aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorRichard Earnshaw <rearnsha@arm.com>2025-03-26 15:56:18 +0000
committerRichard Earnshaw <rearnsha@arm.com>2025-03-27 10:54:23 +0000
commitb631ff45f231db55b28b4c92cf1a1b46b3638ddd (patch)
tree2c17bdf98c74ae55cba6a1dc99e10ac830ffad16
parent271745bafafbf3316d01ceb6430d67b894129a4c (diff)
downloadgcc-b631ff45f231db55b28b4c92cf1a1b46b3638ddd.zip
gcc-b631ff45f231db55b28b4c92cf1a1b46b3638ddd.tar.gz
gcc-b631ff45f231db55b28b4c92cf1a1b46b3638ddd.tar.bz2
arm: don't vectorize fmaxf() unless unsafe math opts are enabled
This test has presumably been failing since vectorization was enabled at -O2. I suspect part of the reason this wasn't picked up sooner is that the test is a hybrid execution/scan-assembler test and the execution part requires appropriate hardware. The problem is that we are vectorizing an expansion of fmaxf() when the vector version of the instruction does not preserve denormal values. This means we should only apply this optimization when -funsafe-math-optimizations is enabled. This fix does a few things: - Moves the expand pattern to vec-common.md. Although I haven't changed its behaviour (beyond fixing the bug), this should really be enabled for MVE as well (but that will need to wait for gcc-16 since the MVE code needs some additional changes first). - Adds support for HF mode vectors. - splits the test that was exposing the bug into two parts: an executable test and a scan-assembler test. The scan-assembler version is more widely enabled, since it does not require a suitable executable environment. gcc/ChangeLog: * config/arm/neon.md (<fmaxmin><mode>3): Move pattern from here... * config/arm/vec-common.md (<fmaxmin><mode>3): ... to here. Convert to define_expand and disable the pattern when denormal values might get truncated to zero. Iterate on VF to add V4HF and V8HF variants. gcc/testsuite/ChangeLog: * gcc.target/arm/fmaxmin.c: Move scan-assembler checks to ... * gcc.target/arm/fmaxmin-2.c: ... here. New test.
-rw-r--r--gcc/config/arm/neon.md11
-rw-r--r--gcc/config/arm/vec-common.md11
-rw-r--r--gcc/testsuite/gcc.target/arm/fmaxmin-2.c12
-rw-r--r--gcc/testsuite/gcc.target/arm/fmaxmin.c9
4 files changed, 24 insertions, 19 deletions
diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
index ef33106..8446dd7 100644
--- a/gcc/config/arm/neon.md
+++ b/gcc/config/arm/neon.md
@@ -2738,17 +2738,6 @@
[(set_attr "type" "neon_fp_minmax_s<q>")]
)
-;; Vector forms for the IEEE-754 fmax()/fmin() functions
-(define_insn "<fmaxmin><mode>3"
- [(set (match_operand:VCVTF 0 "s_register_operand" "=w")
- (unspec:VCVTF [(match_operand:VCVTF 1 "s_register_operand" "w")
- (match_operand:VCVTF 2 "s_register_operand" "w")]
- VMAXMINFNM))]
- "TARGET_NEON && TARGET_VFP5"
- "<fmaxmin_op>.<V_s_elem>\t%<V_reg>0, %<V_reg>1, %<V_reg>2"
- [(set_attr "type" "neon_fp_minmax_s<q>")]
-)
-
(define_expand "neon_vpadd<mode>"
[(match_operand:VD 0 "s_register_operand")
(match_operand:VD 1 "s_register_operand")
diff --git a/gcc/config/arm/vec-common.md b/gcc/config/arm/vec-common.md
index 204205c..a485d05 100644
--- a/gcc/config/arm/vec-common.md
+++ b/gcc/config/arm/vec-common.md
@@ -137,6 +137,17 @@
"ARM_HAVE_<MODE>_ARITH"
)
+;; Vector forms for the IEEE-754 fmax()/fmin() functions
+;; Fixme: Should be enabled for MVE as well, but currently that uses an
+;; incompatible expasion.
+(define_expand "<fmaxmin><mode>3"
+ [(set (match_operand:VF 0 "s_register_operand" "")
+ (unspec:VF [(match_operand:VF 1 "s_register_operand")
+ (match_operand:VF 2 "s_register_operand")]
+ VMAXMINFNM))]
+ "TARGET_NEON && TARGET_VFP5 && ARM_HAVE_<MODE>_ARITH"
+)
+
(define_expand "vec_perm<mode>"
[(match_operand:VE 0 "s_register_operand")
(match_operand:VE 1 "s_register_operand")
diff --git a/gcc/testsuite/gcc.target/arm/fmaxmin-2.c b/gcc/testsuite/gcc.target/arm/fmaxmin-2.c
new file mode 100644
index 0000000..a9990e1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/fmaxmin-2.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_arch_v8a_hard_ok } */
+/* { dg-options "-O2 -fno-inline" } */
+/* { dg-add-options arm_arch_v8a_hard } */
+
+#include "fmaxmin.x"
+
+/* { dg-final { scan-assembler-times "vmaxnm.f32\ts\[0-9\]+, s\[0-9\]+, s\[0-9\]+" 1 } } */
+/* { dg-final { scan-assembler-times "vminnm.f32\ts\[0-9\]+, s\[0-9\]+, s\[0-9\]+" 1 } } */
+
+/* { dg-final { scan-assembler-times "vmaxnm.f64\td\[0-9\]+, d\[0-9\]+, d\[0-9\]+" 1 } } */
+/* { dg-final { scan-assembler-times "vminnm.f64\td\[0-9\]+, d\[0-9\]+, d\[0-9\]+" 1 } } */
diff --git a/gcc/testsuite/gcc.target/arm/fmaxmin.c b/gcc/testsuite/gcc.target/arm/fmaxmin.c
index 5a6fb80..7f30c12 100644
--- a/gcc/testsuite/gcc.target/arm/fmaxmin.c
+++ b/gcc/testsuite/gcc.target/arm/fmaxmin.c
@@ -1,13 +1,6 @@
/* { dg-do run } */
/* { dg-require-effective-target arm_v8_neon_hw } */
-/* { dg-options "-O2 -fno-inline -march=armv8-a -save-temps" } */
+/* { dg-options "-O2 -fno-inline" } */
/* { dg-add-options arm_v8_neon } */
#include "fmaxmin.x"
-
-/* { dg-final { scan-assembler-times "vmaxnm.f32\ts\[0-9\]+, s\[0-9\]+, s\[0-9\]+" 1 } } */
-/* { dg-final { scan-assembler-times "vminnm.f32\ts\[0-9\]+, s\[0-9\]+, s\[0-9\]+" 1 } } */
-
-/* { dg-final { scan-assembler-times "vmaxnm.f64\td\[0-9\]+, d\[0-9\]+, d\[0-9\]+" 1 } } */
-/* { dg-final { scan-assembler-times "vminnm.f64\td\[0-9\]+, d\[0-9\]+, d\[0-9\]+" 1 } } */
-