https://gcc.gnu.org/g:959d6529df206c1983be14383da081f374416e47
commit r13-8977-g959d6529df206c1983be14383da081f374416e47
Author: Richard Sandiford <richard.sandif...@arm.com>
Date: Fri Aug 16 07:58:25 2024 +0100
aarch64: Fix bogus cnot optimisation [PR114603]
aarch64-sve.md had a pattern that combined:
cmpeq pb.T, pa/z, zc.T, #0
mov zd.T, pb/z, #1
into:
cnot zd.T, pa/m, zc.T
But this is only valid if pa.T is a ptrue. In other cases, the
original would set inactive elements of zd.T to 0, whereas the
combined form would copy elements from zc.T.
gcc/
PR target/114603
* config/aarch64/aarch64-sve.md (@aarch64_pred_cnot<mode>): Replace
with...
(@aarch64_ptrue_cnot<mode>): ...this, requiring operand 1 to be
a ptrue.
(*cnot<mode>): Require operand 1 to be a ptrue.
* config/aarch64/aarch64-sve-builtins-base.cc (svcnot_impl::expand):
Use aarch64_ptrue_cnot<mode> for _x operations that are predicated
with a ptrue. Represent other _x operations as fully-defined _m
operations.
gcc/testsuite/
PR target/114603
* gcc.target/aarch64/sve/acle/general/cnot_1.c: New test.
(cherry picked from commit 67cbb1c638d6ab3a9cb77e674541e2b291fb67df)
Diff:
---
gcc/config/aarch64/aarch64-sve-builtins-base.cc | 25 ++++++++++++++--------
gcc/config/aarch64/aarch64-sve.md | 20 ++++++++---------
.../gcc.target/aarch64/sve/acle/general/cnot_1.c | 23 ++++++++++++++++++++
3 files changed, 49 insertions(+), 19 deletions(-)
diff --git a/gcc/config/aarch64/aarch64-sve-builtins-base.cc
b/gcc/config/aarch64/aarch64-sve-builtins-base.cc
index 34f2d8c6e4e..852f569461a 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins-base.cc
+++ b/gcc/config/aarch64/aarch64-sve-builtins-base.cc
@@ -496,15 +496,22 @@ public:
expand (function_expander &e) const override
{
machine_mode mode = e.vector_mode (0);
- if (e.pred == PRED_x)
- {
- /* The pattern for CNOT includes an UNSPEC_PRED_Z, so needs
- a ptrue hint. */
- e.add_ptrue_hint (0, e.gp_mode (0));
- return e.use_pred_x_insn (code_for_aarch64_pred_cnot (mode));
- }
-
- return e.use_cond_insn (code_for_cond_cnot (mode), 0);
+ machine_mode pred_mode = e.gp_mode (0);
+ /* The underlying _x pattern is effectively:
+
+ dst = src == 0 ? 1 : 0
+
+ rather than an UNSPEC_PRED_X. Using this form allows autovec
+ constructs to be matched by combine, but it means that the
+ predicate on the src == 0 comparison must be all-true.
+
+ For simplicity, represent other _x operations as fully-defined _m
+ operations rather than using a separate bespoke pattern. */
+ if (e.pred == PRED_x
+ && gen_lowpart (pred_mode, e.args[0]) == CONSTM1_RTX (pred_mode))
+ return e.use_pred_x_insn (code_for_aarch64_ptrue_cnot (mode));
+ return e.use_cond_insn (code_for_cond_cnot (mode),
+ e.pred == PRED_x ? 1 : 0);
}
};
diff --git a/gcc/config/aarch64/aarch64-sve.md
b/gcc/config/aarch64/aarch64-sve.md
index 7533b956686..0a05aecd1a3 100644
--- a/gcc/config/aarch64/aarch64-sve.md
+++ b/gcc/config/aarch64/aarch64-sve.md
@@ -3225,24 +3225,24 @@
;; - CNOT
;; -------------------------------------------------------------------------
-;; Predicated logical inverse.
-(define_expand "@aarch64_pred_cnot<mode>"
+;; Logical inverse, predicated with a ptrue.
+(define_expand "@aarch64_ptrue_cnot<mode>"
[(set (match_operand:SVE_FULL_I 0 "register_operand")
(unspec:SVE_FULL_I
[(unspec:<VPRED>
[(match_operand:<VPRED> 1 "register_operand")
- (match_operand:SI 2 "aarch64_sve_ptrue_flag")
+ (const_int SVE_KNOWN_PTRUE)
(eq:<VPRED>
- (match_operand:SVE_FULL_I 3 "register_operand")
- (match_dup 4))]
+ (match_operand:SVE_FULL_I 2 "register_operand")
+ (match_dup 3))]
UNSPEC_PRED_Z)
- (match_dup 5)
- (match_dup 4)]
+ (match_dup 4)
+ (match_dup 3)]
UNSPEC_SEL))]
"TARGET_SVE"
{
- operands[4] = CONST0_RTX (<MODE>mode);
- operands[5] = CONST1_RTX (<MODE>mode);
+ operands[3] = CONST0_RTX (<MODE>mode);
+ operands[4] = CONST1_RTX (<MODE>mode);
}
)
@@ -3251,7 +3251,7 @@
(unspec:SVE_I
[(unspec:<VPRED>
[(match_operand:<VPRED> 1 "register_operand" "Upl, Upl")
- (match_operand:SI 5 "aarch64_sve_ptrue_flag")
+ (const_int SVE_KNOWN_PTRUE)
(eq:<VPRED>
(match_operand:SVE_I 2 "register_operand" "0, w")
(match_operand:SVE_I 3 "aarch64_simd_imm_zero"))]
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/acle/general/cnot_1.c
b/gcc/testsuite/gcc.target/aarch64/sve/acle/general/cnot_1.c
new file mode 100644
index 00000000000..b1a489f0cf0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/acle/general/cnot_1.c
@@ -0,0 +1,23 @@
+/* { dg-options "-O2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include <arm_sve.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/*
+** foo:
+** cmpeq (p[0-7])\.s, p0/z, z0\.s, #0
+** mov z0\.s, \1/z, #1
+** ret
+*/
+svint32_t foo(svbool_t pg, svint32_t y)
+{
+ return svsel(svcmpeq(pg, y, 0), svdup_s32(1), svdup_s32(0));
+}
+
+#ifdef __cplusplus
+}
+#endif
