807295614
@@ -0,0 +1,40 @@
+#include <assert.h>
+#include <stdint.h>
+
+static void test_dr(void)
+{
+    register int32_t r0 asm("r0") = -1;
+    register int32_t r1 asm("r1") = -4241;
+    int32_t b = 101, q, r;
+
+    asm("dr %[r0],%[b]"
+        : [r0] "+r" (r0), [r1] "+r" (r1)
+        : [b] "r" (b)
+        : "cc");
+    q = r1;
+    r = r0;
+    assert(q == -41);
+    assert(r == -100);
+}
+
+static void test_dlr(void)
+{
+    register uint32_t r0 asm("r0") = 0;
+    register uint32_t r1 asm("r1") = 4243;
+    uint32_t b = 101, q, r;
+
+    asm("dlr %[r0],%[b]"
+        : [r0] "+r" (r0), [r1] "+r" (r1)
+        : [b] "r" (b)
+        : "cc");
+    q = r1;
+    r = r0;
+    assert(q == 42);
+    assert(r == 1);
+}
+
+int main(void)
+{
+    test_dr();
+    test_dlr();
+}
tests/tcg/s390x/Makefile.target +1 -0
index 07fcc6d0ce..ab7a3bcfb2 100644
@@ -24,6 +24,7 @@ TESTS+=trap
 TESTS+=signals-s390x
 TESTS+=branch-relative-long
 TESTS+=noexec
+TESTS+=div
 
 Z13_TESTS=vistr
 $(Z13_TESTS): CFLAGS+=-march=z13 -O2
Signature · 1 line
2.34.1
#2 lore raw

PATCH v2 2/13 tests/tcg/s390x: Add clst.c

In reply to Richard Henderson

From: Ilya Leoshkevich <[email protected]>

Add a basic test to prevent regressions.

Message-Id: <[email protected]>

---
 tests/tcg/s390x/clst.c          | 82 +++++++++++++++++++++++++++++++++
 tests/tcg/s390x/Makefile.target |  1 +
 2 files changed, 83 insertions(+)
 create mode 100644 tests/tcg/s390x/clst.c
tests/tcg/s390x/clst.c new file +82 -0
new file mode 100644
index 0000000000..ed2fe7326c
@@ -0,0 +1,82 @@
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+
+static int clst(char sep, const char **s1, const char **s2)
+{
+    const char *r1 = *s1;
+    const char *r2 = *s2;
+    int cc;
+
+    do {
+        register int r0 asm("r0") = sep;
+
+        asm("clst %[r1],%[r2]\n"
+            "ipm %[cc]\n"
+            "srl %[cc],28"
+            : [r1] "+r" (r1), [r2] "+r" (r2), "+r" (r0), [cc] "=r" (cc)
+            :
+            : "cc");
+        *s1 = r1;
+        *s2 = r2;
+    } while (cc == 3);
+
+    return cc;
+}
+
+static const struct test {
+    const char *name;
+    char sep;
+    const char *s1;
+    const char *s2;
+    int exp_cc;
+    int exp_off;
+} tests[] = {
+    {
+        .name = "cc0",
+        .sep = 0,
+        .s1 = "aa",
+        .s2 = "aa",
+        .exp_cc = 0,
+        .exp_off = 0,
+    },
+    {
+        .name = "cc1",
+        .sep = 1,
+        .s1 = "a\x01",
+        .s2 = "aa\x01",
+        .exp_cc = 1,
+        .exp_off = 1,
+    },
+    {
+        .name = "cc2",
+        .sep = 2,
+        .s1 = "abc\x02",
+        .s2 = "abb\x02",
+        .exp_cc = 2,
+        .exp_off = 2,
+    },
+};
+
+int main(void)
+{
+    const struct test *t;
+    const char *s1, *s2;
+    size_t i;
+    int cc;
+
+    for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) {
+        t = &tests[i];
+        s1 = t->s1;
+        s2 = t->s2;
+        cc = clst(t->sep, &s1, &s2);
+        if (cc != t->exp_cc ||
+                s1 != t->s1 + t->exp_off ||
+                s2 != t->s2 + t->exp_off) {
+            fprintf(stderr, "%s\n", t->name);
+            return EXIT_FAILURE;
+        }
+    }
+
+    return EXIT_SUCCESS;
+}
tests/tcg/s390x/Makefile.target +1 -0
index ab7a3bcfb2..79250f31dd 100644
@@ -25,6 +25,7 @@ TESTS+=signals-s390x
 TESTS+=branch-relative-long
 TESTS+=noexec
 TESTS+=div
+TESTS+=clst
 
 Z13_TESTS=vistr
 $(Z13_TESTS): CFLAGS+=-march=z13 -O2
Signature · 1 line
2.34.1
#3 lore raw

PATCH v2 3/13 tests/tcg/s390x: Add long-double.c

In reply to Richard Henderson
---
 tests/tcg/s390x/long-double.c   | 24 ++++++++++++++++++++++++
 tests/tcg/s390x/Makefile.target |  1 +
 2 files changed, 25 insertions(+)
 create mode 100644 tests/tcg/s390x/long-double.c
tests/tcg/s390x/long-double.c new file +24 -0
new file mode 100644
index 0000000000..757a6262fd
@@ -0,0 +1,24 @@
+/*
+ * Perform some basic arithmetic with long double, as a sanity check.
+ * With small integral numbers, we can cross-check with integers.
+ */
+
+#include <assert.h>
+
+int main()
+{
+    int i, j;
+
+    for (i = 1; i < 5; i++) {
+        for (j = 1; j < 5; j++) {
+            long double la = (long double)i + j;
+            long double lm = (long double)i * j;
+            long double ls = (long double)i - j;
+
+            assert(la == i + j);
+            assert(lm == i * j);
+            assert(ls == i - j);
+        }
+    }
+    return 0;
+}
tests/tcg/s390x/Makefile.target +1 -0
index 79250f31dd..1d454270c0 100644
@@ -26,6 +26,7 @@ TESTS+=branch-relative-long
 TESTS+=noexec
 TESTS+=div
 TESTS+=clst
+TESTS+=long-double
 
 Z13_TESTS=vistr
 $(Z13_TESTS): CFLAGS+=-march=z13 -O2
Signature · 1 line
2.34.1
#4 lore raw

PATCH v2 4/13 target/s390x: Use a single return for helper_divs32/u32

In reply to Richard Henderson

Pack the quotient and remainder into a single uint64_t.

---
v2: Fix operand ordering; use tcg_extr32_i64.

---
 target/s390x/helper.h         |  2 +-
 target/s390x/tcg/int_helper.c | 26 +++++++++++++-------------
 target/s390x/tcg/translate.c  |  8 ++++----
 3 files changed, 18 insertions(+), 18 deletions(-)
target/s390x/helper.h +1 -1
index bf33d86f74..97a9668eef 100644
@@ -10,7 +10,7 @@ DEF_HELPER_FLAGS_4(clc, TCG_CALL_NO_WG, i32, env, i32, i64, i64)
 DEF_HELPER_3(mvcl, i32, env, i32, i32)
 DEF_HELPER_3(clcl, i32, env, i32, i32)
 DEF_HELPER_FLAGS_4(clm, TCG_CALL_NO_WG, i32, env, i32, i32, i64)
-DEF_HELPER_FLAGS_3(divs32, TCG_CALL_NO_WG, s64, env, s64, s64)
+DEF_HELPER_FLAGS_3(divs32, TCG_CALL_NO_WG, i64, env, s64, s64)
 DEF_HELPER_FLAGS_3(divu32, TCG_CALL_NO_WG, i64, env, i64, i64)
 DEF_HELPER_FLAGS_3(divs64, TCG_CALL_NO_WG, s64, env, s64, s64)
 DEF_HELPER_FLAGS_4(divu64, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
target/s390x/tcg/int_helper.c +13 -13
index 954542388a..7260583cf2 100644
@@ -34,45 +34,45 @@
 #endif
 
 /* 64/32 -> 32 signed division */
-int64_t HELPER(divs32)(CPUS390XState *env, int64_t a, int64_t b64)
+uint64_t HELPER(divs32)(CPUS390XState *env, int64_t a, int64_t b64)
 {
-    int32_t ret, b = b64;
-    int64_t q;
+    int32_t b = b64;
+    int64_t q, r;
 
     if (b == 0) {
         tcg_s390_program_interrupt(env, PGM_FIXPT_DIVIDE, GETPC());
     }
 
-    ret = q = a / b;
-    env->retxl = a % b;
+    q = a / b;
+    r = a % b;
 
     /* Catch non-representable quotient.  */
-    if (ret != q) {
+    if (q != (int32_t)q) {
         tcg_s390_program_interrupt(env, PGM_FIXPT_DIVIDE, GETPC());
     }
 
-    return ret;
+    return deposit64(q, 32, 32, r);
 }
 
 /* 64/32 -> 32 unsigned division */
 uint64_t HELPER(divu32)(CPUS390XState *env, uint64_t a, uint64_t b64)
 {
-    uint32_t ret, b = b64;
-    uint64_t q;
+    uint32_t b = b64;
+    uint64_t q, r;
 
     if (b == 0) {
         tcg_s390_program_interrupt(env, PGM_FIXPT_DIVIDE, GETPC());
     }
 
-    ret = q = a / b;
-    env->retxl = a % b;
+    q = a / b;
+    r = a % b;
 
     /* Catch non-representable quotient.  */
-    if (ret != q) {
+    if (q != (uint32_t)q) {
         tcg_s390_program_interrupt(env, PGM_FIXPT_DIVIDE, GETPC());
     }
 
-    return ret;
+    return deposit64(q, 32, 32, r);
 }
 
 /* 64/64 -> 64 signed division */
target/s390x/tcg/translate.c +4 -4
index 2fbdab7252..9c2ea15c8d 100644
@@ -2395,15 +2395,15 @@ static DisasJumpType op_diag(DisasContext *s, DisasOps *o)
 
 static DisasJumpType op_divs32(DisasContext *s, DisasOps *o)
 {
-    gen_helper_divs32(o->out2, cpu_env, o->in1, o->in2);
-    return_low128(o->out);
+    gen_helper_divs32(o->out, cpu_env, o->in1, o->in2);
+    tcg_gen_extr32_i64(o->out2, o->out, o->out);
     return DISAS_NEXT;
 }
 
 static DisasJumpType op_divu32(DisasContext *s, DisasOps *o)
 {
-    gen_helper_divu32(o->out2, cpu_env, o->in1, o->in2);
-    return_low128(o->out);
+    gen_helper_divu32(o->out, cpu_env, o->in1, o->in2);
+    tcg_gen_extr32_i64(o->out2, o->out, o->out);
     return DISAS_NEXT;
 }
 
Signature · 1 line
2.34.1
Acked-by on v2 4/13
#5 lore raw

Re: [PATCH for-8.0 v2 04/13] target/s390x: Use a single return for helper_divs32/u32

Quoted 10 lines · Richard Henderson

Pack the quotient and remainder into a single uint64_t.

---
v2: Fix operand ordering; use tcg_extr32_i64.

---
 target/s390x/helper.h         |  2 +-
 target/s390x/tcg/int_helper.c | 26 +++++++++++++-------------
 target/s390x/tcg/translate.c  |  8 ++++----
 3 files changed, 18 insertions(+), 18 deletions(-)
#6 lore raw

PATCH v2 5/13 target/s390x: Use a single return for helper_divs64/u64

In reply to Richard Henderson

Pack the quotient and remainder into a single Int128. Use the divu128 primitive to remove the cpu_abort on 32-bit hosts.

---
v2: Extended div test case to cover these insns.

