From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: paul@nowt.org, richard.henderson@linaro.org
Subject: [PATCH 12/18] i386: reimplement AVX comparison helpers
Date: Fri, 26 Aug 2022 00:14:05 +0200 [thread overview]
Message-ID: <20220825221411.35122-13-pbonzini@redhat.com> (raw)
In-Reply-To: <20220825221411.35122-1-pbonzini@redhat.com>
From: Paul Brook <paul@nowt.org>
AVX includes additional a more extensive set of comparison predicates,
some of some of which our softfloat implementation does not expose directly.
Rewrite the helpers in terms of floatN_compare for future extensibility.
Signed-off-by: Paul Brook <paul@nowt.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
target/i386/ops_sse.h | 97 ++++++++++++++++++++----------------
| 24 ++++-----
target/i386/tcg/translate.c | 20 ++++----
3 files changed, 75 insertions(+), 66 deletions(-)
diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 08359b8433..851a05d594 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -992,57 +992,66 @@ void glue(helper_addsubpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
}
}
-/* XXX: unordered */
-#define SSE_HELPER_CMP(name, F) \
- void glue(helper_ ## name ## ps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)\
+#define SSE_HELPER_CMP_P(name, F, C) \
+ void glue(helper_ ## name ## ps, SUFFIX)(CPUX86State *env, \
+ Reg *d, Reg *s) \
{ \
- d->ZMM_L(0) = F(32, d->ZMM_S(0), s->ZMM_S(0)); \
- d->ZMM_L(1) = F(32, d->ZMM_S(1), s->ZMM_S(1)); \
- d->ZMM_L(2) = F(32, d->ZMM_S(2), s->ZMM_S(2)); \
- d->ZMM_L(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_L(i) = F(32, C, 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_L(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_Q(0) = F(64, d->ZMM_D(0), s->ZMM_D(0)); \
- d->ZMM_Q(1) = F(64, d->ZMM_D(1), s->ZMM_D(1)); \
- } \
- \
- void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s) \
- { \
- d->ZMM_Q(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_Q(i) = F(64, C, v->ZMM_D(i), s->ZMM_D(i)); \
+ } \
}
-#define FPU_CMPEQ(size, a, b) \
- (float ## size ## _eq_quiet(a, b, &env->sse_status) ? -1 : 0)
-#define FPU_CMPLT(size, a, b) \
- (float ## size ## _lt(a, b, &env->sse_status) ? -1 : 0)
-#define FPU_CMPLE(size, a, b) \
- (float ## size ## _le(a, b, &env->sse_status) ? -1 : 0)
-#define FPU_CMPUNORD(size, a, b) \
- (float ## size ## _unordered_quiet(a, b, &env->sse_status) ? -1 : 0)
-#define FPU_CMPNEQ(size, a, b) \
- (float ## size ## _eq_quiet(a, b, &env->sse_status) ? 0 : -1)
-#define FPU_CMPNLT(size, a, b) \
- (float ## size ## _lt(a, b, &env->sse_status) ? 0 : -1)
-#define FPU_CMPNLE(size, a, b) \
- (float ## size ## _le(a, b, &env->sse_status) ? 0 : -1)
-#define FPU_CMPORD(size, a, b) \
- (float ## size ## _unordered_quiet(a, b, &env->sse_status) ? 0 : -1)
+#if SHIFT == 1
+#define SSE_HELPER_CMP(name, F, C) \
+ SSE_HELPER_CMP_P(name, F, C) \
+ void helper_ ## name ## ss(CPUX86State *env, Reg *d, Reg *s) \
+ { \
+ Reg *v = d; \
+ d->ZMM_L(0) = F(32, C, v->ZMM_S(0), s->ZMM_S(0)); \
+ } \
+ \
+ void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s) \
+ { \
+ Reg *v = d; \
+ d->ZMM_Q(0) = F(64, C, v->ZMM_D(0), s->ZMM_D(0)); \
