From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: richard.henderson@linaro.org, paul@nowt.org
Subject: [PATCH 16/23] i386: Floating point arithmetic helper AVX prep
Date: Sat, 27 Aug 2022 01:11:57 +0200 [thread overview]
Message-ID: <20220826231204.201395-17-pbonzini@redhat.com> (raw)
In-Reply-To: <20220826231204.201395-1-pbonzini@redhat.com>
From: Paul Brook <paul@nowt.org>
Prepare the "easy" floating point vector helpers for AVX
No functional changes to existing helpers.
Signed-off-by: Paul Brook <paul@nowt.org>
Message-Id: <20220424220204.2493824-16-paul@nowt.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
target/i386/ops_sse.h | 138 ++++++++++++++++++++++++++++--------------
1 file changed, 92 insertions(+), 46 deletions(-)
diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 09dabfcbd5..1d05e42a45 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -548,40 +548,58 @@ void glue(helper_pshufhw, SUFFIX)(Reg *d, Reg *s, int order)
}
#endif
-#if SHIFT == 1
+#if SHIFT >= 1
/* FPU ops */
/* XXX: not accurate */
-#define SSE_HELPER_S(name, F) \
- void glue(helper_ ## name ## ps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)\
+#define SSE_HELPER_P(name, F) \
+ void glue(helper_ ## name ## ps, SUFFIX)(CPUX86State *env, \
+ Reg *d, Reg *s) \
{ \
- d->ZMM_S(0) = F(32, d->ZMM_S(0), s->ZMM_S(0)); \
- d->ZMM_S(1) = F(32, d->ZMM_S(1), s->ZMM_S(1)); \
- d->ZMM_S(2) = F(32, d->ZMM_S(2), s->ZMM_S(2)); \
- d->ZMM_S(3) = F(32, d->ZMM_S(3), s->ZMM_S(3)); \
+ Reg *v = d; \
+ int i; \
+ for (i = 0; i < 2 << SHIFT; i++) { \
+ d->ZMM_S(i) = F(32, v->ZMM_S(i), s->ZMM_S(i)); \
+ } \
} \
\
- void helper_ ## name ## ss(CPUX86State *env, Reg *d, Reg *s) \
+ void glue(helper_ ## name ## pd, SUFFIX)(CPUX86State *env, \
+ Reg *d, Reg *s) \
{ \
- d->ZMM_S(0) = F(32, d->ZMM_S(0), s->ZMM_S(0)); \
- } \
- \
- void glue(helper_ ## name ## pd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)\
- { \
- d->ZMM_D(0) = F(64, d->ZMM_D(0), s->ZMM_D(0)); \
- d->ZMM_D(1) = F(64, d->ZMM_D(1), s->ZMM_D(1)); \
- } \
- \
- void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s) \
- { \
- d->ZMM_D(0) = F(64, d->ZMM_D(0), s->ZMM_D(0)); \
+ Reg *v = d; \
+ int i; \
+ for (i = 0; i < 1 << SHIFT; i++) { \
+ d->ZMM_D(i) = F(64, v->ZMM_D(i), s->ZMM_D(i)); \
+ } \
}
+#if SHIFT == 1
+
+#define SSE_HELPER_S(name, F) \
+ SSE_HELPER_P(name, F) \
+ \
+ void helper_ ## name ## ss(CPUX86State *env, Reg *d, Reg *s)\
+ { \
+ Reg *v = d; \
+ d->ZMM_S(0) = F(32, v->ZMM_S(0), s->ZMM_S(0)); \
+ } \
+ \
+ void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s)\
+ { \
+ Reg *v = d; \
+ d->ZMM_D(0) = F(64, v->ZMM_D(0), s->ZMM_D(0)); \
+ }
+
+#else
+
+#define SSE_HELPER_S(name, F) SSE_HELPER_P(name, F)
+
+#endif
+
#define FPU_ADD(size, a, b) float ## size ## _add(a, b, &env->sse_status)
#define FPU_SUB(size, a, b) float ## size ## _sub(a, b, &env->sse_status)
#define FPU_MUL(size, a, b) float ## size ## _mul(a, b, &env->sse_status)
#define FPU_DIV(size, a, b) float ## size ## _div(a, b, &env->sse_status)
-#define FPU_SQRT(size, a, b) float ## size ## _sqrt(b, &env->sse_status)
/* Note that the choice of comparison op here is important to get the
* special cases right: for min and max Intel specifies that (-0,0),
@@ -598,8 +616,34 @@ SSE_HELPER_S(mul, FPU_MUL)
