130 lines
4.5 KiB
Diff
130 lines
4.5 KiB
Diff
From 764518a35e90a3e13c469275da9c3c7002fe1982 Mon Sep 17 00:00:00 2001
|
|
From: liuhongt <hongtao.liu@intel.com>
|
|
Date: Fri, 8 Sep 2023 09:22:43 +0800
|
|
Subject: [PATCH 13/32] Remove constraint modifier % for
|
|
fcmaddcph/fmaddcph/fcmulcph since there're not commutative.
|
|
|
|
gcc/ChangeLog:
|
|
|
|
PR target/111306
|
|
PR target/111335
|
|
* config/i386/sse.md (int_comm): New int_attr.
|
|
(fma_<complexopname>_<mode><sdc_maskz_name><round_name>):
|
|
Remove % for Complex conjugate operations since they're not
|
|
commutative.
|
|
(fma_<complexpairopname>_<mode>_pair): Ditto.
|
|
(<avx512>_<complexopname>_<mode>_mask<round_name>): Ditto.
|
|
(cmul<conj_op><mode>3): Ditto.
|
|
|
|
gcc/testsuite/ChangeLog:
|
|
|
|
* gcc.target/i386/pr111306.c: New test.
|
|
|
|
(cherry picked from commit f197392a16ffb1327f1d12ff8ff05f9295e015cb)
|
|
---
|
|
gcc/config/i386/sse.md | 16 ++++++++---
|
|
gcc/testsuite/gcc.target/i386/pr111306.c | 36 ++++++++++++++++++++++++
|
|
2 files changed, 48 insertions(+), 4 deletions(-)
|
|
create mode 100644 gcc/testsuite/gcc.target/i386/pr111306.c
|
|
|
|
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
|
|
index 3af159896..f25dd5f2b 100644
|
|
--- a/gcc/config/i386/sse.md
|
|
+++ b/gcc/config/i386/sse.md
|
|
@@ -6318,6 +6318,14 @@
|
|
[(UNSPEC_COMPLEX_FMA_PAIR "fmaddc")
|
|
(UNSPEC_COMPLEX_FCMA_PAIR "fcmaddc")])
|
|
|
|
+(define_int_attr int_comm
|
|
+ [(UNSPEC_COMPLEX_FMA "")
|
|
+ (UNSPEC_COMPLEX_FMA_PAIR "")
|
|
+ (UNSPEC_COMPLEX_FCMA "")
|
|
+ (UNSPEC_COMPLEX_FCMA_PAIR "")
|
|
+ (UNSPEC_COMPLEX_FMUL "%")
|
|
+ (UNSPEC_COMPLEX_FCMUL "")])
|
|
+
|
|
(define_int_attr conj_op
|
|
[(UNSPEC_COMPLEX_FMA "")
|
|
(UNSPEC_COMPLEX_FCMA "_conj")
|
|
@@ -6431,7 +6439,7 @@
|
|
(define_insn "fma_<complexopname>_<mode><sdc_maskz_name><round_name>"
|
|
[(set (match_operand:VF_AVX512FP16VL 0 "register_operand" "=&v")
|
|
(unspec:VF_AVX512FP16VL
|
|
- [(match_operand:VF_AVX512FP16VL 1 "<round_nimm_predicate>" "%v")
|
|
+ [(match_operand:VF_AVX512FP16VL 1 "<round_nimm_predicate>" "<int_comm>v")
|
|
(match_operand:VF_AVX512FP16VL 2 "<round_nimm_predicate>" "<round_constraint>")
|
|
(match_operand:VF_AVX512FP16VL 3 "<round_nimm_predicate>" "0")]
|
|
UNSPEC_COMPLEX_F_C_MA))]
|
|
@@ -6495,7 +6503,7 @@
|
|
(define_insn "fma_<complexpairopname>_<mode>_pair"
|
|
[(set (match_operand:VF1_AVX512VL 0 "register_operand" "=&v")
|
|
(unspec:VF1_AVX512VL
|
|
