RISC-V: Fix VSETVL PASS regression
Checks
| Context |
Check |
Description |
| rivoscibot/toolchain-ci-rivos-apply-patch |
success
|
Patch applied
|
| rivoscibot/toolchain-ci-rivos-lint |
success
|
Lint passed
|
| rivoscibot/toolchain-ci-rivos-build--newlib-rv64gcv-lp64d-multilib |
success
|
Build passed
|
| rivoscibot/toolchain-ci-rivos-build--linux-rv64gcv-lp64d-multilib |
success
|
Build passed
|
| linaro-tcwg-bot/tcwg_gcc_build--master-arm |
success
|
Testing passed
|
| rivoscibot/toolchain-ci-rivos-build--newlib-rv64gc-lp64d-multilib |
success
|
Build passed
|
| rivoscibot/toolchain-ci-rivos-build--linux-rv32gc_zba_zbb_zbc_zbs-ilp32d-non-multilib |
success
|
Build passed
|
| rivoscibot/toolchain-ci-rivos-build--linux-rv64gc_zba_zbb_zbc_zbs-lp64d-non-multilib |
success
|
Build passed
|
| linaro-tcwg-bot/tcwg_gcc_check--master-arm |
success
|
Testing passed
|
| rivoscibot/toolchain-ci-rivos-test |
success
|
Testing passed
|
| linaro-tcwg-bot/tcwg_gcc_build--master-aarch64 |
warning
|
Patch is already merged
|
Commit Message
This patch fix 2 regression (one is bug regression, the other is performance regression).
Those 2 regressions are both we are comparing ratio for same AVL in wrong place.
1. BUG regression:
avl_single-84.c:
f0:
li a5,999424
add a1,a1,a5
li a4,299008
add a5,a0,a5
addi a3,a4,992
addi a5,a5,576
addi a1,a1,576
vsetvli a4,zero,e8,m2,ta,ma
add a0,a0,a3
vlm.v v1,0(a5)
vsm.v v1,0(a1)
vl1re64.v v1,0(a0)
beq a2,zero,.L10
li a5,0
vsetvli zero,zero,e64,m1,tu,ma ---> This is totally incorrect since the ratio above is 4, wheras it is demanding ratio = 64 here.
.L3:
fcvt.d.lu fa5,a5
addi a5,a5,1
fadd.d fa5,fa5,fa0
vfmv.s.f v1,fa5
bne a5,a2,.L3
vfmv.f.s fa0,v1
ret
.L10:
vsetvli zero,zero,e64,m1,ta,ma
vfmv.f.s fa0,v1
ret
2. Performance regression:
before this patch:
vsetvli a5,a4,e8,m1,ta,ma
vsetvli zero,a5,e32,m1,tu,ma
vmv.s.x v2,zero
vmv.s.x v1,zero
vsetvli zero,a5,e32,m4,tu,ma
vle32.v v4,0(a1)
vfmul.vv v4,v4,v4
vfredosum.vs v1,v4,v2
vfmv.f.s fa5,v1
fsw fa5,0(a0)
sub a4,a4,a5
bne a4,zero,.L2
ret
After this patch:
vsetvli a5,a4,e32,m4,tu,ma
vle32.v v4,0(a1)
vmv.s.x v2,zero
vmv.s.x v1,zero
vfmul.vv v4,v4,v4
vfredosum.vs v1,v4,v2
vfmv.f.s fa5,v1
fsw fa5,0(a0)
sub a4,a4,a5
bne a4,zero,.L2
ret
Tested rv64gcv_zvfh_zfh passed no regression.
zvl256b/zvl512b/zvl1024b/zve64d is runing.
PR target/112776
gcc/ChangeLog:
* config/riscv/riscv-vsetvl.cc (pre_vsetvl::pre_global_vsetvl_info): Fix ratio.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/vsetvl/avl_single-84.c: Adapt test.
* gcc.target/riscv/rvv/vsetvl/pr111037-3.c: Ditto.
* gcc.target/riscv/rvv/vsetvl/pr112776.c: New test.
---
gcc/config/riscv/riscv-vsetvl.cc | 13 ++++---
.../riscv/rvv/vsetvl/avl_single-84.c | 6 ++--
.../gcc.target/riscv/rvv/vsetvl/pr111037-3.c | 2 +-
.../gcc.target/riscv/rvv/vsetvl/pr112776.c | 36 +++++++++++++++++++
4 files changed, 46 insertions(+), 11 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/pr112776.c
Comments
All regressions (zve64d/zvl128b/zvl256b/zvl512b/zvl1024b) passed.
juzhe.zhong@rivai.ai
From: Juzhe-Zhong
Date: 2023-12-01 08:51
To: gcc-patches
CC: kito.cheng; kito.cheng; jeffreyalaw; rdapp.gcc; Juzhe-Zhong
Subject: [PATCH] RISC-V: Fix VSETVL PASS regression
This patch fix 2 regression (one is bug regression, the other is performance regression).
Those 2 regressions are both we are comparing ratio for same AVL in wrong place.
