[Bug target/111333] New: Runtime failure for fcmulcph instrinsic

[Bug target/111333] New: Runtime failure for fcmulcph instrinsic

[crazylht at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111333

            Bug ID: 111333
           Summary: Runtime failure for fcmulcph instrinsic
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: crazylht at gmail dot com
  Target Milestone: ---

cat main.cpp

#include <immintrin.h>
#include <cstdio>

__attribute__((optimize("O0")))
auto func0(_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));
  }
}

__attribute__((optimize("O2")))
auto 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));
  }
}

int main() {
  int n = 32;

  _Float16 a[n], b[n], c[n];
  for (int i = 1; i <= n; i++) {
    a[i - 1] = i & 1 ? -i : i;
    b[i - 1] = i;
  }
  printf("a = %f + %fi \n", (float)a[0], (float)a[1]);
  printf("b = %f + %fi \n", (float)b[0], (float)b[1]);
  printf("b * conj(a) = %f + %fi \n\n", (float)(a[0]*b[0] + a[1]*b[1]),
(float)(a[0]*b[1] - a[1]*b[0]));

  func0(a, b, n, c);
    for (int i = 0; i < n / 32 * 2; i++) {
      printf("%f ", (float)c[i]);
    }
    printf("\n");

  func1(a, b, n, c);
    for (int i = 0; i < n / 32 * 2; i++) {
      printf("%f ", (float)c[i]);
    }
    printf("\n");

  return 0;
}

g++ -march=sapphirerapids main.cpp -o test
sde -spr-- ./test

a = -1.000000 + 2.000000i
b = 1.000000 + 2.000000i
b * conj(a) = 3.000000 + -4.000000i

3.000000 -4.000000
3.000000 4.000000

[Bug target/111333] Runtime failure for fcmulcph instrinsic

[crazylht at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111333

--- Comment #1 from Hongtao.liu <crazylht at gmail dot com> ---
fmulcph/fmaddcph is commutative for operands[1] and operands[2], but
fcmulcph/fcmaddcph is not, since it's Complex conjugate operations.

Below change fixes the issue.

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 6d3ae8dea0c..833546c5228 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -6480,6 +6480,14 @@ (define_int_attr complexpairopname
        [(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")
@@ -6593,7 +6601,7 @@ (define_expand "cmla<conj_op><mode>4"
 (define_insn "fma_<complexopname>_<mode><sdc_maskz_name><round_name>"
   [(set (match_operand:VHF_AVX512VL 0 "register_operand" "=&v")
        (unspec:VHF_AVX512VL
-         [(match_operand:VHF_AVX512VL 1 "<round_nimm_predicate>" "%v")
+         [(match_operand:VHF_AVX512VL 1 "<round_nimm_predicate>"
"<int_comm>v")
           (match_operand:VHF_AVX512VL 2 "<round_nimm_predicate>"
"<round_constraint>")
           (match_operand:VHF_AVX512VL 3 "<round_nimm_predicate>" "0")]
           UNSPEC_COMPLEX_F_C_MA))]
@@ -6658,7 +6666,7 @@ (define_insn_and_split
"fma_<complexopname>_<mode>_fma_zero"
 (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))]
@@ -6727,7 +6735,7 @@ (define_insn
"<avx512>_<complexopname>_<mode>_mask<round_name>"
   [(set (match_operand:VHF_AVX512VL 0 "register_operand" "=&v")
        (vec_merge:VHF_AVX512VL
          (unspec:VHF_AVX512VL
-           [(match_operand:VHF_AVX512VL 1 "nonimmediate_operand" "%v")
+           [(match_operand:VHF_AVX512VL 1 "nonimmediate_operand"
"<int_comm>v")
             (match_operand:VHF_AVX512VL 2 "nonimmediate_operand"
"<round_constraint>")
             (match_operand:VHF_AVX512VL 3 "register_operand" "0")]
             UNSPEC_COMPLEX_F_C_MA)
@@ -6752,7 +6760,7 @@ (define_expand "cmul<conj_op><mode>3"
 (define_insn "<avx512>_<complexopname>_<mode><maskc_name><round_name>"
   [(set (match_operand:VHF_AVX512VL 0 "register_operand" "=&v")
          (unspec:VHF_AVX512VL
-           [(match_operand:VHF_AVX512VL 1 "nonimmediate_operand" "%v")
+           [(match_operand:VHF_AVX512VL 1 "nonimmediate_operand"
"<int_comm>v")
             (match_operand:VHF_AVX512VL 2 "nonimmediate_operand"
"<round_constraint>")]
             UNSPEC_COMPLEX_F_C_MUL))]
   "TARGET_AVX512FP16 && <round_mode512bit_condition>"

[Bug target/111333] Runtime failure for fcmulcph instrinsic

[crazylht at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111333

--- Comment #2 from Hongtao.liu <crazylht at gmail dot com> ---
The test failed since GCC12 when the pattern is added

[Bug target/111333] Runtime failure for fcmulcph instrinsic

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111333

--- Comment #3 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
Isn't this a dup of bug 111306 ?

[Bug target/111333] Runtime failure for fcmulcph instrinsic

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111333

Andrew Pinski <pinskia at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
         Resolution|---                         |DUPLICATE
             Status|UNCONFIRMED                 |RESOLVED

--- Comment #4 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
Yes this is an exact dup.

*** This bug has been marked as a duplicate of bug 111306 ***