- [(match_operand:VF1_AVX512VL 1 "vector_operand" "%v")
|
|
+ [(match_operand:VF1_AVX512VL 1 "vector_operand" "<int_comm>v")
|
|
(match_operand:VF1_AVX512VL 2 "bcst_vector_operand" "vmBr")
|
|
(match_operand:VF1_AVX512VL 3 "vector_operand" "0")]
|
|
UNSPEC_COMPLEX_F_C_MA_PAIR))]
|
|
@@ -6562,7 +6570,7 @@
|
|
[(set (match_operand:VF_AVX512FP16VL 0 "register_operand" "=&v")
|
|
(vec_merge:VF_AVX512FP16VL
|
|
(unspec:VF_AVX512FP16VL
|
|
- [(match_operand:VF_AVX512FP16VL 1 "nonimmediate_operand" "%v")
|
|
+ [(match_operand:VF_AVX512FP16VL 1 "nonimmediate_operand" "<int_comm>v")
|
|
(match_operand:VF_AVX512FP16VL 2 "nonimmediate_operand" "<round_constraint>")
|
|
(match_operand:VF_AVX512FP16VL 3 "register_operand" "0")]
|
|
UNSPEC_COMPLEX_F_C_MA)
|
|
@@ -6586,7 +6594,7 @@
|
|
(define_insn "<avx512>_<complexopname>_<mode><maskc_name><round_name>"
|
|
[(set (match_operand:VF_AVX512FP16VL 0 "register_operand" "=&v")
|
|
(unspec:VF_AVX512FP16VL
|
|
- [(match_operand:VF_AVX512FP16VL 1 "nonimmediate_operand" "%v")
|
|
+ [(match_operand:VF_AVX512FP16VL 1 "nonimmediate_operand" "<int_comm>v")
|
|
(match_operand:VF_AVX512FP16VL 2 "nonimmediate_operand" "<round_constraint>")]
|
|
UNSPEC_COMPLEX_F_C_MUL))]
|
|
"TARGET_AVX512FP16 && <round_mode512bit_condition>"
|
|
diff --git a/gcc/testsuite/gcc.target/i386/pr111306.c b/gcc/testsuite/gcc.target/i386/pr111306.c
|
|
new file mode 100644
|
|
index 000000000..541725ebd
|
|
--- /dev/null
|
|
+++ b/gcc/testsuite/gcc.target/i386/pr111306.c
|
|
@@ -0,0 +1,36 @@
|
|
+/* { dg-do run } */
|
|
+/* { dg-options "-O2 -mavx512fp16 -mavx512vl" } */
|
|
+/* { dg-require-effective-target avx512fp16 } */
|
|
+
|
|
+#define AVX512FP16
|
|
+#include "avx512f-helper.h"
|
|
+
|
|
+__attribute__((optimize("O2"),noipa))
|
|
+void func1(_Float16 *a, _Float16 *b, int n, _Float16 *c) {
|
|
+ __m512h rA = _mm512_loadu_ph(a);
|
|
+ for (int i = 0; i < n; i += 32) {
|
|
+ __m512h rB = _mm512_loadu_ph(b + i);
|
|
+ _mm512_storeu_ph(c + i, _mm512_fcmul_pch(rB, rA));
|
|
+ }
|
|
+}
|
|
+
|
|
+void
|
|
+test_512 (void)
|
|
+{
|
|
+ int n = 32;
|
|
+ _Float16 a[n], b[n], c[n];
|
|
+ _Float16 exp[n];
|
|
+ for (int i = 1; i <= n; i++) {
|
|
+ a[i - 1] = i & 1 ? -i : i;
|
|
+ b[i - 1] = i;
|
|
+ }
|
|
+
|
|
+ func1(a, b, n, c);
|
|
+ for (int i = 0; i < n / 32; i += 2) {
|
|
+ if (c[i] != a[i] * b[i] + a[i+1] * b[i+1]
|
|
+ || c[i+1] != a[i] * b[i+1] - a[i+1]*b[i])
|
|
+ __builtin_abort ();
|
|
+ }
|
|
+}
|
|
+
|
|
+
|
|
--
|
|
2.28.0.windows.1
|
|
|