SSE_HELPER_S(div, FPU_DIV)
SSE_HELPER_S(min, FPU_MIN)
SSE_HELPER_S(max, FPU_MAX)
-SSE_HELPER_S(sqrt, FPU_SQRT)
+void glue(helper_sqrtps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+ int i;
+ for (i = 0; i < 2 << SHIFT; i++) {
+ d->ZMM_S(i) = float32_sqrt(s->ZMM_S(i), &env->sse_status);
+ }
+}
+
+void glue(helper_sqrtpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+ int i;
+ for (i = 0; i < 1 << SHIFT; i++) {
+ d->ZMM_D(i) = float64_sqrt(s->ZMM_D(i), &env->sse_status);
+ }
+}
+
+#if SHIFT == 1
+void helper_sqrtss(CPUX86State *env, Reg *d, Reg *s)
+{
+ d->ZMM_S(0) = float32_sqrt(s->ZMM_S(0), &env->sse_status);
+}
+
+void helper_sqrtsd(CPUX86State *env, Reg *d, Reg *s)
+{
+ d->ZMM_D(0) = float64_sqrt(s->ZMM_D(0), &env->sse_status);
+}
+#endif
/* float to float conversions */
void glue(helper_cvtps2pd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
@@ -817,18 +861,12 @@ int64_t helper_cvttsd2sq(CPUX86State *env, ZMMReg *s)
void glue(helper_rsqrtps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
{
uint8_t old_flags = get_float_exception_flags(&env->sse_status);
- d->ZMM_S(0) = float32_div(float32_one,
- float32_sqrt(s->ZMM_S(0), &env->sse_status),
- &env->sse_status);
- d->ZMM_S(1) = float32_div(float32_one,
- float32_sqrt(s->ZMM_S(1), &env->sse_status),
- &env->sse_status);
- d->ZMM_S(2) = float32_div(float32_one,
- float32_sqrt(s->ZMM_S(2), &env->sse_status),
- &env->sse_status);
- d->ZMM_S(3) = float32_div(float32_one,
- float32_sqrt(s->ZMM_S(3), &env->sse_status),
- &env->sse_status);
+ int i;
+ for (i = 0; i < 2 << SHIFT; i++) {
+ d->ZMM_S(i) = float32_div(float32_one,
+ float32_sqrt(s->ZMM_S(i), &env->sse_status),
+ &env->sse_status);
+ }
set_float_exception_flags(old_flags, &env->sse_status);
}
@@ -844,10 +882,10 @@ void helper_rsqrtss(CPUX86State *env, ZMMReg *d, ZMMReg *s)
void glue(helper_rcpps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
{
uint8_t old_flags = get_float_exception_flags(&env->sse_status);
- d->ZMM_S(0) = float32_div(float32_one, s->ZMM_S(0), &env->sse_status);
- d->ZMM_S(1) = float32_div(float32_one, s->ZMM_S(1), &env->sse_status);
- d->ZMM_S(2) = float32_div(float32_one, s->ZMM_S(2), &env->sse_status);
- d->ZMM_S(3) = float32_div(float32_one, s->ZMM_S(3), &env->sse_status);
+ int i;
+ for (i = 0; i < 2 << SHIFT; i++) {
+ d->ZMM_S(i) = float32_div(float32_one, s->ZMM_S(i), &env->sse_status);
+ }
set_float_exception_flags(old_flags, &env->sse_status);
}
@@ -942,18 +980,24 @@ void glue(helper_hsubpd, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
MOVE(*d, r);
}
-void glue(helper_addsubps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
+void glue(helper_addsubps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
- d->ZMM_S(0) = float32_sub(d->ZMM_S(0), s->ZMM_S(0), &env->sse_status);
- d->ZMM_S(1) = float32_add(d->ZMM_S(1), s->ZMM_S(1), &env->sse_status);
- d->ZMM_S(2) = float32_sub(d->ZMM_S(2), s->ZMM_S(2), &env->sse_status);
- d->ZMM_S(3) = float32_add(d->ZMM_S(3), s->ZMM_S(3), &env->sse_status);
+ Reg *v = d;
+ int i;
+ for (i = 0; i < 2 << SHIFT; i += 2) {
+ d->ZMM_S(i) = float32_sub(v->ZMM_S(i), s->ZMM_S(i), &env->sse_status);
+ d->ZMM_S(i+1) = float32_add(v->ZMM_S(i+1), s->ZMM_S(i+1), &env->sse_status);
+ }
}
-void glue(helper_addsubpd, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
