From f4ff20d464f90c85919ce2e7fa63e204dcda4e40 Mon Sep 17 00:00:00 2001 From: Tamar Christina Date: Fri, 12 Aug 2022 12:28:41 +0100 Subject: [PATCH] sve: Fix fcmuo combine patterns [PR106524] There's no encoding for fcmuo with zero. This restricts the combine patterns from accepting zero registers. gcc/ChangeLog: PR target/106524 * config/aarch64/aarch64-sve.md (*fcmuo_nor_combine, *fcmuo_bic_combine): Don't accept comparisons against zero. gcc/testsuite/ChangeLog: PR target/106524 * gcc.target/aarch64/sve/pr106524.c: New test. --- gcc/config/aarch64/aarch64-sve.md | 4 ++-- gcc/testsuite/gcc.target/aarch64/sve/pr106524.c | 11 +++++++++++ 2 files changed, 13 insertions(+), 2 deletions(-) create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/pr106524.c diff --git a/gcc/config/aarch64/aarch64-sve.md b/gcc/config/aarch64/aarch64-sve.md index bd60e65b0c3f..e08bee197d85 100644 --- a/gcc/config/aarch64/aarch64-sve.md +++ b/gcc/config/aarch64/aarch64-sve.md @@ -8231,7 +8231,7 @@ [(match_operand: 1) (const_int SVE_KNOWN_PTRUE) (match_operand:SVE_FULL_F 2 "register_operand" "w") - (match_operand:SVE_FULL_F 3 "aarch64_simd_reg_or_zero" "wDz")] + (match_operand:SVE_FULL_F 3 "register_operand" "w")] UNSPEC_COND_FCMUO)) (match_operand: 4 "register_operand" "Upa")) (match_dup: 1))) @@ -8267,7 +8267,7 @@ [(match_operand: 1) (const_int SVE_KNOWN_PTRUE) (match_operand:SVE_FULL_F 2 "register_operand" "w") - (match_operand:SVE_FULL_F 3 "aarch64_simd_reg_or_zero" "wDz")] + (match_operand:SVE_FULL_F 3 "register_operand" "w")] UNSPEC_COND_FCMUO)) (not: (match_operand: 4 "register_operand" "Upa"))) diff --git a/gcc/testsuite/gcc.target/aarch64/sve/pr106524.c b/gcc/testsuite/gcc.target/aarch64/sve/pr106524.c new file mode 100644 index 000000000000..a9f650f971a5 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/sve/pr106524.c @@ -0,0 +1,11 @@ +/* { dg-do compile } */ +/* { dg-options "-march=armv8-a+sve -O2 -fno-move-loop-invariants" } */ + +void +test__zero (int *restrict dest, int *restrict src, float *a, int count) +{ + int i; + + for (i = 0; i < count; ++i) + dest[i] = !__builtin_isunordered (a[i], 0) ? src[i] : 0; +} -- 2.47.2