---
 target/s390x/helper.h         |  4 ++--
 target/s390x/tcg/int_helper.c | 38 +++++++++--------------------------
 target/s390x/tcg/translate.c  | 14 +++++++++----
 tests/tcg/s390x/div.c         | 35 ++++++++++++++++++++++++++++++++
 4 files changed, 56 insertions(+), 35 deletions(-)
target/s390x/helper.h +2 -2
index 97a9668eef..29986557ed 100644
@@ -12,8 +12,8 @@ DEF_HELPER_3(clcl, i32, env, i32, i32)
 DEF_HELPER_FLAGS_4(clm, TCG_CALL_NO_WG, i32, env, i32, i32, i64)
 DEF_HELPER_FLAGS_3(divs32, TCG_CALL_NO_WG, i64, env, s64, s64)
 DEF_HELPER_FLAGS_3(divu32, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_3(divs64, TCG_CALL_NO_WG, s64, env, s64, s64)
-DEF_HELPER_FLAGS_4(divu64, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
+DEF_HELPER_FLAGS_3(divs64, TCG_CALL_NO_WG, i128, env, s64, s64)
+DEF_HELPER_FLAGS_4(divu64, TCG_CALL_NO_WG, i128, env, i64, i64, i64)
 DEF_HELPER_3(srst, void, env, i32, i32)
 DEF_HELPER_3(srstu, void, env, i32, i32)
 DEF_HELPER_4(clst, i64, env, i64, i64, i64)
target/s390x/tcg/int_helper.c +9 -29
index 7260583cf2..eb8e6dd1b5 100644
@@ -76,46 +76,26 @@ uint64_t HELPER(divu32)(CPUS390XState *env, uint64_t a, uint64_t b64)
 }
 
 /* 64/64 -> 64 signed division */
-int64_t HELPER(divs64)(CPUS390XState *env, int64_t a, int64_t b)
+Int128 HELPER(divs64)(CPUS390XState *env, int64_t a, int64_t b)
 {
     /* Catch divide by zero, and non-representable quotient (MIN / -1).  */
     if (b == 0 || (b == -1 && a == (1ll << 63))) {
         tcg_s390_program_interrupt(env, PGM_FIXPT_DIVIDE, GETPC());
     }
-    env->retxl = a % b;
-    return a / b;
+    return int128_make128(a / b, a % b);
 }
 
 /* 128 -> 64/64 unsigned division */
-uint64_t HELPER(divu64)(CPUS390XState *env, uint64_t ah, uint64_t al,
-                        uint64_t b)
+Int128 HELPER(divu64)(CPUS390XState *env, uint64_t ah, uint64_t al, uint64_t b)
 {
-    uint64_t ret;
-    /* Signal divide by zero.  */
-    if (b == 0) {
-        tcg_s390_program_interrupt(env, PGM_FIXPT_DIVIDE, GETPC());
-    }
-    if (ah == 0) {
-        /* 64 -> 64/64 case */
-        env->retxl = al % b;
-        ret = al / b;
-    } else {
-        /* ??? Move i386 idivq helper to host-utils.  */
-#ifdef CONFIG_INT128
-        __uint128_t a = ((__uint128_t)ah << 64) | al;
-        __uint128_t q = a / b;
-        env->retxl = a % b;
-        ret = q;
-        if (ret != q) {
-            tcg_s390_program_interrupt(env, PGM_FIXPT_DIVIDE, GETPC());
+    if (b != 0) {
+        uint64_t r = divu128(&al, &ah, b);
+        if (ah == 0) {
+            return int128_make128(al, r);
         }
-#else
-        /* 32-bit hosts would need special wrapper functionality - just abort if
-           we encounter such a case; it's very unlikely anyways. */
-        cpu_abort(env_cpu(env), "128 -> 64/64 division not implemented\n");
-#endif
     }
-    return ret;
+    /* divide by zero or overflow */
+    tcg_s390_program_interrupt(env, PGM_FIXPT_DIVIDE, GETPC());
 }
 
 uint64_t HELPER(cvd)(int32_t reg)
target/s390x/tcg/translate.c +10 -4
index 9c2ea15c8d..36613bb20b 100644
@@ -2409,15 +2409,21 @@ static DisasJumpType op_divu32(DisasContext *s, DisasOps *o)
 
 static DisasJumpType op_divs64(DisasContext *s, DisasOps *o)
 {
-    gen_helper_divs64(o->out2, cpu_env, o->in1, o->in2);
-    return_low128(o->out);
+    TCGv_i128 t = tcg_temp_new_i128();
+
+    gen_helper_divs64(t, cpu_env, o->in1, o->in2);
+    tcg_gen_extr_i128_i64(o->out2, o->out, t);
+    tcg_temp_free_i128(t);
     return DISAS_NEXT;
 }
 
 static DisasJumpType op_divu64(DisasContext *s, DisasOps *o)
 {
-    gen_helper_divu64(o->out2, cpu_env, o->out, o->out2, o->in2);
-    return_low128(o->out);
+    TCGv_i128 t = tcg_temp_new_i128();
+
+    gen_helper_divu64(t, cpu_env, o->out, o->out2, o->in2);
+    tcg_gen_extr_i128_i64(o->out2, o->out, t);
+    tcg_temp_free_i128(t);
     return DISAS_NEXT;
 }
 
tests/tcg/s390x/div.c +35 -0
index 5807295614..6ad9900e08 100644
@@ -33,8 +33,43 @@ static void test_dlr(void)
     assert(r == 1);
 }
 
+static void test_dsgr(void)
+{
+    register int64_t r0 asm("r0") = -1;
+    register int64_t r1 asm("r1") = -4241;
+    int64_t b = 101, q, r;
+
+    asm("dsgr %[r0],%[b]"
+        : [r0] "+r" (r0), [r1] "+r" (r1)
+        : [b] "r" (b)
+        : "cc");
+    q = r1;
+    r = r0;
+    assert(q == -41);
+    assert(r == -100);
+}
+
+static void test_dlgr(void)
+{
+    register uint64_t r0 asm("r0") = 0;
+    register uint64_t r1 asm("r1") = 4243;
+    uint64_t b = 101, q, r;
+
+    asm("dlgr %[r0],%[b]"
+        : [r0] "+r" (r0), [r1] "+r" (r1)
+        : [b] "r" (b)
+        : "cc");
+    q = r1;
+    r = r0;
+    assert(q == 42);
+    assert(r == 1);
+}
+
 int main(void)
 {
     test_dr();
     test_dlr();
+    test_dsgr();
+    test_dlgr();
+    return 0;
 }
Signature · 1 line
2.34.1
#7 lore raw

PATCH v2 6/13 target/s390x: Use Int128 for return from CLST

In reply to Richard Henderson
---
 target/s390x/helper.h         |  2 +-
 target/s390x/tcg/mem_helper.c | 11 ++++-------
 target/s390x/tcg/translate.c  |  8 ++++++--
 3 files changed, 11 insertions(+), 10 deletions(-)
target/s390x/helper.h +1 -1
index 29986557ed..ba9ed11896 100644
@@ -16,7 +16,7 @@ DEF_HELPER_FLAGS_3(divs64, TCG_CALL_NO_WG, i128, env, s64, s64)
 DEF_HELPER_FLAGS_4(divu64, TCG_CALL_NO_WG, i128, env, i64, i64, i64)
 DEF_HELPER_3(srst, void, env, i32, i32)
 DEF_HELPER_3(srstu, void, env, i32, i32)
-DEF_HELPER_4(clst, i64, env, i64, i64, i64)
+DEF_HELPER_4(clst, i128, env, i64, i64, i64)
 DEF_HELPER_FLAGS_4(mvn, TCG_CALL_NO_WG, void, env, i32, i64, i64)
 DEF_HELPER_FLAGS_4(mvo, TCG_CALL_NO_WG, void, env, i32, i64, i64)
 DEF_HELPER_FLAGS_4(mvpg, TCG_CALL_NO_WG, i32, env, i64, i32, i32)
target/s390x/tcg/mem_helper.c +4 -7
index 3758b9e688..5a299ca9a2 100644
@@ -886,7 +886,7 @@ void HELPER(srstu)(CPUS390XState *env, uint32_t r1, uint32_t r2)
 }
 
 /* unsigned string compare (c is string terminator) */
-uint64_t HELPER(clst)(CPUS390XState *env, uint64_t c, uint64_t s1, uint64_t s2)
+Int128 HELPER(clst)(CPUS390XState *env, uint64_t c, uint64_t s1, uint64_t s2)
 {
     uintptr_t ra = GETPC();
     uint32_t len;
@@ -904,23 +904,20 @@ uint64_t HELPER(clst)(CPUS390XState *env, uint64_t c, uint64_t s1, uint64_t s2)
             if (v1 == c) {
                 /* Equal.  CC=0, and don't advance the registers.  */
                 env->cc_op = 0;
-                env->retxl = s2;
-                return s1;
+                return int128_make128(s2, s1);
             }
         } else {
             /* Unequal.  CC={1,2}, and advance the registers.  Note that
                the terminator need not be zero, but the string that contains
                the terminator is by definition "low".  */
             env->cc_op = (v1 == c ? 1 : v2 == c ? 2 : v1 < v2 ? 1 : 2);
-            env->retxl = s2 + len;
-            return s1 + len;
+            return int128_make128(s2 + len, s1 + len);
         }
     }
 
     /* CPU-determined bytes equal; advance the registers.  */
     env->cc_op = 3;
-    env->retxl = s2 + len;
-    return s1 + len;
+    return int128_make128(s2 + len, s1 + len);
 }
 
 /* move page */
target/s390x/tcg/translate.c +6 -2
index 36613bb20b..3708faec0e 100644
@@ -2164,9 +2164,13 @@ static DisasJumpType op_clm(DisasContext *s, DisasOps *o)
 
 static DisasJumpType op_clst(DisasContext *s, DisasOps *o)
 {
-    gen_helper_clst(o->in1, cpu_env, regs[0], o->in1, o->in2);
+    TCGv_i128 pair = tcg_temp_new_i128();
+
+    gen_helper_clst(pair, cpu_env, regs[0], o->in1, o->in2);
+    tcg_gen_extr_i128_i64(o->in2, o->in1, pair);
+    tcg_temp_free_i128(pair);
+
     set_cc_static(s);
-    return_low128(o->in2);
     return DISAS_NEXT;
 }
 
Signature · 1 line
2.34.1
#8 lore raw

PATCH v2 7/13 target/s390x: Use Int128 for return from CKSM

In reply to Richard Henderson
---
 target/s390x/helper.h         | 2 +-
 target/s390x/tcg/mem_helper.c | 7 +++----
 target/s390x/tcg/translate.c  | 6 ++++--
 3 files changed, 8 insertions(+), 7 deletions(-)
target/s390x/helper.h +1 -1
index ba9ed11896..16045b6dbe 100644
@@ -103,7 +103,7 @@ DEF_HELPER_4(tre, i64, env, i64, i64, i64)
 DEF_HELPER_4(trt, i32, env, i32, i64, i64)
 DEF_HELPER_4(trtr, i32, env, i32, i64, i64)
 DEF_HELPER_5(trXX, i32, env, i32, i32, i32, i32)
-DEF_HELPER_4(cksm, i64, env, i64, i64, i64)
+DEF_HELPER_4(cksm, i128, env, i64, i64, i64)
 DEF_HELPER_FLAGS_5(calc_cc, TCG_CALL_NO_RWG_SE, i32, env, i32, i64, i64, i64)
 DEF_HELPER_FLAGS_2(sfpc, TCG_CALL_NO_WG, void, env, i64)
 DEF_HELPER_FLAGS_2(sfas, TCG_CALL_NO_WG, void, env, i64)
target/s390x/tcg/mem_helper.c +3 -4
index 5a299ca9a2..bb6714aee4 100644
@@ -1350,8 +1350,8 @@ uint32_t HELPER(clclu)(CPUS390XState *env, uint32_t r1, uint64_t a2,
 }
 
