[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PULL 22/37] s390x/tcg: Implement 32/128 bit for VECTOR FP MULTIPLY AND
From: |
Cornelia Huck |
Subject: |
[PULL 22/37] s390x/tcg: Implement 32/128 bit for VECTOR FP MULTIPLY AND (ADD|SUBTRACT) |
Date: |
Mon, 21 Jun 2021 11:58:27 +0200 |
From: David Hildenbrand <david@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210608092337.12221-22-david@redhat.com>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
---
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(-)
diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index bae73b9a5677..236675606313 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -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)
diff --git a/target/s390x/translate_vx.c.inc b/target/s390x/translate_vx.c.inc
index 765f75df9c6f..17d41b178fc4 100644
--- a/target/s390x/translate_vx.c.inc
+++ b/target/s390x/translate_vx.c.inc
@@ -2818,18 +2818,51 @@ static DisasJumpType op_vfma(DisasContext *s, DisasOps
*o)
{
const uint8_t m5 = get_field(s, m5);
const uint8_t fpf = get_field(s, m6);
- gen_helper_gvec_4_ptr *fn;
+ gen_helper_gvec_4_ptr *fn = NULL;
- if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
+ if (s->fields.op2 == 0x8f) {
+ switch (fpf) {
+ case FPF_SHORT:
+ if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+ fn = gen_helper_gvec_vfma32;
+ }
+ break;
+ case FPF_LONG:
+ fn = gen_helper_gvec_vfma64;
+ break;
+ case FPF_EXT:
+ if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+ fn = gen_helper_gvec_vfma128;
+ }
+ break;
+ default:
+ break;
+ }
+ } else {
+ switch (fpf) {
+ case FPF_SHORT:
+ if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+ fn = gen_helper_gvec_vfms32;
+ }
+ break;
+ case FPF_LONG:
+ fn = gen_helper_gvec_vfms64;
+ break;
+ case FPF_EXT:
+ if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+ fn = gen_helper_gvec_vfms128;
+ }
+ break;
+ default:
+ break;
+ }
+ }
+
+ if (!fn || extract32(m5, 0, 3)) {
gen_program_exception(s, PGM_SPECIFICATION);
return DISAS_NORETURN;
}
- if (s->fields.op2 == 0x8f) {
- fn = gen_helper_gvec_vfma64;
- } else {
- 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, m5, fn);
return DISAS_NEXT;
diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c
index 6984f770ff01..29ccc608dc45 100644
--- a/target/s390x/vec_fpu_helper.c
+++ b/target/s390x/vec_fpu_helper.c
@@ -582,6 +582,30 @@ void HELPER(gvec_vflr128)(void *v1, const void *v2,
CPUS390XState *env,
s390_vec_write_float64(v1, 0, ret);
}
+static void vfma32(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
+ const S390Vector *v4, CPUS390XState *env, bool s, int flags,
+ uintptr_t retaddr)
+{
+ uint8_t vxc, vec_exc = 0;
+ S390Vector tmp = {};
+ int i;
+
+ for (i = 0; i < 4; i++) {
+ const float32 a = s390_vec_read_float32(v2, i);
+ const float32 b = s390_vec_read_float32(v3, i);
+ const float32 c = s390_vec_read_float32(v4, i);
+ float32 ret = float32_muladd(a, b, c, flags, &env->fpu_status);
+
+ s390_vec_write_float32(&tmp, i, ret);
+ vxc = check_ieee_exc(env, i, false, &vec_exc);
+ if (s || vxc) {
+ break;
+ }
+ }
+ handle_ieee_exc(env, vxc, vec_exc, retaddr);
+ *v1 = tmp;
+}
+
static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
const S390Vector *v4, CPUS390XState *env, bool s, int flags,
uintptr_t retaddr)
@@ -606,6 +630,22 @@ static void vfma64(S390Vector *v1, const S390Vector *v2,