+ }
-SSE_HELPER_CMP(cmpeq, FPU_CMPEQ)
-SSE_HELPER_CMP(cmplt, FPU_CMPLT)
-SSE_HELPER_CMP(cmple, FPU_CMPLE)
-SSE_HELPER_CMP(cmpunord, FPU_CMPUNORD)
-SSE_HELPER_CMP(cmpneq, FPU_CMPNEQ)
-SSE_HELPER_CMP(cmpnlt, FPU_CMPNLT)
-SSE_HELPER_CMP(cmpnle, FPU_CMPNLE)
-SSE_HELPER_CMP(cmpord, FPU_CMPORD)
+#define FPU_EQ(x) (x == float_relation_equal)
+#define FPU_LT(x) (x == float_relation_less)
+#define FPU_LE(x) (x <= float_relation_equal)
+#define FPU_UNORD(x) (x == float_relation_unordered)
+
+#define FPU_CMPQ(size, COND, a, b) \
+ (COND(float ## size ## _compare_quiet(a, b, &env->sse_status)) ? -1 : 0)
+#define FPU_CMPS(size, COND, a, b) \
+ (COND(float ## size ## _compare(a, b, &env->sse_status)) ? -1 : 0)
+
+#else
+#define SSE_HELPER_CMP(name, F, C) SSE_HELPER_CMP_P(name, F, C)
+#endif
+
+SSE_HELPER_CMP(cmpeq, FPU_CMPQ, FPU_EQ)
+SSE_HELPER_CMP(cmplt, FPU_CMPS, FPU_LT)
+SSE_HELPER_CMP(cmple, FPU_CMPS, FPU_LE)
+SSE_HELPER_CMP(cmpunord, FPU_CMPQ, FPU_UNORD)
+SSE_HELPER_CMP(cmpneq, FPU_CMPQ, !FPU_EQ)
+SSE_HELPER_CMP(cmpnlt, FPU_CMPS, !FPU_LT)
+SSE_HELPER_CMP(cmpnle, FPU_CMPS, !FPU_LE)
+SSE_HELPER_CMP(cmpord, FPU_CMPQ, !FPU_UNORD)
+
+#undef SSE_HELPER_CMP
static const int comis_eflags[4] = {CC_C, CC_Z, 0, CC_Z | CC_P | CC_C};
--git a/target/i386/ops_sse_header.h b/target/i386/ops_sse_header.h
index fc697536a0..d99464afb0 100644
--- a/target/i386/ops_sse_header.h
+++ b/target/i386/ops_sse_header.h
@@ -201,20 +201,20 @@ DEF_HELPER_3(glue(hsubpd, SUFFIX), void, env, ZMMReg, ZMMReg)
DEF_HELPER_3(glue(addsubps, SUFFIX), void, env, ZMMReg, ZMMReg)
DEF_HELPER_3(glue(addsubpd, SUFFIX), void, env, ZMMReg, ZMMReg)
-#define SSE_HELPER_CMP(name, F) \
- DEF_HELPER_3(glue(name ## ps, SUFFIX), void, env, Reg, Reg) \
- DEF_HELPER_3(name ## ss, void, env, Reg, Reg) \
- DEF_HELPER_3(glue(name ## pd, SUFFIX), void, env, Reg, Reg) \
+#define SSE_HELPER_CMP(name, F, C) \
+ DEF_HELPER_3(glue(name ## ps, SUFFIX), void, env, Reg, Reg) \
+ DEF_HELPER_3(name ## ss, void, env, Reg, Reg) \
+ DEF_HELPER_3(glue(name ## pd, SUFFIX), void, env, Reg, Reg) \
DEF_HELPER_3(name ## sd, void, env, Reg, Reg)
-SSE_HELPER_CMP(cmpeq, FPU_CMPEQ)
-SSE_HELPER_CMP(cmplt, FPU_CMPLT)
-SSE_HELPER_CMP(cmple, FPU_CMPLE)
-SSE_HELPER_CMP(cmpunord, FPU_CMPUNORD)
-SSE_HELPER_CMP(cmpneq, FPU_CMPNEQ)
-SSE_HELPER_CMP(cmpnlt, FPU_CMPNLT)
-SSE_HELPER_CMP(cmpnle, FPU_CMPNLE)
-SSE_HELPER_CMP(cmpord, FPU_CMPORD)
+SSE_HELPER_CMP(cmpeq, FPU_CMPQ, FPU_EQ)
+SSE_HELPER_CMP(cmplt, FPU_CMPS, FPU_LT)
+SSE_HELPER_CMP(cmple, FPU_CMPS, FPU_LE)
+SSE_HELPER_CMP(cmpunord, FPU_CMPQ, FPU_UNORD)
+SSE_HELPER_CMP(cmpneq, FPU_CMPQ, !FPU_EQ)
+SSE_HELPER_CMP(cmpnlt, FPU_CMPS, !FPU_LT)
+SSE_HELPER_CMP(cmpnle, FPU_CMPS, !FPU_LE)
+SSE_HELPER_CMP(cmpord, FPU_CMPQ, !FPU_UNORD)
DEF_HELPER_3(ucomiss, void, env, Reg, Reg)
DEF_HELPER_3(comiss, void, env, Reg, Reg)
diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
index 1e67607ca3..059e001d82 100644
--- a/target/i386/tcg/translate.c
+++ b/target/i386/tcg/translate.c
@@ -3021,20 +3021,20 @@ static const SSEFunc_l_ep sse_op_table3bq[] = {
};
#endif
-#define SSE_FOP(x) { \
+#define SSE_CMP(x) { \