 /* checksum */
-uint64_t HELPER(cksm)(CPUS390XState *env, uint64_t r1,
-                      uint64_t src, uint64_t src_len)
+Int128 HELPER(cksm)(CPUS390XState *env, uint64_t r1,
+                    uint64_t src, uint64_t src_len)
 {
     uintptr_t ra = GETPC();
     uint64_t max_len, len;
@@ -1392,8 +1392,7 @@ uint64_t HELPER(cksm)(CPUS390XState *env, uint64_t r1,
     env->cc_op = (len == src_len ? 0 : 3);
 
     /* Return both cksm and processed length.  */
-    env->retxl = cksm;
-    return len;
+    return int128_make128(cksm, len);
 }
 
 void HELPER(pack)(CPUS390XState *env, uint32_t len, uint64_t dest, uint64_t src)
target/s390x/tcg/translate.c +4 -2
index 3708faec0e..112ec35160 100644
@@ -2041,11 +2041,13 @@ static DisasJumpType op_cxlgb(DisasContext *s, DisasOps *o)
 static DisasJumpType op_cksm(DisasContext *s, DisasOps *o)
 {
     int r2 = get_field(s, r2);
+    TCGv_i128 pair = tcg_temp_new_i128();
     TCGv_i64 len = tcg_temp_new_i64();
 
-    gen_helper_cksm(len, cpu_env, o->in1, o->in2, regs[r2 + 1]);
+    gen_helper_cksm(pair, cpu_env, o->in1, o->in2, regs[r2 + 1]);
     set_cc_static(s);
-    return_low128(o->out);
+    tcg_gen_extr_i128_i64(o->out, len, pair);
+    tcg_temp_free_i128(pair);
 
     tcg_gen_add_i64(regs[r2], regs[r2], len);
     tcg_gen_sub_i64(regs[r2 + 1], regs[r2 + 1], len);
Signature · 1 line
2.34.1
#9 lore raw

PATCH v2 8/13 target/s390x: Use Int128 for return from TRE

In reply to Richard Henderson
---
 target/s390x/helper.h         | 2 +-
 target/s390x/tcg/mem_helper.c | 7 +++----
 target/s390x/tcg/translate.c  | 7 +++++--
 3 files changed, 9 insertions(+), 7 deletions(-)
target/s390x/helper.h +1 -1
index 16045b6dbe..aaea177246 100644
@@ -99,7 +99,7 @@ DEF_HELPER_FLAGS_4(unpka, TCG_CALL_NO_WG, i32, env, i64, i32, i64)
 DEF_HELPER_FLAGS_4(unpku, TCG_CALL_NO_WG, i32, env, i64, i32, i64)
 DEF_HELPER_FLAGS_3(tp, TCG_CALL_NO_WG, i32, env, i64, i32)
 DEF_HELPER_FLAGS_4(tr, TCG_CALL_NO_WG, void, env, i32, i64, i64)
-DEF_HELPER_4(tre, i64, env, i64, i64, i64)
+DEF_HELPER_4(tre, i128, env, i64, i64, i64)
 DEF_HELPER_4(trt, i32, env, i32, i64, i64)
 DEF_HELPER_4(trtr, i32, env, i32, i64, i64)
 DEF_HELPER_5(trXX, i32, env, i32, i32, i32, i32)
target/s390x/tcg/mem_helper.c +3 -4
index bb6714aee4..caf8c408ef 100644
@@ -1632,8 +1632,8 @@ void HELPER(tr)(CPUS390XState *env, uint32_t len, uint64_t array,
     do_helper_tr(env, len, array, trans, GETPC());
 }
 
-uint64_t HELPER(tre)(CPUS390XState *env, uint64_t array,
-                     uint64_t len, uint64_t trans)
+Int128 HELPER(tre)(CPUS390XState *env, uint64_t array,
+                   uint64_t len, uint64_t trans)
 {
     uintptr_t ra = GETPC();
     uint8_t end = env->regs[0] & 0xff;
@@ -1668,8 +1668,7 @@ uint64_t HELPER(tre)(CPUS390XState *env, uint64_t array,
     }
 
     env->cc_op = cc;
-    env->retxl = len - i;
-    return array + i;
+    return int128_make128(len - i, array + i);
 }
 
 static inline uint32_t do_helper_trt(CPUS390XState *env, int len,
target/s390x/tcg/translate.c +5 -2
index 112ec35160..4ad951a46f 100644
@@ -4903,8 +4903,11 @@ static DisasJumpType op_tr(DisasContext *s, DisasOps *o)
 
 static DisasJumpType op_tre(DisasContext *s, DisasOps *o)
 {
-    gen_helper_tre(o->out, cpu_env, o->out, o->out2, o->in2);
-    return_low128(o->out2);
+    TCGv_i128 pair = tcg_temp_new_i128();
+
+    gen_helper_tre(pair, cpu_env, o->out, o->out2, o->in2);
+    tcg_gen_extr_i128_i64(o->out2, o->out, pair);
+    tcg_temp_free_i128(pair);
     set_cc_static(s);
     return DISAS_NEXT;
 }
Signature · 1 line
2.34.1
#10 lore raw

PATCH v2 9/13 target/s390x: Copy wout_x1 to wout_x1_P

In reply to Richard Henderson

Make a copy of wout_x1 before modifying it, as wout_x1_P emphasizing that it operates on the out/out2 pair. The insns that use x1_P are data movement that will not change to Int128.

---
 target/s390x/tcg/translate.c     |  8 ++++++++
 target/s390x/tcg/insn-data.h.inc | 12 ++++++------
 2 files changed, 14 insertions(+), 6 deletions(-)
target/s390x/tcg/translate.c +8 -0
index 4ad951a46f..3b9c9d3b3a 100644
@@ -5516,6 +5516,14 @@ static void wout_x1(DisasContext *s, DisasOps *o)
 }
 #define SPEC_wout_x1 SPEC_r1_f128
 
+static void wout_x1_P(DisasContext *s, DisasOps *o)
+{
+    int f1 = get_field(s, r1);
+    store_freg(f1, o->out);
+    store_freg(f1 + 2, o->out2);
+}
+#define SPEC_wout_x1_P SPEC_r1_f128
+
 static void wout_cond_r1r2_32(DisasContext *s, DisasOps *o)
 {
     if (get_field(s, r1) != get_field(s, r2)) {
target/s390x/tcg/insn-data.h.inc +6 -6
index 7e952bdfc8..87c04f89da 100644
@@ -422,7 +422,7 @@
     F(0x3800, LER,     RR_a,  Z,   0, e2, 0, cond_e1e2, mov2, 0, IF_AFP1 | IF_AFP2)
     F(0x7800, LE,      RX_a,  Z,   0, m2_32u, 0, e1, mov2, 0, IF_AFP1)
     F(0xed64, LEY,     RXY_a, LD,  0, m2_32u, 0, e1, mov2, 0, IF_AFP1)
-    F(0xb365, LXR,     RRE,   Z,   x2h, x2l, 0, x1, movx, 0, IF_AFP1)
+    F(0xb365, LXR,     RRE,   Z,   x2h, x2l, 0, x1_P, movx, 0, IF_AFP1)
 /* LOAD IMMEDIATE */
     C(0xc001, LGFI,    RIL_a, EI,  0, i2, 0, r1, mov2, 0)
 /* LOAD RELATIVE LONG */
@@ -461,7 +461,7 @@
     C(0xe332, LTGF,    RXY_a, GIE, 0, a2, r1, 0, ld32s, s64)
     F(0xb302, LTEBR,   RRE,   Z,   0, e2, 0, cond_e1e2, mov2, f32, IF_BFP)
     F(0xb312, LTDBR,   RRE,   Z,   0, f2, 0, f1, mov2, f64, IF_BFP)
-    F(0xb342, LTXBR,   RRE,   Z,   x2h, x2l, 0, x1, movx, f128, IF_BFP)
+    F(0xb342, LTXBR,   RRE,   Z,   x2h, x2l, 0, x1_P, movx, f128, IF_BFP)
 /* LOAD AND TRAP */
     C(0xe39f, LAT,     RXY_a, LAT, 0, m2_32u, r1, 0, lat, 0)
     C(0xe385, LGAT,    RXY_a, LAT, 0, a2, r1, 0, lgat, 0)
@@ -483,7 +483,7 @@
     C(0xb913, LCGFR,   RRE,   Z,   0, r2_32s, r1, 0, neg, neg64)
     F(0xb303, LCEBR,   RRE,   Z,   0, e2, new, e1, negf32, f32, IF_BFP)
     F(0xb313, LCDBR,   RRE,   Z,   0, f2, new, f1, negf64, f64, IF_BFP)
-    F(0xb343, LCXBR,   RRE,   Z,   x2h, x2l, new_P, x1, negf128, f128, IF_BFP)
+    F(0xb343, LCXBR,   RRE,   Z,   x2h, x2l, new_P, x1_P, negf128, f128, IF_BFP)
     F(0xb373, LCDFR,   RRE,   FPSSH, 0, f2, new, f1, negf64, 0, IF_AFP1 | IF_AFP2)
 /* LOAD COUNT TO BLOCK BOUNDARY */
     C(0xe727, LCBB,    RXE,   V,   la2, 0, r1, 0, lcbb, 0)
@@ -552,7 +552,7 @@
     C(0xb911, LNGFR,   RRE,   Z,   0, r2_32s, r1, 0, nabs, nabs64)
     F(0xb301, LNEBR,   RRE,   Z,   0, e2, new, e1, nabsf32, f32, IF_BFP)
     F(0xb311, LNDBR,   RRE,   Z,   0, f2, new, f1, nabsf64, f64, IF_BFP)
-    F(0xb341, LNXBR,   RRE,   Z,   x2h, x2l, new_P, x1, nabsf128, f128, IF_BFP)
+    F(0xb341, LNXBR,   RRE,   Z,   x2h, x2l, new_P, x1_P, nabsf128, f128, IF_BFP)
     F(0xb371, LNDFR,   RRE,   FPSSH, 0, f2, new, f1, nabsf64, 0, IF_AFP1 | IF_AFP2)
 /* LOAD ON CONDITION */
     C(0xb9f2, LOCR,    RRF_c, LOC, r1, r2, new, r1_32, loc, 0)
@@ -577,7 +577,7 @@
     C(0xb910, LPGFR,   RRE,   Z,   0, r2_32s, r1, 0, abs, abs64)
     F(0xb300, LPEBR,   RRE,   Z,   0, e2, new, e1, absf32, f32, IF_BFP)
     F(0xb310, LPDBR,   RRE,   Z,   0, f2, new, f1, absf64, f64, IF_BFP)
-    F(0xb340, LPXBR,   RRE,   Z,   x2h, x2l, new_P, x1, absf128, f128, IF_BFP)
+    F(0xb340, LPXBR,   RRE,   Z,   x2h, x2l, new_P, x1_P, absf128, f128, IF_BFP)
     F(0xb370, LPDFR,   RRE,   FPSSH, 0, f2, new, f1, absf64, 0, IF_AFP1 | IF_AFP2)
 /* LOAD REVERSED */
     C(0xb91f, LRVR,    RRE,   Z,   0, r2_32u, new, r1_32, rev32, 0)
@@ -588,7 +588,7 @@
 /* LOAD ZERO */
     F(0xb374, LZER,    RRE,   Z,   0, 0, 0, e1, zero, 0, IF_AFP1)
     F(0xb375, LZDR,    RRE,   Z,   0, 0, 0, f1, zero, 0, IF_AFP1)
-    F(0xb376, LZXR,    RRE,   Z,   0, 0, 0, x1, zero2, 0, IF_AFP1)
+    F(0xb376, LZXR,    RRE,   Z,   0, 0, 0, x1_P, zero2, 0, IF_AFP1)
 
 /* LOAD FPC */
     F(0xb29d, LFPC,    S,     Z,   0, m2_32u, 0, 0, sfpc, 0, IF_BFP)
Signature · 1 line
2.34.1
#11 lore raw

PATCH v2 10/13 target/s390x: Use Int128 for returning float128

In reply to Richard Henderson

---
v2: Remove extraneous return_low128.

