This patch fixes the following inefficient vectorized codes:
vsetvli a5,zero,e8,mf2,ta,ma
li a2,17
vid.v v1
li a4,-32768
vsetvli zero,zero,e16,m1,ta,ma
addiw a4,a4,104
vmv.v.i v3,15
lui a1,%hi(a)
li a0,19
vsetvli zero,zero,e8,mf2,ta,ma
vadd.vx v1,v1,a2
sb a0,%lo(a)(a1)
vsetvli zero,zero,e16,m1,ta,ma
vzext.vf2 v2,v1
vmv.v.x v1,a4
vminu.vv v2,v2,v3
vsrl.vv v1,v1,v2
vslidedown.vi v1,v1,1
vmv.x.s a0,v1
snez a0,a0
ret
The reason is scalar_to_vec_cost is too low.
Consider in VEC_SET, we always have a slide + scalar move instruction,
scalar_to_vec_cost = 1 (current cost) is not reasonable.
I tried to set it as 2 but failed fix this case, that is, I need to
set it as 3 to fix this case.
No matter scalar move or slide instruction, I believe they are more costly
than normal vector instructions (e.g. vadd.vv). So set it as 3 looks reasonable
to me.
After this patch:
lui a5,%hi(a)
li a4,19
sb a4,%lo(a)(a5)
li a0,0
ret
Tested on both RV32/RV64 no regression, Ok for trunk ?
PR target/113281
gcc/ChangeLog:
* config/riscv/riscv.cc: Set scalar_to_vec_cost as 3.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/pr113209.c: Adapt test.
* gcc.dg/vect/costmodel/riscv/rvv/pr113281-1.c: New test.
---
gcc/config/riscv/riscv.cc | 4 ++--
.../vect/costmodel/riscv/rvv/pr113281-1.c | 18 ++++++++++++++++++
.../gcc.target/riscv/rvv/autovec/pr113209.c | 2 +-
3 files changed, 21 insertions(+), 3 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113281-1.c
diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index df9799d9c5e..bcfb3c15a39 100644
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -366,7 +366,7 @@ static const common_vector_cost rvv_vls_vector_cost = {
1, /* gather_load_cost */
1, /* scatter_store_cost */
1, /* vec_to_scalar_cost */
- 1, /* scalar_to_vec_cost */
+ 3, /* scalar_to_vec_cost */
1, /* permute_cost */
1, /* align_load_cost */
1, /* align_store_cost */
@@ -382,7 +382,7 @@ static const scalable_vector_cost rvv_vla_vector_cost = {
1, /* gather_load_cost */
1, /* scatter_store_cost */
1, /* vec_to_scalar_cost */
- 1, /* scalar_to_vec_cost */
+ 3, /* scalar_to_vec_cost */
1, /* permute_cost */
1, /* align_load_cost */
1, /* align_store_cost */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113281-1.c
b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113281-1.c
new file mode 100644
index 00000000000..331cf961a1f
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113281-1.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl256b -mabi=lp64d -O3 -ftree-vectorize
-fdump-tree-vect-details" } */
+
+unsigned char a;
+
+int main() {
+ short b = a = 0;
+ for (; a != 19; a++)
+ if (a)
+ b = 32872 >> a;
+
+ if (b == 0)
+ return 0;
+ else
+ return 1;
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 0 loops" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr113209.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr113209.c
index 081ee369394..70aae151000 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr113209.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr113209.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-march=rv64gcv_zvl256b -mabi=lp64d -O3" } */
+/* { dg-options "-march=rv64gcv_zvl256b -mabi=lp64d -O3 -fno-vect-cost-model"
} */
int b, c, d, f, i, a;
int e[1] = {0};
--
2.36.3