gen_helper_ ## x ## ps ## _xmm, gen_helper_ ## x ## pd ## _xmm, \
gen_helper_ ## x ## ss, gen_helper_ ## x ## sd}
static const SSEFunc_0_epp sse_op_table4[8][4] = {
- SSE_FOP(cmpeq),
- SSE_FOP(cmplt),
- SSE_FOP(cmple),
- SSE_FOP(cmpunord),
- SSE_FOP(cmpneq),
- SSE_FOP(cmpnlt),
- SSE_FOP(cmpnle),
- SSE_FOP(cmpord),
+ SSE_CMP(cmpeq),
+ SSE_CMP(cmplt),
+ SSE_CMP(cmple),
+ SSE_CMP(cmpunord),
+ SSE_CMP(cmpneq),
+ SSE_CMP(cmpnlt),
+ SSE_CMP(cmpnle),
+ SSE_CMP(cmpord),
};
-#undef SSE_FOP
+#undef SSE_CMP
static const SSEFunc_0_epp sse_op_table5[256] = {
[0x0c] = gen_helper_pi2fw,
--
2.37.1
next prev parent reply other threads:[~2022-08-25 22:40 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-25 22:13 [PATCH 00/18] target/i386: make most SSE helpers generic in the vector size Paolo Bonzini
2022-08-25 22:13 ` [PATCH 01/18] i386: Rework sse_op_table1 Paolo Bonzini
2022-08-25 23:38 ` Richard Henderson
2022-08-26 20:15 ` Paolo Bonzini
2022-08-25 22:13 ` [PATCH 02/18] i386: Rework sse_op_table6/7 Paolo Bonzini
2022-08-25 23:43 ` Richard Henderson
2022-08-25 22:13 ` [PATCH 03/18] i386: Add CHECK_NO_VEX Paolo Bonzini
2022-08-26 15:37 ` Richard Henderson
2022-08-25 22:13 ` [PATCH 04/18] i386: Move 3DNOW decoder Paolo Bonzini
2022-08-25 23:47 ` Richard Henderson
2022-08-25 22:13 ` [PATCH 05/18] i386: Add ZMM_OFFSET macro Paolo Bonzini
2022-08-25 22:13 ` [PATCH 06/18] i386: Rewrite vector shift helper Paolo Bonzini
2022-08-25 23:53 ` Richard Henderson
2022-08-25 22:14 ` [PATCH 07/18] i386: Rewrite simple integer vector helpers Paolo Bonzini
2022-08-26 0:01 ` Richard Henderson
2022-08-26 11:31 ` Paolo Bonzini
2022-08-25 22:14 ` [PATCH 08/18] i386: Misc integer AVX helper prep Paolo Bonzini
2022-08-26 0:06 ` Richard Henderson
2022-08-25 22:14 ` [PATCH 09/18] i386: Destructive vector helpers for AVX Paolo Bonzini
2022-08-26 0:41 ` Richard Henderson
2022-08-25 22:14 ` [PATCH 10/18] i386: Add size suffix to vector FP helpers Paolo Bonzini
2022-08-26 0:42 ` Richard Henderson
2022-08-25 22:14 ` [PATCH 11/18] i386: Floating point arithmetic helper AVX prep Paolo Bonzini
2022-08-26 0:44 ` Richard Henderson
2022-08-25 22:14 ` Paolo Bonzini [this message]
2022-08-26 0:56 ` [PATCH 12/18] i386: reimplement AVX comparison helpers Richard Henderson
2022-08-25 22:14 ` [PATCH 13/18] i386: Dot product AVX helper prep Paolo Bonzini
2022-08-26 1:01 ` Richard Henderson
2022-08-25 22:14 ` [PATCH 14/18] i386: Destructive FP helpers for AVX Paolo Bonzini
2022-08-26 1:03 ` Richard Henderson
2022-08-25 22:14 ` [PATCH 15/18] i386: Misc AVX helper prep Paolo Bonzini
2022-08-26 15:47 ` Richard Henderson
2022-08-25 22:14 ` [PATCH 16/18] i386: Rewrite blendv helpers Paolo Bonzini
2022-08-26 15:53 ` Richard Henderson
2022-08-25 22:14 ` [PATCH 17/18] i386: AVX pclmulqdq prep Paolo Bonzini
2022-08-26 15:57 ` Richard Henderson
2022-08-25 22:14 ` [PATCH 18/18] i386: AVX+AES helpers prep Paolo Bonzini
2022-08-26 16:55 ` Richard Henderson
2022-08-25 23:32 ` [PATCH 00/18] target/i386: make most SSE helpers generic in the vector size 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=20220825221411.35122-13-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).