public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc/devel/autopar_devel] x86: Enable FMA in rsqrt<mode>2 expander
@ 2020-08-22 23:29 Giuliano Belinassi
0 siblings, 0 replies; only message in thread
From: Giuliano Belinassi @ 2020-08-22 23:29 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:7d54540883078fd9faabdab9d39df8f3e5714f69
commit 7d54540883078fd9faabdab9d39df8f3e5714f69
Author: H.J. Lu <hjl.tools@gmail.com>
Date: Wed Jan 23 06:33:58 2019 -0800
x86: Enable FMA in rsqrt<mode>2 expander
Enable FMA in rsqrt<mode>2 expander and fold rsqrtv16sf2 expander into
rsqrt<mode>2 expander which expands to UNSPEC_RSQRT28 for TARGET_AVX512ER.
Although it doesn't show performance change in our workloads, FMA can
improve other workloads.
gcc/
PR target/88713
* config/i386/i386-expand.c (ix86_emit_swsqrtsf): Enable FMA.
* config/i386/sse.md (VF_AVX512VL_VF1_128_256): New.
(rsqrt<mode>2): Replace VF1_128_256 with VF_AVX512VL_VF1_128_256.
(rsqrtv16sf2): Removed.
gcc/testsuite/
PR target/88713
* gcc.target/i386/pr88713-1.c: New test.
* gcc.target/i386/pr88713-2.c: Likewise.
Diff:
---
gcc/config/i386/i386-expand.c | 18 +++++++++++++-----
gcc/config/i386/sse.md | 24 ++++++++++--------------
gcc/testsuite/gcc.target/i386/pr88713-1.c | 13 +++++++++++++
gcc/testsuite/gcc.target/i386/pr88713-2.c | 6 ++++++
4 files changed, 42 insertions(+), 19 deletions(-)
diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index d81dd73f034..49718b7a41c 100644
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -15535,14 +15535,22 @@ void ix86_emit_swsqrtsf (rtx res, rtx a, machine_mode mode, bool recip)
}
}
+ mthree = force_reg (mode, mthree);
+
/* e0 = x0 * a */
emit_insn (gen_rtx_SET (e0, gen_rtx_MULT (mode, x0, a)));
- /* e1 = e0 * x0 */
- emit_insn (gen_rtx_SET (e1, gen_rtx_MULT (mode, e0, x0)));
- /* e2 = e1 - 3. */
- mthree = force_reg (mode, mthree);
- emit_insn (gen_rtx_SET (e2, gen_rtx_PLUS (mode, e1, mthree)));
+ if (TARGET_FMA || TARGET_AVX512F)
+ emit_insn (gen_rtx_SET (e2,
+ gen_rtx_FMA (mode, e0, x0, mthree)));
+ else
+ {
+ /* e1 = e0 * x0 */
+ emit_insn (gen_rtx_SET (e1, gen_rtx_MULT (mode, e0, x0)));
+
+ /* e2 = e1 - 3. */
+ emit_insn (gen_rtx_SET (e2, gen_rtx_PLUS (mode, e1, mthree)));
+ }
mhalf = force_reg (mode, mhalf);
if (recip)
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 431571a4bc1..d3ad5833e1f 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -326,6 +326,12 @@
[V16SF (V8SF "TARGET_AVX512VL") (V4SF "TARGET_AVX512VL")
V8DF (V4DF "TARGET_AVX512VL") (V2DF "TARGET_AVX512VL")])
+;; AVX512VL SF/DF plus 128- and 256-bit SF vector modes
+(define_mode_iterator VF_AVX512VL_VF1_128_256
+ [(V16SF "TARGET_AVX512F") (V8SF "TARGET_AVX") V4SF
+ (V8DF "TARGET_AVX512F") (V4DF "TARGET_AVX512VL")
+ (V2DF "TARGET_AVX512VL")])
+
(define_mode_iterator VF2_AVX512VL
[V8DF (V4DF "TARGET_AVX512VL") (V2DF "TARGET_AVX512VL")])
@@ -2070,26 +2076,16 @@
(set_attr "mode" "<ssescalarmode>")])
(define_expand "rsqrt<mode>2"
- [(set (match_operand:VF1_128_256 0 "register_operand")
- (unspec:VF1_128_256
- [(match_operand:VF1_128_256 1 "vector_operand")] UNSPEC_RSQRT))]
+ [(set (match_operand:VF_AVX512VL_VF1_128_256 0 "register_operand")
+ (unspec:VF_AVX512VL_VF1_128_256
+ [(match_operand:VF_AVX512VL_VF1_128_256 1 "vector_operand")]
+ UNSPEC_RSQRT))]
"TARGET_SSE && TARGET_SSE_MATH"
{
ix86_emit_swsqrtsf (operands[0], operands[1], <MODE>mode, true);
DONE;
})
-(define_expand "rsqrtv16sf2"
- [(set (match_operand:V16SF 0 "register_operand")
- (unspec:V16SF
- [(match_operand:V16SF 1 "vector_operand")]
- UNSPEC_RSQRT28))]
- "TARGET_AVX512ER && TARGET_SSE_MATH"
-{
- ix86_emit_swsqrtsf (operands[0], operands[1], V16SFmode, true);
- DONE;
-})
-
(define_insn "<sse>_rsqrt<mode>2"
[(set (match_operand:VF1_128_256 0 "register_operand" "=x")
(unspec:VF1_128_256
diff --git a/gcc/testsuite/gcc.target/i386/pr88713-1.c b/gcc/testsuite/gcc.target/i386/pr88713-1.c
new file mode 100644
index 00000000000..26a0da57a41
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr88713-1.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-Ofast -mno-avx512f -mfma" } */
+
+extern float sqrtf (float);
+
+void
+rsqrt (float* restrict r, float* restrict a)
+{
+ for (int i = 0; i < 64; i++)
+ r[i] = sqrtf(a[i]);
+}
+
+/* { dg-final { scan-assembler "\tvfmadd\[123\]+ps" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr88713-2.c b/gcc/testsuite/gcc.target/i386/pr88713-2.c
new file mode 100644
index 00000000000..8b55dfcf924
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr88713-2.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-options "-Ofast -march=skylake-avx512 -mno-fma" } */
+
+#include "pr88713-1.c"
+
+/* { dg-final { scan-assembler "\tvfmadd\[123\]+ps" } } */
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2020-08-22 23:29 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-08-22 23:29 [gcc/devel/autopar_devel] x86: Enable FMA in rsqrt<mode>2 expander Giuliano Belinassi
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 read-only IMAP folder(s) and NNTP newsgroup(s).