When some RVV integer compare operators act on the same vector registers
without mask. They can be simplified to VMSET.
This PATCH allows the eq, le, leu, ge, geu to perform such kind of the
simplification by adding one macro in riscv for simplify rtx.
Given we have:
vbool1_t test_shortcut_for_riscv_vmseq_case_0(vint8m8_t v1, size_t vl)
{
return __riscv_vmseq_vv_i8m8_b1(v1, v1, vl);
}
Before this patch:
vsetvli zero,a2,e8,m8,ta,ma
vl8re8.v v8,0(a1)
vmseq.vv v8,v8,v8
vsetvli a5,zero,e8,m8,ta,ma
vsm.v v8,0(a0)
ret
After this patch:
vsetvli zero,a2,e8,m8,ta,ma
vmset.m v1 <- optimized to vmset.m
vsetvli a5,zero,e8,m8,ta,ma
vsm.v v1,0(a0)
ret
As above, we may have one instruction eliminated and require less vector
registers.
Signed-off-by: Pan Li <pan2.li@intel.com>
gcc/ChangeLog:
* config/riscv/riscv.h (VECTOR_STORE_FLAG_VALUE): Add new macro
consumed by simplify_rtx.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/base/integer_compare_insn_shortcut.c:
Adjust test check condition.
#define DWARF_REG_TO_UNWIND_COLUMN(REGNO) \
((REGNO == RISCV_DWARF_VLENB) ? (FIRST_PSEUDO_REGISTER + 1) : REGNO)
+/* Like s390, riscv also defined this macro for the vector comparision. Then
+ the simplify-rtx relational_result will canonicalize the result to the
+ CONST1_RTX for the simplification. */
+#define VECTOR_STORE_FLAG_VALUE(MODE) CONSTM1_RTX (GET_MODE_INNER (MODE))
+
#endif /* ! GCC_RISCV_H */
return __riscv_vmsgeu_vv_u8mf8_b64(v1, v1, vl);
}
-/* { dg-final { scan-assembler-times {vmseq\.vv\sv[0-9],\s*v[0-9],\s*v[0-9]} 7 } } */
-/* { dg-final { scan-assembler-times {vmsle\.vv\sv[0-9],\s*v[0-9],\s*v[0-9]} 7 } } */
-/* { dg-final { scan-assembler-times {vmsleu\.vv\sv[0-9],\s*v[0-9],\s*v[0-9]} 7 } } */
-/* { dg-final { scan-assembler-times {vmsge\.vv\sv[0-9],\s*v[0-9],\s*v[0-9]} 7 } } */
-/* { dg-final { scan-assembler-times {vmsgeu\.vv\sv[0-9],\s*v[0-9],\s*v[0-9]} 7 } } */
/* { dg-final { scan-assembler-times {vmclr\.m\sv[0-9]} 35 } } */
+/* { dg-final { scan-assembler-times {vmset\.m\sv[0-9]} 35 } } */