+void glue(helper_addsubpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
- d->ZMM_D(0) = float64_sub(d->ZMM_D(0), s->ZMM_D(0), &env->sse_status);
- d->ZMM_D(1) = float64_add(d->ZMM_D(1), s->ZMM_D(1), &env->sse_status);
+ Reg *v = d;
+ int i;
+ for (i = 0; i < 1 << SHIFT; i += 2) {
+ d->ZMM_D(i) = float64_sub(v->ZMM_D(i), s->ZMM_D(i), &env->sse_status);
+ d->ZMM_D(i+1) = float64_add(v->ZMM_D(i+1), s->ZMM_D(i+1), &env->sse_status);
+ }
}
/* XXX: unordered */
@@ -2280,6 +2324,8 @@ void glue(helper_aeskeygenassist, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
}
#endif
+#undef SSE_HELPER_S
+
#undef SHIFT
#undef XMM_ONLY
#undef Reg
--
2.37.1
next prev parent reply other threads:[~2022-08-26 23:30 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-26 23:11 [PATCH v2 00/23] target/i386: make most SSE helpers generic in the vector size Paolo Bonzini
2022-08-26 23:11 ` [PATCH 01/23] i386: do not use MOVL to move data between SSE registers Paolo Bonzini
2022-08-26 23:17 ` Richard Henderson
2022-08-26 23:11 ` [PATCH 02/23] i386: formatting fixes Paolo Bonzini
2022-08-26 23:17 ` Richard Henderson
2022-08-26 23:11 ` [PATCH 03/23] i386: Add ZMM_OFFSET macro Paolo Bonzini
2022-08-26 23:11 ` [PATCH 04/23] i386: Rework sse_op_table1 Paolo Bonzini
2022-08-26 23:11 ` [PATCH 05/23] i386: Rework sse_op_table6/7 Paolo Bonzini
2022-08-26 23:11 ` [PATCH 06/23] i386: Move 3DNOW decoder Paolo Bonzini
2022-08-26 23:11 ` [PATCH 07/23] i386: check SSE table flags instead of hardcoding opcodes Paolo Bonzini
2022-08-26 23:23 ` Richard Henderson
2022-08-26 23:11 ` [PATCH 08/23] i386: isolate MMX code more Paolo Bonzini
2022-08-26 23:28 ` Richard Henderson
2022-08-26 23:11 ` [PATCH 09/23] i386: Add size suffix to vector FP helpers Paolo Bonzini
2022-08-26 23:11 ` [PATCH 10/23] i386: do not cast gen_helper_* function pointers Paolo Bonzini
2022-08-26 23:32 ` Richard Henderson
2022-08-26 23:11 ` [PATCH 11/23] i386: Add CHECK_NO_VEX Paolo Bonzini
2022-08-26 23:11 ` [PATCH 12/23] i386: Rewrite vector shift helper Paolo Bonzini
2022-08-26 23:11 ` [PATCH 13/23] i386: Rewrite simple integer vector helpers Paolo Bonzini
2022-08-26 23:11 ` [PATCH 14/23] i386: Misc integer AVX helper prep Paolo Bonzini
2022-08-26 23:11 ` [PATCH 15/23] i386: Destructive vector helpers for AVX Paolo Bonzini
2022-08-26 23:45 ` Richard Henderson
2022-08-27 6:22 ` Paolo Bonzini
2022-08-26 23:11 ` Paolo Bonzini [this message]
2022-08-26 23:11 ` [PATCH 17/23] i386: reimplement AVX comparison helpers Paolo Bonzini
2022-08-26 23:11 ` [PATCH 18/23] i386: Dot product AVX helper prep Paolo Bonzini
2022-08-26 23:12 ` [PATCH 19/23] i386: Destructive FP helpers for AVX Paolo Bonzini
2022-08-26 23:12 ` [PATCH 20/23] i386: Misc AVX helper prep Paolo Bonzini
2022-08-26 23:12 ` [PATCH 21/23] i386: Rewrite blendv helpers Paolo Bonzini
2022-08-26 23:12 ` [PATCH 22/23] i386: AVX pclmulqdq prep Paolo Bonzini
2022-08-26 23:12 ` [PATCH 23/23] i386: AVX+AES helpers prep Paolo Bonzini
2022-08-26 23:50 ` Richard Henderson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220826231204.201395-17-pbonzini@redhat.com \
--to=pbonzini@redhat.com \
--cc=paul@nowt.org \
--cc=qemu-devel@nongnu.org \
--cc=richard.henderson@linaro.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).