---
 target/s390x/helper.h            | 22 +++++++-------
 target/s390x/tcg/fpu_helper.c    | 29 +++++++++---------
 target/s390x/tcg/translate.c     | 51 +++++++++++++++++---------------
 target/s390x/tcg/insn-data.h.inc | 20 ++++++-------
 4 files changed, 63 insertions(+), 59 deletions(-)
target/s390x/helper.h +11 -11
index aaea177246..429131a85e 100644
@@ -31,32 +31,32 @@ DEF_HELPER_4(clcle, i32, env, i32, i64, i32)
 DEF_HELPER_4(clclu, i32, env, i32, i64, i32)
 DEF_HELPER_3(cegb, i64, env, s64, i32)
 DEF_HELPER_3(cdgb, i64, env, s64, i32)
-DEF_HELPER_3(cxgb, i64, env, s64, i32)
+DEF_HELPER_3(cxgb, i128, env, s64, i32)
 DEF_HELPER_3(celgb, i64, env, i64, i32)
 DEF_HELPER_3(cdlgb, i64, env, i64, i32)
-DEF_HELPER_3(cxlgb, i64, env, i64, i32)
+DEF_HELPER_3(cxlgb, i128, env, i64, i32)
 DEF_HELPER_4(cdsg, void, env, i64, i32, i32)
 DEF_HELPER_4(cdsg_parallel, void, env, i64, i32, i32)
 DEF_HELPER_4(csst, i32, env, i32, i64, i64)
 DEF_HELPER_4(csst_parallel, i32, env, i32, i64, i64)
 DEF_HELPER_FLAGS_3(aeb, TCG_CALL_NO_WG, i64, env, i64, i64)
 DEF_HELPER_FLAGS_3(adb, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_5(axb, TCG_CALL_NO_WG, i64, env, i64, i64, i64, i64)
+DEF_HELPER_FLAGS_5(axb, TCG_CALL_NO_WG, i128, env, i64, i64, i64, i64)
 DEF_HELPER_FLAGS_3(seb, TCG_CALL_NO_WG, i64, env, i64, i64)
 DEF_HELPER_FLAGS_3(sdb, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_5(sxb, TCG_CALL_NO_WG, i64, env, i64, i64, i64, i64)
+DEF_HELPER_FLAGS_5(sxb, TCG_CALL_NO_WG, i128, env, i64, i64, i64, i64)
 DEF_HELPER_FLAGS_3(deb, TCG_CALL_NO_WG, i64, env, i64, i64)
 DEF_HELPER_FLAGS_3(ddb, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_5(dxb, TCG_CALL_NO_WG, i64, env, i64, i64, i64, i64)
+DEF_HELPER_FLAGS_5(dxb, TCG_CALL_NO_WG, i128, env, i64, i64, i64, i64)
 DEF_HELPER_FLAGS_3(meeb, TCG_CALL_NO_WG, i64, env, i64, i64)
 DEF_HELPER_FLAGS_3(mdeb, TCG_CALL_NO_WG, i64, env, i64, i64)
 DEF_HELPER_FLAGS_3(mdb, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_5(mxb, TCG_CALL_NO_WG, i64, env, i64, i64, i64, i64)
-DEF_HELPER_FLAGS_4(mxdb, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
+DEF_HELPER_FLAGS_5(mxb, TCG_CALL_NO_WG, i128, env, i64, i64, i64, i64)
+DEF_HELPER_FLAGS_4(mxdb, TCG_CALL_NO_WG, i128, env, i64, i64, i64)
 DEF_HELPER_FLAGS_2(ldeb, TCG_CALL_NO_WG, i64, env, i64)
 DEF_HELPER_FLAGS_4(ldxb, TCG_CALL_NO_WG, i64, env, i64, i64, i32)
-DEF_HELPER_FLAGS_2(lxdb, TCG_CALL_NO_WG, i64, env, i64)
-DEF_HELPER_FLAGS_2(lxeb, TCG_CALL_NO_WG, i64, env, i64)
+DEF_HELPER_FLAGS_2(lxdb, TCG_CALL_NO_WG, i128, env, i64)
+DEF_HELPER_FLAGS_2(lxeb, TCG_CALL_NO_WG, i128, env, i64)
 DEF_HELPER_FLAGS_3(ledb, TCG_CALL_NO_WG, i64, env, i64, i32)
 DEF_HELPER_FLAGS_4(lexb, TCG_CALL_NO_WG, i64, env, i64, i64, i32)
 DEF_HELPER_FLAGS_3(ceb, TCG_CALL_NO_WG_SE, i32, env, i64, i64)
@@ -79,7 +79,7 @@ DEF_HELPER_3(clfdb, i64, env, i64, i32)
 DEF_HELPER_4(clfxb, i64, env, i64, i64, i32)
 DEF_HELPER_FLAGS_3(fieb, TCG_CALL_NO_WG, i64, env, i64, i32)
 DEF_HELPER_FLAGS_3(fidb, TCG_CALL_NO_WG, i64, env, i64, i32)
-DEF_HELPER_FLAGS_4(fixb, TCG_CALL_NO_WG, i64, env, i64, i64, i32)
+DEF_HELPER_FLAGS_4(fixb, TCG_CALL_NO_WG, i128, env, i64, i64, i32)
 DEF_HELPER_FLAGS_4(maeb, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
 DEF_HELPER_FLAGS_4(madb, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
 DEF_HELPER_FLAGS_4(mseb, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
@@ -89,7 +89,7 @@ DEF_HELPER_FLAGS_3(tcdb, TCG_CALL_NO_RWG_SE, i32, env, i64, i64)
 DEF_HELPER_FLAGS_4(tcxb, TCG_CALL_NO_RWG_SE, i32, env, i64, i64, i64)
 DEF_HELPER_FLAGS_2(sqeb, TCG_CALL_NO_WG, i64, env, i64)
 DEF_HELPER_FLAGS_2(sqdb, TCG_CALL_NO_WG, i64, env, i64)
-DEF_HELPER_FLAGS_3(sqxb, TCG_CALL_NO_WG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_3(sqxb, TCG_CALL_NO_WG, i128, env, i64, i64)
 DEF_HELPER_FLAGS_1(cvd, TCG_CALL_NO_RWG_SE, i64, s32)
 DEF_HELPER_FLAGS_4(pack, TCG_CALL_NO_WG, void, env, i32, i64, i64)
 DEF_HELPER_FLAGS_4(pka, TCG_CALL_NO_WG, void, env, i64, i64, i32)
target/s390x/tcg/fpu_helper.c +15 -14
index 4067205405..a584794be6 100644
@@ -34,7 +34,10 @@
 #define HELPER_LOG(x...)
 #endif
 
-#define RET128(F) (env->retxl = F.low, F.high)
+static inline Int128 RET128(float128 f)
+{
+    return int128_make128(f.low, f.high);
+}
 
 uint8_t s390_softfloat_exc_to_ieee(unsigned int exc)
 {
@@ -224,7 +227,7 @@ uint64_t HELPER(adb)(CPUS390XState *env, uint64_t f1, uint64_t f2)
 }
 
 /* 128-bit FP addition */
-uint64_t HELPER(axb)(CPUS390XState *env, uint64_t ah, uint64_t al,
+Int128 HELPER(axb)(CPUS390XState *env, uint64_t ah, uint64_t al,
                      uint64_t bh, uint64_t bl)
 {
     float128 ret = float128_add(make_float128(ah, al),
@@ -251,7 +254,7 @@ uint64_t HELPER(sdb)(CPUS390XState *env, uint64_t f1, uint64_t f2)
 }
 
 /* 128-bit FP subtraction */
-uint64_t HELPER(sxb)(CPUS390XState *env, uint64_t ah, uint64_t al,
+Int128 HELPER(sxb)(CPUS390XState *env, uint64_t ah, uint64_t al,
                      uint64_t bh, uint64_t bl)
 {
     float128 ret = float128_sub(make_float128(ah, al),
@@ -278,7 +281,7 @@ uint64_t HELPER(ddb)(CPUS390XState *env, uint64_t f1, uint64_t f2)
 }
 
 /* 128-bit FP division */
-uint64_t HELPER(dxb)(CPUS390XState *env, uint64_t ah, uint64_t al,
+Int128 HELPER(dxb)(CPUS390XState *env, uint64_t ah, uint64_t al,
                      uint64_t bh, uint64_t bl)
 {
     float128 ret = float128_div(make_float128(ah, al),
@@ -314,7 +317,7 @@ uint64_t HELPER(mdeb)(CPUS390XState *env, uint64_t f1, uint64_t f2)
 }
 
 /* 128-bit FP multiplication */
-uint64_t HELPER(mxb)(CPUS390XState *env, uint64_t ah, uint64_t al,
+Int128 HELPER(mxb)(CPUS390XState *env, uint64_t ah, uint64_t al,
                      uint64_t bh, uint64_t bl)
 {
     float128 ret = float128_mul(make_float128(ah, al),
@@ -325,8 +328,7 @@ uint64_t HELPER(mxb)(CPUS390XState *env, uint64_t ah, uint64_t al,
 }
 
 /* 128/64-bit FP multiplication */
-uint64_t HELPER(mxdb)(CPUS390XState *env, uint64_t ah, uint64_t al,
-                      uint64_t f2)
+Int128 HELPER(mxdb)(CPUS390XState *env, uint64_t ah, uint64_t al, uint64_t f2)
 {
     float128 ret = float64_to_float128(f2, &env->fpu_status);
     ret = float128_mul(make_float128(ah, al), ret, &env->fpu_status);
@@ -355,7 +357,7 @@ uint64_t HELPER(ldxb)(CPUS390XState *env, uint64_t ah, uint64_t al,
 }
 
 /* convert 64-bit float to 128-bit float */
-uint64_t HELPER(lxdb)(CPUS390XState *env, uint64_t f2)
+Int128 HELPER(lxdb)(CPUS390XState *env, uint64_t f2)
 {
     float128 ret = float64_to_float128(f2, &env->fpu_status);
     handle_exceptions(env, false, GETPC());
@@ -363,7 +365,7 @@ uint64_t HELPER(lxdb)(CPUS390XState *env, uint64_t f2)
 }
 
 /* convert 32-bit float to 128-bit float */
-uint64_t HELPER(lxeb)(CPUS390XState *env, uint64_t f2)
+Int128 HELPER(lxeb)(CPUS390XState *env, uint64_t f2)
 {
     float128 ret = float32_to_float128(f2, &env->fpu_status);
     handle_exceptions(env, false, GETPC());
@@ -486,7 +488,7 @@ uint64_t HELPER(cdgb)(CPUS390XState *env, int64_t v2, uint32_t m34)
 }
 
 /* convert 64-bit int to 128-bit float */
-uint64_t HELPER(cxgb)(CPUS390XState *env, int64_t v2, uint32_t m34)
+Int128 HELPER(cxgb)(CPUS390XState *env, int64_t v2, uint32_t m34)
 {
     int old_mode = s390_swap_bfp_rounding_mode(env, round_from_m34(m34));
     float128 ret = int64_to_float128(v2, &env->fpu_status);
@@ -519,7 +521,7 @@ uint64_t HELPER(cdlgb)(CPUS390XState *env, uint64_t v2, uint32_t m34)
 }
 
