From: Pan Li <pan2...@intel.com>
This patch aligned the MODE_CLASS condition of the IOR to the AND. Then
more MODE_CLASS besides SCALAR_INT can able to perform the optimization
A | (~A) -> -1 similar to AND operator. For example as below sample code.
vbool32_t test_shortcut_for_riscv_vmorn_case_5(vbool32_t v1, size_t vl)
{
return __riscv_vmorn_mm_b32(v1, v1, vl);
}
Before this patch:
vsetvli a5,zero,e8,mf4,ta,ma
vlm.v v24,0(a1)
vsetvli zero,a2,e8,mf4,ta,ma
vmorn.mm v24,v24,v24
vsetvli a5,zero,e8,mf4,ta,ma
vsm.v v24,0(a0)
ret
After this patch:
vsetvli zero,a2,e8,mf4,ta,ma
vmset.m v24
vsetvli a5,zero,e8,mf4,ta,ma
vsm.v v24,0(a0)
ret
Or in RTL's perspective,
from:
(ior:VNx2BI (reg/v:VNx2BI 137 [ v1 ]) (not:VNx2BI (reg/v:VNx2BI 137 [ v1 ])))
to:
(const_vector:VNx2BI repeat [ (const_int 1 [0x1]) ])
The similar optimization like VMANDN has enabled already. There should
be no difference execpt the operator when compare the VMORN and VMANDN
for such kind of optimization. The patch aligns the IOR MODE_CLASS condition
of the simplification to the AND operator.
gcc/ChangeLog:
* simplify-rtx.cc (simplify_context::simplify_binary_operation_1):
Align IOR (A | (~A) -> -1) optimization MODE_CLASS condition to AND.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/base/mask_insn_shortcut.c: Update check
condition.
* gcc.target/riscv/simplify_ior_optimization.c: New test.
Signed-off-by: Pan Li <pan2...@intel.com>
---
gcc/simplify-rtx.cc | 4 +-
.../riscv/rvv/base/mask_insn_shortcut.c | 3 +-
.../riscv/simplify_ior_optimization.c | 50 +++++++++++++++++++
3 files changed, 53 insertions(+), 4 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/riscv/simplify_ior_optimization.c
diff --git a/gcc/simplify-rtx.cc b/gcc/simplify-rtx.cc
index c57ff3320ee..d4aeebc7a5f 100644
--- a/gcc/simplify-rtx.cc
+++ b/gcc/simplify-rtx.cc
@@ -3370,8 +3370,8 @@ simplify_context::simplify_binary_operation_1 (rtx_code
code,
if (((GET_CODE (op0) == NOT && rtx_equal_p (XEXP (op0, 0), op1))
|| (GET_CODE (op1) == NOT && rtx_equal_p (XEXP (op1, 0), op0)))
&& ! side_effects_p (op0)
- && SCALAR_INT_MODE_P (mode))
- return constm1_rtx;
+ && GET_MODE_CLASS (mode) != MODE_CC)
+ return CONSTM1_RTX (mode);
/* (ior A C) is C if all bits of A that might be nonzero are on in C. */
if (CONST_INT_P (op1)
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/mask_insn_shortcut.c
b/gcc/testsuite/gcc.target/riscv/rvv/base/mask_insn_shortcut.c
index 83cc4a1b5a5..57d0241675a 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/base/mask_insn_shortcut.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/mask_insn_shortcut.c
@@ -233,9 +233,8 @@ vbool64_t test_shortcut_for_riscv_vmxnor_case_6(vbool64_t
v1, size_t vl) {
/* { dg-final { scan-assembler-not {vmxor\.mm\s+v[0-9]+,\s*v[0-9]+} } } */
/* { dg-final { scan-assembler-not {vmor\.mm\s+v[0-9]+,\s*v[0-9]+} } } */
/* { dg-final { scan-assembler-not {vmnor\.mm\s+v[0-9]+,\s*v[0-9]+} } } */
-/* { dg-final { scan-assembler-times
{vmorn\.mm\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 7 } } */
/* { dg-final { scan-assembler-not {vmxnor\.mm\s+v[0-9]+,\s*v[0-9]+} } } */
/* { dg-final { scan-assembler-times {vmclr\.m\s+v[0-9]+} 14 } } */
-/* { dg-final { scan-assembler-times {vmset\.m\s+v[0-9]+} 7 } } */
+/* { dg-final { scan-assembler-times {vmset\.m\s+v[0-9]+} 14 } } */
/* { dg-final { scan-assembler-times {vmmv\.m\s+v[0-9]+,\s*v[0-9]+} 14 } } */
/* { dg-final { scan-assembler-times {vmnot\.m\s+v[0-9]+,\s*v[0-9]+} 14 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/simplify_ior_optimization.c
b/gcc/testsuite/gcc.target/riscv/simplify_ior_optimization.c
new file mode 100644
index 00000000000..ec3bd0baf03
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/simplify_ior_optimization.c
@@ -0,0 +1,50 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc -mabi=lp64 -O2" } */
+
+#include <stdint.h>
+
+uint8_t test_simplify_ior_scalar_case_0 (uint8_t a)
+{
+ return a | ~a;
+}
+
+uint16_t test_simplify_ior_scalar_case_1 (uint16_t a)
+{
+ return a | ~a;
+}
+
+uint32_t test_simplify_ior_scalar_case_2 (uint32_t a)
+{
+ return a | ~a;
+}
+
+uint64_t test_simplify_ior_scalar_case_3 (uint64_t a)
+{
+ return a | ~a;
+}
+
+int8_t test_simplify_ior_scalar_case_4 (int8_t a)
+{
+ return a | ~a;
+}
+
+int16_t test_simplify_ior_scalar_case_5 (int16_t a)
+{
+ return a | ~a;
+}
+
+int32_t test_simplify_ior_scalar_case_6 (int32_t a)
+{
+ return a | ~a;
+}
+
+int64_t test_simplify_ior_scalar_case_7 (int64_t a)
+{
+ return a | ~a;
+}
+
+/* { dg-final { scan-assembler-times {li\s+a[0-9]+,\s*-1} 6 } } */
+/* { dg-final { scan-assembler-times {li\s+a[0-9]+,\s*255} 1 } } */
+/* { dg-final { scan-assembler-times {li\s+a[0-9]+,\s*65536} 1 } } */
+/* { dg-final { scan-assembler-not {or\s+a[0-9]+} } } */
+/* { dg-final { scan-assembler-not {not\s+a[0-9]+} } } */
--
2.34.1