const S390Vector *v3,
*v1 = tmp;
}
+static void vfma128(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
+ const S390Vector *v4, CPUS390XState *env, bool s, int
flags,
+ uintptr_t retaddr)
+{
+ const float128 a = s390_vec_read_float128(v2);
+ const float128 b = s390_vec_read_float128(v3);
+ const float128 c = s390_vec_read_float128(v4);
+ uint8_t vxc, vec_exc = 0;
+ float128 ret;
+
+ ret = float128_muladd(a, b, c, flags, &env->fpu_status);
+ vxc = check_ieee_exc(env, 0, false, &vec_exc);
+ handle_ieee_exc(env, vxc, vec_exc, retaddr);
+ s390_vec_write_float128(v1, ret);
+}
+
#define DEF_GVEC_VFMA_B(NAME, FLAGS, BITS)
\
void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, const void *v3,
\
const void *v4, CPUS390XState *env,
\
@@ -617,7 +657,9 @@ void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2,
const void *v3, \
}
#define DEF_GVEC_VFMA(NAME, FLAGS)
\
- DEF_GVEC_VFMA_B(NAME, FLAGS, 64)
+ DEF_GVEC_VFMA_B(NAME, FLAGS, 32)
\
+ DEF_GVEC_VFMA_B(NAME, FLAGS, 64)
\
+ DEF_GVEC_VFMA_B(NAME, FLAGS, 128)
DEF_GVEC_VFMA(vfma, 0)
DEF_GVEC_VFMA(vfms, float_muladd_negate_c)
--
2.31.1
- [PULL 13/37] s390x/tcg: Implement VECTOR MULTIPLY SUM LOGICAL, (continued)
- [PULL 13/37] s390x/tcg: Implement VECTOR MULTIPLY SUM LOGICAL, Cornelia Huck, 2021/06/21
- [PULL 15/37] s390x/tcg: Implement 32/128 bit for VECTOR (LOAD FP INTEGER|FP SQUARE ROOT), Cornelia Huck, 2021/06/21
- [PULL 16/37] s390x/tcg: Implement 32/128 bit for VECTOR FP COMPARE *, Cornelia Huck, 2021/06/21
- [PULL 18/37] s390x/tcg: Implement 64 bit for VECTOR FP LOAD LENGTHENED, Cornelia Huck, 2021/06/21
- [PULL 17/37] s390x/tcg: Implement 32/128 bit for VECTOR FP COMPARE (AND SIGNAL) SCALAR, Cornelia Huck, 2021/06/21
- [PULL 19/37] s390x/tcg: Implement 128 bit for VECTOR FP LOAD ROUNDED, Cornelia Huck, 2021/06/21
- [PULL 21/37] s390x/tcg: Implement 32/128 bit for VECTOR FP TEST DATA CLASS IMMEDIATE, Cornelia Huck, 2021/06/21
- [PULL 20/37] s390x/tcg: Implement 32/128 bit for VECTOR FP PERFORM SIGN OPERATION, Cornelia Huck, 2021/06/21
- [PULL 23/37] s390x/tcg: Implement VECTOR FP NEGATIVE MULTIPLY AND (ADD|SUBTRACT), Cornelia Huck, 2021/06/21
- [PULL 24/37] s390x/tcg: Implement VECTOR FP (MAXIMUM|MINIMUM), Cornelia Huck, 2021/06/21
- [PULL 22/37] s390x/tcg: Implement 32/128 bit for VECTOR FP MULTIPLY AND (ADD|SUBTRACT),
Cornelia Huck <=
- [PULL 25/37] linux-user: elf: s390x: Prepare for Vector enhancements facility, Cornelia Huck, 2021/06/21
- [PULL 27/37] s390x/cpumodel: Bump up QEMU model to a stripped-down IBM z14 GA2, Cornelia Huck, 2021/06/21
- [PULL 26/37] s390x/tcg: We support Vector enhancements facility, Cornelia Huck, 2021/06/21
- [PULL 28/37] configure: Check whether we can compile the s390-ccw bios with -msoft-float, Cornelia Huck, 2021/06/21
- [PULL 29/37] target/s390x: Expose load_psw and get_psw_mask to cpu.h, Cornelia Huck, 2021/06/21
- [PULL 30/37] target/s390x: Do not modify cpu state in s390_cpu_get_psw_mask, Cornelia Huck, 2021/06/21
- [PULL 31/37] target/s390x: Improve s390_cpu_dump_state vs cc_op, Cornelia Huck, 2021/06/21
- [PULL 32/37] target/s390x: Use s390_cpu_{set_psw, get_psw_mask} in gdbstub, Cornelia Huck, 2021/06/21
- [PULL 35/37] s390x/css: Split out the IRB sense data, Cornelia Huck, 2021/06/21
- [PULL 33/37] linux-user/s390x: Save and restore psw.mask properly, Cornelia Huck, 2021/06/21