 /* convert 64-bit uint to 128-bit float */
-uint64_t HELPER(cxlgb)(CPUS390XState *env, uint64_t v2, uint32_t m34)
+Int128 HELPER(cxlgb)(CPUS390XState *env, uint64_t v2, uint32_t m34)
 {
     int old_mode = s390_swap_bfp_rounding_mode(env, round_from_m34(m34));
     float128 ret = uint64_to_float128(v2, &env->fpu_status);
@@ -748,8 +750,7 @@ uint64_t HELPER(fidb)(CPUS390XState *env, uint64_t f2, uint32_t m34)
 }
 
 /* round to integer 128-bit */
-uint64_t HELPER(fixb)(CPUS390XState *env, uint64_t ah, uint64_t al,
-                      uint32_t m34)
+Int128 HELPER(fixb)(CPUS390XState *env, uint64_t ah, uint64_t al, uint32_t m34)
 {
     int old_mode = s390_swap_bfp_rounding_mode(env, round_from_m34(m34));
     float128 ret = float128_round_to_int(make_float128(ah, al),
@@ -890,7 +891,7 @@ uint64_t HELPER(sqdb)(CPUS390XState *env, uint64_t f2)
 }
 
 /* square root 128-bit */
-uint64_t HELPER(sqxb)(CPUS390XState *env, uint64_t ah, uint64_t al)
+Int128 HELPER(sqxb)(CPUS390XState *env, uint64_t ah, uint64_t al)
 {
     float128 ret = float128_sqrt(make_float128(ah, al), &env->fpu_status);
     handle_exceptions(env, false, GETPC());
target/s390x/tcg/translate.c +27 -24

151 lines not on this page · raw message

target/s390x/tcg/insn-data.h.inc +10 -10
index 87c04f89da..d895a9e8a7 100644
@@ -306,10 +306,10 @@
 /* CONVERT FROM FIXED */
     F(0xb394, CEFBR,   RRF_e, Z,   0, r2_32s, new, e1, cegb, 0, IF_BFP)
     F(0xb395, CDFBR,   RRF_e, Z,   0, r2_32s, new, f1, cdgb, 0, IF_BFP)
-    F(0xb396, CXFBR,   RRF_e, Z,   0, r2_32s, new_P, x1, cxgb, 0, IF_BFP)
+    F(0xb396, CXFBR,   RRF_e, Z,   0, r2_32s, new_x, x1, cxgb, 0, IF_BFP)
     F(0xb3a4, CEGBR,   RRF_e, Z,   0, r2_o, new, e1, cegb, 0, IF_BFP)
     F(0xb3a5, CDGBR,   RRF_e, Z,   0, r2_o, new, f1, cdgb, 0, IF_BFP)
-    F(0xb3a6, CXGBR,   RRF_e, Z,   0, r2_o, new_P, x1, cxgb, 0, IF_BFP)
+    F(0xb3a6, CXGBR,   RRF_e, Z,   0, r2_o, new_x, x1, cxgb, 0, IF_BFP)
 /* CONVERT TO LOGICAL */
     F(0xb39c, CLFEBR,  RRF_e, FPE, 0, e2, new, r1_32, clfeb, 0, IF_BFP)
     F(0xb39d, CLFDBR,  RRF_e, FPE, 0, f2, new, r1_32, clfdb, 0, IF_BFP)
@@ -320,10 +320,10 @@
 /* CONVERT FROM LOGICAL */
     F(0xb390, CELFBR,  RRF_e, FPE, 0, r2_32u, new, e1, celgb, 0, IF_BFP)
     F(0xb391, CDLFBR,  RRF_e, FPE, 0, r2_32u, new, f1, cdlgb, 0, IF_BFP)
-    F(0xb392, CXLFBR,  RRF_e, FPE, 0, r2_32u, new_P, x1, cxlgb, 0, IF_BFP)
+    F(0xb392, CXLFBR,  RRF_e, FPE, 0, r2_32u, new_x, x1, cxlgb, 0, IF_BFP)
     F(0xb3a0, CELGBR,  RRF_e, FPE, 0, r2_o, new, e1, celgb, 0, IF_BFP)
     F(0xb3a1, CDLGBR,  RRF_e, FPE, 0, r2_o, new, f1, cdlgb, 0, IF_BFP)
-    F(0xb3a2, CXLGBR,  RRF_e, FPE, 0, r2_o, new_P, x1, cxlgb, 0, IF_BFP)
+    F(0xb3a2, CXLGBR,  RRF_e, FPE, 0, r2_o, new_x, x1, cxlgb, 0, IF_BFP)
 
 /* CONVERT UTF-8 TO UTF-16 */
     D(0xb2a7, CU12,    RRF_c, Z,   0, 0, 0, 0, cuXX, 0, 12)
@@ -597,15 +597,15 @@
 /* LOAD FP INTEGER */
     F(0xb357, FIEBR,   RRF_e, Z,   0, e2, new, e1, fieb, 0, IF_BFP)
     F(0xb35f, FIDBR,   RRF_e, Z,   0, f2, new, f1, fidb, 0, IF_BFP)
-    F(0xb347, FIXBR,   RRF_e, Z,   x2h, x2l, new_P, x1, fixb, 0, IF_BFP)
+    F(0xb347, FIXBR,   RRF_e, Z,   x2h, x2l, new_x, x1, fixb, 0, IF_BFP)
 
 /* LOAD LENGTHENED */
     F(0xb304, LDEBR,   RRE,   Z,   0, e2, new, f1, ldeb, 0, IF_BFP)
-    F(0xb305, LXDBR,   RRE,   Z,   0, f2, new_P, x1, lxdb, 0, IF_BFP)
-    F(0xb306, LXEBR,   RRE,   Z,   0, e2, new_P, x1, lxeb, 0, IF_BFP)
+    F(0xb305, LXDBR,   RRE,   Z,   0, f2, new_x, x1, lxdb, 0, IF_BFP)
+    F(0xb306, LXEBR,   RRE,   Z,   0, e2, new_x, x1, lxeb, 0, IF_BFP)
     F(0xed04, LDEB,    RXE,   Z,   0, m2_32u, new, f1, ldeb, 0, IF_BFP)
-    F(0xed05, LXDB,    RXE,   Z,   0, m2_64, new_P, x1, lxdb, 0, IF_BFP)
-    F(0xed06, LXEB,    RXE,   Z,   0, m2_32u, new_P, x1, lxeb, 0, IF_BFP)
+    F(0xed05, LXDB,    RXE,   Z,   0, m2_64, new_x, x1, lxdb, 0, IF_BFP)
+    F(0xed06, LXEB,    RXE,   Z,   0, m2_32u, new_x, x1, lxeb, 0, IF_BFP)
     F(0xb324, LDER,    RXE,   Z,   0, e2, new, f1, lde, 0, IF_AFP1)
     F(0xed24, LDE,     RXE,   Z,   0, m2_32u, new, f1, lde, 0, IF_AFP1)
 /* LOAD ROUNDED */
@@ -835,7 +835,7 @@
 /* SQUARE ROOT */
     F(0xb314, SQEBR,   RRE,   Z,   0, e2, new, e1, sqeb, 0, IF_BFP)
     F(0xb315, SQDBR,   RRE,   Z,   0, f2, new, f1, sqdb, 0, IF_BFP)
-    F(0xb316, SQXBR,   RRE,   Z,   x2h, x2l, new_P, x1, sqxb, 0, IF_BFP)
+    F(0xb316, SQXBR,   RRE,   Z,   x2h, x2l, new_x, x1, sqxb, 0, IF_BFP)
     F(0xed14, SQEB,    RXE,   Z,   0, m2_32u, new, e1, sqeb, 0, IF_BFP)
     F(0xed15, SQDB,    RXE,   Z,   0, m2_64, new, f1, sqdb, 0, IF_BFP)
 
Signature · 1 line
2.34.1
Acked-by on v2 10/13
#12 lore raw

Re: [PATCH for-8.0 v2 10/13] target/s390x: Use Int128 for returning float128

Quoted 10 lines · Richard Henderson

---
v2: Remove extraneous return_low128.

---
 target/s390x/helper.h            | 22 +++++++-------
 target/s390x/tcg/fpu_helper.c    | 29 +++++++++---------
 target/s390x/tcg/translate.c     | 51 +++++++++++++++++---------------
 target/s390x/tcg/insn-data.h.inc | 20 ++++++-------
 4 files changed, 63 insertions(+), 59 deletions(-)
#13 lore raw

PATCH v2 11/13 target/s390x: Use Int128 for passing float128

In reply to Richard Henderson

---
v2: Fix SPEC_in1_x1.

---
 target/s390x/helper.h            | 32 ++++++------
 target/s390x/tcg/fpu_helper.c    | 88 ++++++++++++++------------------
 target/s390x/tcg/translate.c     | 76 ++++++++++++++++++---------
 target/s390x/tcg/insn-data.h.inc | 30 +++++------
 4 files changed, 121 insertions(+), 105 deletions(-)
target/s390x/helper.h +16 -16
index 429131a85e..481b9019f9 100644
@@ -41,55 +41,55 @@ DEF_HELPER_4(csst, i32, env, i32, i64, i64)
 DEF_HELPER_4(csst_parallel, i32, env, i32, i64, i64)
 DEF_HELPER_FLAGS_3(aeb, TCG_CALL_NO_WG, i64, env, i64, i64)
 DEF_HELPER_FLAGS_3(adb, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_5(axb, TCG_CALL_NO_WG, i128, env, i64, i64, i64, i64)
+DEF_HELPER_FLAGS_3(axb, TCG_CALL_NO_WG, i128, env, i128, i128)
 DEF_HELPER_FLAGS_3(seb, TCG_CALL_NO_WG, i64, env, i64, i64)
 DEF_HELPER_FLAGS_3(sdb, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_5(sxb, TCG_CALL_NO_WG, i128, env, i64, i64, i64, i64)
+DEF_HELPER_FLAGS_3(sxb, TCG_CALL_NO_WG, i128, env, i128, i128)
 DEF_HELPER_FLAGS_3(deb, TCG_CALL_NO_WG, i64, env, i64, i64)
 DEF_HELPER_FLAGS_3(ddb, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_5(dxb, TCG_CALL_NO_WG, i128, env, i64, i64, i64, i64)
+DEF_HELPER_FLAGS_3(dxb, TCG_CALL_NO_WG, i128, env, i128, i128)
 DEF_HELPER_FLAGS_3(meeb, TCG_CALL_NO_WG, i64, env, i64, i64)
 DEF_HELPER_FLAGS_3(mdeb, TCG_CALL_NO_WG, i64, env, i64, i64)
 DEF_HELPER_FLAGS_3(mdb, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_5(mxb, TCG_CALL_NO_WG, i128, env, i64, i64, i64, i64)
-DEF_HELPER_FLAGS_4(mxdb, TCG_CALL_NO_WG, i128, env, i64, i64, i64)
+DEF_HELPER_FLAGS_3(mxb, TCG_CALL_NO_WG, i128, env, i128, i128)
+DEF_HELPER_FLAGS_3(mxdb, TCG_CALL_NO_WG, i128, env, i128, i64)
 DEF_HELPER_FLAGS_2(ldeb, TCG_CALL_NO_WG, i64, env, i64)
-DEF_HELPER_FLAGS_4(ldxb, TCG_CALL_NO_WG, i64, env, i64, i64, i32)
+DEF_HELPER_FLAGS_3(ldxb, TCG_CALL_NO_WG, i64, env, i128, i32)
 DEF_HELPER_FLAGS_2(lxdb, TCG_CALL_NO_WG, i128, env, i64)
 DEF_HELPER_FLAGS_2(lxeb, TCG_CALL_NO_WG, i128, env, i64)
 DEF_HELPER_FLAGS_3(ledb, TCG_CALL_NO_WG, i64, env, i64, i32)
-DEF_HELPER_FLAGS_4(lexb, TCG_CALL_NO_WG, i64, env, i64, i64, i32)
+DEF_HELPER_FLAGS_3(lexb, TCG_CALL_NO_WG, i64, env, i128, i32)
 DEF_HELPER_FLAGS_3(ceb, TCG_CALL_NO_WG_SE, i32, env, i64, i64)
 DEF_HELPER_FLAGS_3(cdb, TCG_CALL_NO_WG_SE, i32, env, i64, i64)
-DEF_HELPER_FLAGS_5(cxb, TCG_CALL_NO_WG_SE, i32, env, i64, i64, i64, i64)
+DEF_HELPER_FLAGS_3(cxb, TCG_CALL_NO_WG_SE, i32, env, i128, i128)
 DEF_HELPER_FLAGS_3(keb, TCG_CALL_NO_WG, i32, env, i64, i64)
 DEF_HELPER_FLAGS_3(kdb, TCG_CALL_NO_WG, i32, env, i64, i64)
-DEF_HELPER_FLAGS_5(kxb, TCG_CALL_NO_WG, i32, env, i64, i64, i64, i64)
+DEF_HELPER_FLAGS_3(kxb, TCG_CALL_NO_WG, i32, env, i128, i128)
 DEF_HELPER_3(cgeb, i64, env, i64, i32)
 DEF_HELPER_3(cgdb, i64, env, i64, i32)
-DEF_HELPER_4(cgxb, i64, env, i64, i64, i32)
+DEF_HELPER_3(cgxb, i64, env, i128, i32)
 DEF_HELPER_3(cfeb, i64, env, i64, i32)
 DEF_HELPER_3(cfdb, i64, env, i64, i32)
-DEF_HELPER_4(cfxb, i64, env, i64, i64, i32)
+DEF_HELPER_3(cfxb, i64, env, i128, i32)
 DEF_HELPER_3(clgeb, i64, env, i64, i32)
 DEF_HELPER_3(clgdb, i64, env, i64, i32)
-DEF_HELPER_4(clgxb, i64, env, i64, i64, i32)
+DEF_HELPER_3(clgxb, i64, env, i128, i32)
 DEF_HELPER_3(clfeb, i64, env, i64, i32)
 DEF_HELPER_3(clfdb, i64, env, i64, i32)
-DEF_HELPER_4(clfxb, i64, env, i64, i64, i32)
+DEF_HELPER_3(clfxb, i64, env, i128, i32)
 DEF_HELPER_FLAGS_3(fieb, TCG_CALL_NO_WG, i64, env, i64, i32)
 DEF_HELPER_FLAGS_3(fidb, TCG_CALL_NO_WG, i64, env, i64, i32)
-DEF_HELPER_FLAGS_4(fixb, TCG_CALL_NO_WG, i128, env, i64, i64, i32)
+DEF_HELPER_FLAGS_3(fixb, TCG_CALL_NO_WG, i128, env, i128, i32)
 DEF_HELPER_FLAGS_4(maeb, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
 DEF_HELPER_FLAGS_4(madb, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
 DEF_HELPER_FLAGS_4(mseb, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
 DEF_HELPER_FLAGS_4(msdb, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
 DEF_HELPER_FLAGS_3(tceb, TCG_CALL_NO_RWG_SE, i32, env, i64, i64)
 DEF_HELPER_FLAGS_3(tcdb, TCG_CALL_NO_RWG_SE, i32, env, i64, i64)
-DEF_HELPER_FLAGS_4(tcxb, TCG_CALL_NO_RWG_SE, i32, env, i64, i64, i64)
+DEF_HELPER_FLAGS_3(tcxb, TCG_CALL_NO_RWG_SE, i32, env, i128, i64)
 DEF_HELPER_FLAGS_2(sqeb, TCG_CALL_NO_WG, i64, env, i64)
 DEF_HELPER_FLAGS_2(sqdb, TCG_CALL_NO_WG, i64, env, i64)
-DEF_HELPER_FLAGS_3(sqxb, TCG_CALL_NO_WG, i128, env, i64, i64)
+DEF_HELPER_FLAGS_2(sqxb, TCG_CALL_NO_WG, i128, env, i128)
 DEF_HELPER_FLAGS_1(cvd, TCG_CALL_NO_RWG_SE, i64, s32)
 DEF_HELPER_FLAGS_4(pack, TCG_CALL_NO_WG, void, env, i32, i64, i64)
 DEF_HELPER_FLAGS_4(pka, TCG_CALL_NO_WG, void, env, i64, i64, i32)
target/s390x/tcg/fpu_helper.c +37 -51

213 lines not on this page · raw message

target/s390x/tcg/translate.c +53 -23

219 lines not on this page · raw message

target/s390x/tcg/insn-data.h.inc +15 -15
index d895a9e8a7..1a2a55bf5e 100644
@@ -34,7 +34,7 @@
     C(0xe318, AGF,     RXY_a, Z,   r1, m2_32s, r1, 0, add, adds64)
     F(0xb30a, AEBR,    RRE,   Z,   e1, e2, new, e1, aeb, f32, IF_BFP)
     F(0xb31a, ADBR,    RRE,   Z,   f1, f2, new, f1, adb, f64, IF_BFP)
-    F(0xb34a, AXBR,    RRE,   Z,   x2h, x2l, x1, x1, axb, f128, IF_BFP)
+    F(0xb34a, AXBR,    RRE,   Z,   x1, x2, new_x, x1, axb, f128, IF_BFP)
     F(0xed0a, AEB,     RXE,   Z,   e1, m2_32u, new, e1, aeb, f32, IF_BFP)
     F(0xed1a, ADB,     RXE,   Z,   f1, m2_64, new, f1, adb, f64, IF_BFP)
 /* ADD HIGH */
@@ -172,13 +172,13 @@
     C(0xe330, CGF,     RXY_a, Z,   r1_o, m2_32s, 0, 0, 0, cmps64)
     F(0xb309, CEBR,    RRE,   Z,   e1, e2, 0, 0, ceb, 0, IF_BFP)
     F(0xb319, CDBR,    RRE,   Z,   f1, f2, 0, 0, cdb, 0, IF_BFP)
-    F(0xb349, CXBR,    RRE,   Z,   x2h, x2l, x1, 0, cxb, 0, IF_BFP)
+    F(0xb349, CXBR,    RRE,   Z,   x1, x2, 0, 0, cxb, 0, IF_BFP)
     F(0xed09, CEB,     RXE,   Z,   e1, m2_32u, 0, 0, ceb, 0, IF_BFP)
     F(0xed19, CDB,     RXE,   Z,   f1, m2_64, 0, 0, cdb, 0, IF_BFP)
 /* COMPARE AND SIGNAL */
     F(0xb308, KEBR,    RRE,   Z,   e1, e2, 0, 0, keb, 0, IF_BFP)
     F(0xb318, KDBR,    RRE,   Z,   f1, f2, 0, 0, kdb, 0, IF_BFP)
-    F(0xb348, KXBR,    RRE,   Z,   x2h, x2l, x1, 0, kxb, 0, IF_BFP)
+    F(0xb348, KXBR,    RRE,   Z,   x1, x2, 0, 0, kxb, 0, IF_BFP)
     F(0xed08, KEB,     RXE,   Z,   e1, m2_32u, 0, 0, keb, 0, IF_BFP)
     F(0xed18, KDB,     RXE,   Z,   f1, m2_64, 0, 0, kdb, 0, IF_BFP)
 /* COMPARE IMMEDIATE */
@@ -299,10 +299,10 @@
 /* CONVERT TO FIXED */
     F(0xb398, CFEBR,   RRF_e, Z,   0, e2, new, r1_32, cfeb, 0, IF_BFP)
     F(0xb399, CFDBR,   RRF_e, Z,   0, f2, new, r1_32, cfdb, 0, IF_BFP)
-    F(0xb39a, CFXBR,   RRF_e, Z,   x2h, x2l, new, r1_32, cfxb, 0, IF_BFP)
+    F(0xb39a, CFXBR,   RRF_e, Z,   0, x2, new, r1_32, cfxb, 0, IF_BFP)
     F(0xb3a8, CGEBR,   RRF_e, Z,   0, e2, r1, 0, cgeb, 0, IF_BFP)
     F(0xb3a9, CGDBR,   RRF_e, Z,   0, f2, r1, 0, cgdb, 0, IF_BFP)
-    F(0xb3aa, CGXBR,   RRF_e, Z,   x2h, x2l, r1, 0, cgxb, 0, IF_BFP)
+    F(0xb3aa, CGXBR,   RRF_e, Z,   0, x2, r1, 0, cgxb, 0, IF_BFP)
 /* CONVERT FROM FIXED */
     F(0xb394, CEFBR,   RRF_e, Z,   0, r2_32s, new, e1, cegb, 0, IF_BFP)
     F(0xb395, CDFBR,   RRF_e, Z,   0, r2_32s, new, f1, cdgb, 0, IF_BFP)
@@ -313,10 +313,10 @@
 /* CONVERT TO LOGICAL */
     F(0xb39c, CLFEBR,  RRF_e, FPE, 0, e2, new, r1_32, clfeb, 0, IF_BFP)
     F(0xb39d, CLFDBR,  RRF_e, FPE, 0, f2, new, r1_32, clfdb, 0, IF_BFP)
-    F(0xb39e, CLFXBR,  RRF_e, FPE, x2h, x2l, new, r1_32, clfxb, 0, IF_BFP)
+    F(0xb39e, CLFXBR,  RRF_e, FPE, 0, x2, new, r1_32, clfxb, 0, IF_BFP)
     F(0xb3ac, CLGEBR,  RRF_e, FPE, 0, e2, r1, 0, clgeb, 0, IF_BFP)
     F(0xb3ad, CLGDBR,  RRF_e, FPE, 0, f2, r1, 0, clgdb, 0, IF_BFP)
-    F(0xb3ae, CLGXBR,  RRF_e, FPE, x2h, x2l, r1, 0, clgxb, 0, IF_BFP)
+    F(0xb3ae, CLGXBR,  RRF_e, FPE, 0, x2, r1, 0, clgxb, 0, IF_BFP)
 /* CONVERT FROM LOGICAL */
     F(0xb390, CELFBR,  RRF_e, FPE, 0, r2_32u, new, e1, celgb, 0, IF_BFP)
     F(0xb391, CDLFBR,  RRF_e, FPE, 0, r2_32u, new, f1, cdlgb, 0, IF_BFP)
@@ -343,7 +343,7 @@
     C(0x5d00, D,       RX_a,  Z,   r1_D32, m2_32s, new_P, r1_P32, divs32, 0)
     F(0xb30d, DEBR,    RRE,   Z,   e1, e2, new, e1, deb, 0, IF_BFP)
     F(0xb31d, DDBR,    RRE,   Z,   f1, f2, new, f1, ddb, 0, IF_BFP)
-    F(0xb34d, DXBR,    RRE,   Z,   x2h, x2l, x1, x1, dxb, 0, IF_BFP)
+    F(0xb34d, DXBR,    RRE,   Z,   x1, x2, new_x, x1, dxb, 0, IF_BFP)
     F(0xed0d, DEB,     RXE,   Z,   e1, m2_32u, new, e1, deb, 0, IF_BFP)
     F(0xed1d, DDB,     RXE,   Z,   f1, m2_64, new, f1, ddb, 0, IF_BFP)
 /* DIVIDE LOGICAL */
@@ -597,7 +597,7 @@
 /* LOAD FP INTEGER */
     F(0xb357, FIEBR,   RRF_e, Z,   0, e2, new, e1, fieb, 0, IF_BFP)
     F(0xb35f, FIDBR,   RRF_e, Z,   0, f2, new, f1, fidb, 0, IF_BFP)
-    F(0xb347, FIXBR,   RRF_e, Z,   x2h, x2l, new_x, x1, fixb, 0, IF_BFP)
+    F(0xb347, FIXBR,   RRF_e, Z,   0, x2, new_x, x1, fixb, 0, IF_BFP)
 
 /* LOAD LENGTHENED */
     F(0xb304, LDEBR,   RRE,   Z,   0, e2, new, f1, ldeb, 0, IF_BFP)
@@ -610,8 +610,8 @@
     F(0xed24, LDE,     RXE,   Z,   0, m2_32u, new, f1, lde, 0, IF_AFP1)
 /* LOAD ROUNDED */
     F(0xb344, LEDBR,   RRF_e, Z,   0, f2, new, e1, ledb, 0, IF_BFP)
-    F(0xb345, LDXBR,   RRF_e, Z,   x2h, x2l, new, f1, ldxb, 0, IF_BFP)
-    F(0xb346, LEXBR,   RRF_e, Z,   x2h, x2l, new, e1, lexb, 0, IF_BFP)
+    F(0xb345, LDXBR,   RRF_e, Z,   0, x2, new, f1, ldxb, 0, IF_BFP)
+    F(0xb346, LEXBR,   RRF_e, Z,   0, x2, new, e1, lexb, 0, IF_BFP)
 
 /* LOAD MULTIPLE */
     C(0x9800, LM,      RS_a,  Z,   0, a2, 0, 0, lm32, 0)
@@ -666,7 +666,7 @@
     C(0xe384, MG,      RXY_a, MIE2,r1p1_o, m2_64, r1_P, 0, muls128, 0)
     F(0xb317, MEEBR,   RRE,   Z,   e1, e2, new, e1, meeb, 0, IF_BFP)
     F(0xb31c, MDBR,    RRE,   Z,   f1, f2, new, f1, mdb, 0, IF_BFP)
-    F(0xb34c, MXBR,    RRE,   Z,   x2h, x2l, x1, x1, mxb, 0, IF_BFP)
+    F(0xb34c, MXBR,    RRE,   Z,   x1, x2, new_x, x1, mxb, 0, IF_BFP)
     F(0xb30c, MDEBR,   RRE,   Z,   f1, e2, new, f1, mdeb, 0, IF_BFP)
     F(0xb307, MXDBR,   RRE,   Z,   0, f2, x1, x1, mxdb, 0, IF_BFP)
     F(0xed17, MEEB,    RXE,   Z,   e1, m2_32u, new, e1, meeb, 0, IF_BFP)
@@ -835,7 +835,7 @@
 /* SQUARE ROOT */
     F(0xb314, SQEBR,   RRE,   Z,   0, e2, new, e1, sqeb, 0, IF_BFP)
     F(0xb315, SQDBR,   RRE,   Z,   0, f2, new, f1, sqdb, 0, IF_BFP)
-    F(0xb316, SQXBR,   RRE,   Z,   x2h, x2l, new_x, x1, sqxb, 0, IF_BFP)
+    F(0xb316, SQXBR,   RRE,   Z,   0, x2, new_x, x1, sqxb, 0, IF_BFP)
     F(0xed14, SQEB,    RXE,   Z,   0, m2_32u, new, e1, sqeb, 0, IF_BFP)
     F(0xed15, SQDB,    RXE,   Z,   0, m2_64, new, f1, sqdb, 0, IF_BFP)
 
@@ -913,7 +913,7 @@
     C(0xe319, SGF,     RXY_a, Z,   r1, m2_32s, r1, 0, sub, subs64)
     F(0xb30b, SEBR,    RRE,   Z,   e1, e2, new, e1, seb, f32, IF_BFP)
     F(0xb31b, SDBR,    RRE,   Z,   f1, f2, new, f1, sdb, f64, IF_BFP)
-    F(0xb34b, SXBR,    RRE,   Z,   x2h, x2l, x1, x1, sxb, f128, IF_BFP)
+    F(0xb34b, SXBR,    RRE,   Z,   x1, x2, new_x, x1, sxb, f128, IF_BFP)
     F(0xed0b, SEB,     RXE,   Z,   e1, m2_32u, new, e1, seb, f32, IF_BFP)
     F(0xed1b, SDB,     RXE,   Z,   f1, m2_64, new, f1, sdb, f64, IF_BFP)
 /* SUBTRACT HALFWORD */
@@ -957,7 +957,7 @@
 /* TEST DATA CLASS */
     F(0xed10, TCEB,    RXE,   Z,   e1, a2, 0, 0, tceb, 0, IF_BFP)
     F(0xed11, TCDB,    RXE,   Z,   f1, a2, 0, 0, tcdb, 0, IF_BFP)
-    F(0xed12, TCXB,    RXE,   Z,   0, a2, x1, 0, tcxb, 0, IF_BFP)
+    F(0xed12, TCXB,    RXE,   Z,   x1, a2, 0, 0, tcxb, 0, IF_BFP)
 
 /* TEST DECIMAL */
     C(0xebc0, TP,      RSL,   E2,  la1, 0, 0, 0, tp, 0)
Signature · 1 line
2.34.1
Acked-by on v2 11/13
#14 lore raw

Re: [PATCH for-8.0 v2 11/13] target/s390x: Use Int128 for passing float128

Quoted 9 lines · Richard Henderson

---
v2: Fix SPEC_in1_x1.

---
 target/s390x/helper.h            | 32 ++++++------
 target/s390x/tcg/fpu_helper.c    | 88 ++++++++++++++------------------
 target/s390x/tcg/translate.c     | 76 ++++++++++++++++++---------
 target/s390x/tcg/insn-data.h.inc | 30 +++++------
 4 files changed, 121 insertions(+), 105 deletions(-)
#15 lore raw

PATCH v2 12/13 target/s390x: Use tcg_gen_atomic_cmpxchg_i128 for CDSG

In reply to Richard Henderson
---
 target/s390x/helper.h            |  2 --
 target/s390x/tcg/mem_helper.c    | 52 ---------------------------
 target/s390x/tcg/translate.c     | 60 ++++++++++++++++++++------------
 target/s390x/tcg/insn-data.h.inc |  2 +-
 4 files changed, 38 insertions(+), 78 deletions(-)
target/s390x/helper.h +0 -2
index 481b9019f9..e5001ffddc 100644
@@ -35,8 +35,6 @@ DEF_HELPER_3(cxgb, i128, env, s64, i32)
 DEF_HELPER_3(celgb, i64, env, i64, i32)
 DEF_HELPER_3(cdlgb, i64, env, i64, i32)
 DEF_HELPER_3(cxlgb, i128, env, i64, i32)
-DEF_HELPER_4(cdsg, void, env, i64, i32, i32)
-DEF_HELPER_4(cdsg_parallel, void, env, i64, i32, i32)
 DEF_HELPER_4(csst, i32, env, i32, i64, i64)
 DEF_HELPER_4(csst_parallel, i32, env, i32, i64, i64)
 DEF_HELPER_FLAGS_3(aeb, TCG_CALL_NO_WG, i64, env, i64, i64)
target/s390x/tcg/mem_helper.c +0 -52

58 lines not on this page · raw message

target/s390x/tcg/translate.c +37 -23

86 lines not on this page · raw message

target/s390x/tcg/insn-data.h.inc +1 -1
index 1a2a55bf5e..7dfcbdd980 100644
@@ -276,7 +276,7 @@
 /* COMPARE DOUBLE AND SWAP */
     D(0xbb00, CDS,     RS_a,  Z,   r3_D32, r1_D32, new, r1_D32, cs, 0, MO_TEUQ)
     D(0xeb31, CDSY,    RSY_a, LD,  r3_D32, r1_D32, new, r1_D32, cs, 0, MO_TEUQ)
-    C(0xeb3e, CDSG,    RSY_a, Z,   0, 0, 0, 0, cdsg, 0)
+    C(0xeb3e, CDSG,    RSY_a, Z,   la2, r3_D64, r1_D64, r1_D64, cdsg, 0)
 /* COMPARE AND SWAP AND STORE */
     C(0xc802, CSST,    SSF,   CASS, la1, a2, 0, 0, csst, 0)
 
Signature · 1 line
2.34.1
Acked-by on v2 12/13
#16 lore raw

Re: [PATCH for-8.0 v2 12/13] target/s390x: Use tcg_gen_atomic_cmpxchg_i128 for CDSG

Quoted 7 lines · Richard Henderson
---
 target/s390x/helper.h            |  2 --
 target/s390x/tcg/mem_helper.c    | 52 ---------------------------
 target/s390x/tcg/translate.c     | 60 ++++++++++++++++++++------------
 target/s390x/tcg/insn-data.h.inc |  2 +-
 4 files changed, 38 insertions(+), 78 deletions(-)

I was wondering what assembly this would generate in parallel mode and wrote a small test. On my x86_64 machine it ended up being helper_atomic_cmpxchgo_be() -> cpu_atomic_cmpxchgo_be_mmu() -> lock cmpxchg16b, nothing surprising.

On an s390x host we fall back to cpu_exec_step_atomic(), because in the configure test:

      int main(void)
      {
        unsigned __int128 x = 0, y = 0;
        __sync_val_compare_and_swap_16(&x, y, x);
        return 0;
      }

x and y are not aligned. I guess that's working as intended as well, even though it would be nice to eventually make use of cdsg there.

I will post the test shortly.

#17 lore raw

PATCH 1/1 tests/tcg/s390x: Add cdsg.c

Add a simple test to prevent regressions.

---
 tests/tcg/s390x/Makefile.target |  4 ++
 tests/tcg/s390x/cdsg.c          | 73 +++++++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+)
 create mode 100644 tests/tcg/s390x/cdsg.c
tests/tcg/s390x/Makefile.target +4 -0
index 1d454270c0e..523214dac33 100644
@@ -27,6 +27,7 @@ TESTS+=noexec
 TESTS+=div
 TESTS+=clst
 TESTS+=long-double
+TESTS+=cdsg
 
 Z13_TESTS=vistr
 $(Z13_TESTS): CFLAGS+=-march=z13 -O2
@@ -66,3 +67,6 @@ sha512-mvx: sha512.c
 	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
 
 TESTS+=sha512-mvx
+
+cdsg: CFLAGS+=-pthread
+cdsg: LDFLAGS+=-pthread
tests/tcg/s390x/cdsg.c new file +73 -0

73 lines not on this page · raw message

Signature · 1 line
2.38.1
#18 lore raw

Re: [PATCH] tests/tcg/s390x: Add cdsg.c

Quoted 48 lines · Ilya Leoshkevich

Add a simple test to prevent regressions.

---
  tests/tcg/s390x/Makefile.target |  4 ++
  tests/tcg/s390x/cdsg.c          | 73 +++++++++++++++++++++++++++++++++
  2 files changed, 77 insertions(+)

create mode 100644 tests/tcg/s390x/cdsg.c

tests/tcg/s390x/Makefile.target +4 -0
index 1d454270c0e..523214dac33 100644
@@ -27,6 +27,7 @@ TESTS+=noexec
  TESTS+=div
  TESTS+=clst
  TESTS+=long-double
+TESTS+=cdsg
 
  Z13_TESTS=vistr
  $(Z13_TESTS): CFLAGS+=-march=z13 -O2
@@ -66,3 +67,6 @@ sha512-mvx: sha512.c
  	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
 
  TESTS+=sha512-mvx
+
+cdsg: CFLAGS+=-pthread
+cdsg: LDFLAGS+=-pthread
tests/tcg/s390x/cdsg.c new file +14 -0
new file mode 100644
index 00000000000..83313699f7d
@@ -0,0 +1,73 @@
+#include <assert.h>
+#include <pthread.h>
+#include <stdbool.h>
+#include <stdlib.h>
+
+static volatile bool start;
+static unsigned long val[2] __attribute__((__aligned__(16)));
+
+void *cdsg_loop(void *arg)
+{
+    unsigned long orig0, orig1, new0, new1;
+    register unsigned long r0 asm("r0");
+    register unsigned long r1 asm("r1");
+    register unsigned long r2 asm("r2");

tests/tcg/s390x/cdsg.c line 24

Quoted 10 lines
tests/tcg/s390x/cdsg.c new file +10 -0
+    register unsigned long r3 asm("r3");
+    int cc;
+    int i;
+
+    while (!start) {
+    }
+
+    orig0 = val[0];
+    orig1 = val[1];
+    for (i = 0; i < 1000;) {

Are 1000 iterations sufficient to catch the race window reliably?

Quoted 6 lines
tests/tcg/s390x/cdsg.c new file +6 -0
+        new0 = orig0 + 1;
+        new1 = orig1 + 2;
+
+        r0 = orig0;
+        r1 = orig1;
+        r2 = new0;

tests/tcg/s390x/cdsg.c line 40

Quoted 10 lines
tests/tcg/s390x/cdsg.c new file +10 -0
+        r3 = new1;
+        asm("cdsg %[r0],%[r2],%[db2]\n"
+            "ipm %[cc]"
+            : [r0] "+r" (r0)
+            , [r1] "+r" (r1)
+            , [db2] "=m" (val)
+            , [cc] "=r" (cc)
+            : [r2] "r" (r2)
+            , [r3] "r" (r3)
+            : "cc");

Nit: I'd suggest a simple cdsg helper function that makes this code easier to digest.

Quoted 33 lines
tests/tcg/s390x/cdsg.c new file +33 -0
+        orig0 = r0;
+        orig1 = r1;
+        cc = (cc >> 28) & 3;
+
+        if (cc == 0) {
+            orig0 = new0;
+            orig1 = new1;
+            i++;
+        } else {
+            assert(cc == 1);
+        }
+    }
+
+    return NULL;
+}
+
+int main(void)
+{
+    pthread_t thread;
+    int ret;
+
+    ret = pthread_create(&thread, NULL, cdsg_loop, NULL);
+    assert(ret == 0);
+    start = true;
+    cdsg_loop(NULL);
+    ret = pthread_join(thread, NULL);
+    assert(ret == 0);
+
+    assert(val[0] == 2000);
+    assert(val[1] == 4000);
+
+    return EXIT_SUCCESS;
+}
Signature · 3 lines
Thanks,

David / dhildenb
#19 lore raw

Re: [PATCH] tests/tcg/s390x: Add cdsg.c

Quoted 51 lines · David Hildenbrand
Quoted 50 lines · Ilya Leoshkevich

Add a simple test to prevent regressions.

---
  tests/tcg/s390x/Makefile.target |  4 ++
  tests/tcg/s390x/cdsg.c          | 73 +++++++++++++++++++++++++++++++++
  2 files changed, 77 insertions(+)

create mode 100644 tests/tcg/s390x/cdsg.c

tests/tcg/s390x/Makefile.target +4 -0
index 1d454270c0e..523214dac33 100644
@@ -27,6 +27,7 @@ TESTS+=noexec
  TESTS+=div
  TESTS+=clst
  TESTS+=long-double
+TESTS+=cdsg
  Z13_TESTS=vistr
  $(Z13_TESTS): CFLAGS+=-march=z13 -O2
@@ -66,3 +67,6 @@ sha512-mvx: sha512.c
  	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
  TESTS+=sha512-mvx
+
+cdsg: CFLAGS+=-pthread
+cdsg: LDFLAGS+=-pthread
tests/tcg/s390x/cdsg.c new file +18 -0
new file mode 100644
index 00000000000..83313699f7d
@@ -0,0 +1,73 @@
+#include <assert.h>
+#include <pthread.h>
+#include <stdbool.h>
+#include <stdlib.h>
+
+static volatile bool start;
+static unsigned long val[2] __attribute__((__aligned__(16)));
+
+void *cdsg_loop(void *arg)
+{
+    unsigned long orig0, orig1, new0, new1;
+    register unsigned long r0 asm("r0");
+    register unsigned long r1 asm("r1");
+    register unsigned long r2 asm("r2");
+    register unsigned long r3 asm("r3");
+    int cc;
+    int i;
+
Quoted 8 lines

tests/tcg/s390x/cdsg.c line 24

Quoted 6 lines
tests/tcg/s390x/cdsg.c new file +6 -0
+    while (!start) {
+    }
+
+    orig0 = val[0];
+    orig1 = val[1];
+    for (i = 0; i < 1000;) {

Are 1000 iterations sufficient to catch the race window reliably?

Good point, I had to raise it to 10k.
If I break the code like this:

tcg/tcg-op.c +1 -1
@@ -3509,7 +3509,7 @@ void tcg_gen_atomic_cmpxchg_i128(TCGv_i128 retv, TCGv addr, TCGv_i128 cmpv,
 {
     gen_atomic_cx_i128 gen;
 
-    if (!(tcg_ctx->tb_cflags & CF_PARALLEL)) {
+    if (true) {
         tcg_gen_nonatomic_cmpxchg_i128(retv, addr, cmpv, newv, idx, memop);
         return;
     }

the test with 10k iterations fails consistently.
And it's still fast:

$ time -p ./qemu-s390x ./tests/tcg/s390x-linux-user/cdsg
real 0.01
Quoted 17 lines
Quoted 6 lines
tests/tcg/s390x/cdsg.c new file +6 -0
+        new0 = orig0 + 1;
+        new1 = orig1 + 2;
+
+        r0 = orig0;
+        r1 = orig1;
+        r2 = new0;

tests/tcg/s390x/cdsg.c line 40

Quoted 10 lines
tests/tcg/s390x/cdsg.c new file +10 -0
+        r3 = new1;
+        asm("cdsg %[r0],%[r2],%[db2]\n"
+            "ipm %[cc]"
+            : [r0] "+r" (r0)
+            , [r1] "+r" (r1)
+            , [db2] "=m" (val)
+            , [cc] "=r" (cc)
+            : [r2] "r" (r2)
+            , [r3] "r" (r3)
+            : "cc");
Quoted 2 lines

Nit: I'd suggest a simple cdsg helper function that makes this code easier to digest.

Ok.

Quoted 41 lines
Quoted 34 lines
tests/tcg/s390x/cdsg.c new file +33 -0
+        orig0 = r0;
+        orig1 = r1;
+        cc = (cc >> 28) & 3;
+
+        if (cc == 0) {
+            orig0 = new0;
+            orig1 = new1;
+            i++;
+        } else {
+            assert(cc == 1);
+        }
+    }
+
+    return NULL;
+}
+
+int main(void)
+{
+    pthread_t thread;
+    int ret;
+
+    ret = pthread_create(&thread, NULL, cdsg_loop, NULL);
+    assert(ret == 0);
+    start = true;
+    cdsg_loop(NULL);
+    ret = pthread_join(thread, NULL);
+    assert(ret == 0);
+
+    assert(val[0] == 2000);
+    assert(val[1] == 4000);
+
+    return EXIT_SUCCESS;
+}
Signature · 3 lines
Thanks,

David / dhildenb
#20 lore raw

PATCH v2 1/1 tests/tcg/s390x: Add cdsg.c

In reply to David Hildenbrand

Add a simple test to prevent regressions.

---
 tests/tcg/s390x/Makefile.target |  4 ++
 tests/tcg/s390x/cdsg.c          | 84 +++++++++++++++++++++++++++++++++
 2 files changed, 88 insertions(+)
 create mode 100644 tests/tcg/s390x/cdsg.c
tests/tcg/s390x/Makefile.target +4 -0
index 1d454270c0e..523214dac33 100644
@@ -27,6 +27,7 @@ TESTS+=noexec
 TESTS+=div
 TESTS+=clst
 TESTS+=long-double
+TESTS+=cdsg
 
 Z13_TESTS=vistr
 $(Z13_TESTS): CFLAGS+=-march=z13 -O2
@@ -66,3 +67,6 @@ sha512-mvx: sha512.c
 	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
 
 TESTS+=sha512-mvx
+
+cdsg: CFLAGS+=-pthread
+cdsg: LDFLAGS+=-pthread
tests/tcg/s390x/cdsg.c new file +84 -0

84 lines not on this page · raw message

Signature · 1 line
2.38.1
#21 lore raw

PATCH v3 1/1 tests/tcg/s390x: Add cdsg.c

Add a simple test to prevent regressions.

---

Sorry, I just realized that in v2 that I sent the iteration count was not increased. For v3 I've decided to bump it further to 1m, since it's still fast enough:

$ time -p ./qemu-s390x ./tests/tcg/s390x-linux-user/cdsg
real 0.15

v2 -> v3: Increase iteration count to 1m.
v1 -> v2: Add cdsg() wrapper.

 tests/tcg/s390x/Makefile.target |  4 ++
 tests/tcg/s390x/cdsg.c          | 85 +++++++++++++++++++++++++++++++++
 2 files changed, 89 insertions(+)
 create mode 100644 tests/tcg/s390x/cdsg.c
tests/tcg/s390x/Makefile.target +4 -0
index 1d454270c0e..523214dac33 100644
@@ -27,6 +27,7 @@ TESTS+=noexec
 TESTS+=div
 TESTS+=clst
 TESTS+=long-double
+TESTS+=cdsg
 
 Z13_TESTS=vistr
 $(Z13_TESTS): CFLAGS+=-march=z13 -O2
@@ -66,3 +67,6 @@ sha512-mvx: sha512.c
 	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
 
 TESTS+=sha512-mvx
+
+cdsg: CFLAGS+=-pthread
+cdsg: LDFLAGS+=-pthread
tests/tcg/s390x/cdsg.c new file +85 -0

85 lines not on this page · raw message

Signature · 1 line
2.38.1
#22 lore raw

Re: [PATCH for-8.0 v2 12/13] target/s390x: Use tcg_gen_atomic_cmpxchg_i128 for CDSG

In reply to Ilya Leoshkevich
Quoted 10 lines · Ilya Leoshkevich

On an s390x host we fall back to cpu_exec_step_atomic(), because in the configure test:

       int main(void)
       {
         unsigned __int128 x = 0, y = 0;
         __sync_val_compare_and_swap_16(&x, y, x);
         return 0;
       }
Quoted 2 lines

x and y are not aligned. I guess that's working as intended as well, even though it would be nice to eventually make use of cdsg there.

I have a fix for that as a part of '[PATCH for-8.0 00/29] tcg: Improve atomicity support':
https://lore.kernel.org/qemu-devel/[email protected]/

r~

#23 lore raw

PATCH v2 13/13 target/s390x: Implement CC_OP_NZ in gen_op_calc_cc

In reply to Richard Henderson

This case is trivial to implement inline.

---
 target/s390x/tcg/translate.c | 3 +++
 1 file changed, 3 insertions(+)
target/s390x/tcg/translate.c +3 -0
index 480c89dae3..f8a6f29d9c 100644
@@ -625,6 +625,9 @@ static void gen_op_calc_cc(DisasContext *s)
         /* env->cc_op already is the cc value */
         break;
     case CC_OP_NZ:
+        tcg_gen_setcondi_i64(TCG_COND_NE, cc_dst, cc_dst, 0);
+        tcg_gen_extrl_i64_i32(cc_op, cc_dst);
+        break;
     case CC_OP_ABS_64:
     case CC_OP_NABS_64:
     case CC_OP_ABS_32:
Signature · 1 line
2.34.1