1. BUG regression:
avl_single-84.c:
f0:
li a5,999424
add a1,a1,a5
li a4,299008
add a5,a0,a5
addi a3,a4,992
addi a5,a5,576
addi a1,a1,576
vsetvli a4,zero,e8,m2,ta,ma
add a0,a0,a3
vlm.v v1,0(a5)
vsm.v v1,0(a1)
vl1re64.v v1,0(a0)
beq a2,zero,.L10
li a5,0
vsetvli zero,zero,e64,m1,tu,ma ---> This is totally incorrect since the ratio above is 4, wheras it is demanding ratio = 64 here.
.L3:
fcvt.d.lu fa5,a5
addi a5,a5,1
fadd.d fa5,fa5,fa0
vfmv.s.f v1,fa5
bne a5,a2,.L3
vfmv.f.s fa0,v1
ret
.L10:
vsetvli zero,zero,e64,m1,ta,ma
vfmv.f.s fa0,v1
ret
2. Performance regression:
before this patch:
vsetvli a5,a4,e8,m1,ta,ma
vsetvli zero,a5,e32,m1,tu,ma
vmv.s.x v2,zero
vmv.s.x v1,zero
vsetvli zero,a5,e32,m4,tu,ma
vle32.v v4,0(a1)
vfmul.vv v4,v4,v4
vfredosum.vs v1,v4,v2
vfmv.f.s fa5,v1
fsw fa5,0(a0)
sub a4,a4,a5
bne a4,zero,.L2
ret
After this patch:
vsetvli a5,a4,e32,m4,tu,ma
vle32.v v4,0(a1)
vmv.s.x v2,zero
vmv.s.x v1,zero
vfmul.vv v4,v4,v4
vfredosum.vs v1,v4,v2
vfmv.f.s fa5,v1
fsw fa5,0(a0)
sub a4,a4,a5
bne a4,zero,.L2
ret
Tested rv64gcv_zvfh_zfh passed no regression.
zvl256b/zvl512b/zvl1024b/zve64d is runing.
PR target/112776
gcc/ChangeLog:
* config/riscv/riscv-vsetvl.cc (pre_vsetvl::pre_global_vsetvl_info): Fix ratio.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/vsetvl/avl_single-84.c: Adapt test.
* gcc.target/riscv/rvv/vsetvl/pr111037-3.c: Ditto.
* gcc.target/riscv/rvv/vsetvl/pr112776.c: New test.
---
gcc/config/riscv/riscv-vsetvl.cc | 13 ++++---
.../riscv/rvv/vsetvl/avl_single-84.c | 6 ++--
.../gcc.target/riscv/rvv/vsetvl/pr111037-3.c | 2 +-
.../gcc.target/riscv/rvv/vsetvl/pr112776.c | 36 +++++++++++++++++++
4 files changed, 46 insertions(+), 11 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/pr112776.c
diff --git a/gcc/config/riscv/riscv-vsetvl.cc b/gcc/config/riscv/riscv-vsetvl.cc
index b3e07d4c3aa..1da95daeeb0 100644
--- a/gcc/config/riscv/riscv-vsetvl.cc
+++ b/gcc/config/riscv/riscv-vsetvl.cc
@@ -1497,9 +1497,6 @@ private:
{
gcc_assert (prev.valid_p () && next.valid_p ());
- if (prev.get_ratio () != next.get_ratio ())
- return false;
-
if (next.has_vl () && next.vl_used_by_non_rvv_insn_p ())
return false;
@@ -2188,7 +2185,7 @@ private:
return true;
}
- bool preds_has_same_avl_p (const vsetvl_info &curr_info)
+ bool preds_all_same_avl_and_ratio_p (const vsetvl_info &curr_info)
{
gcc_assert (
!bitmap_empty_p (m_vsetvl_def_in[curr_info.get_bb ()->index ()]));
@@ -2200,7 +2197,8 @@ private:
{
const vsetvl_info &prev_info = *m_vsetvl_def_exprs[expr_index];
if (!prev_info.valid_p ()
- || !m_dem.avl_available_p (prev_info, curr_info))
+ || !m_dem.avl_available_p (prev_info, curr_info)
+ || prev_info.get_ratio () != curr_info.get_ratio ())
return false;
}
@@ -3171,7 +3169,7 @@ pre_vsetvl::pre_global_vsetvl_info ()
curr_info = block_info.local_infos[0];
}
if (curr_info.valid_p () && !curr_info.vl_used_by_non_rvv_insn_p ()
- && preds_has_same_avl_p (curr_info))
+ && preds_all_same_avl_and_ratio_p (curr_info))
curr_info.set_change_vtype_only ();
vsetvl_info prev_info = vsetvl_info ();
@@ -3179,7 +3177,8 @@ pre_vsetvl::pre_global_vsetvl_info ()
for (auto &curr_info : block_info.local_infos)
{
if (prev_info.valid_p () && curr_info.valid_p ()
- && m_dem.avl_available_p (prev_info, curr_info))
+ && m_dem.avl_available_p (prev_info, curr_info)
+ && prev_info.get_ratio () == curr_info.get_ratio ())
curr_info.set_change_vtype_only ();
prev_info = curr_info;
}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/avl_single-84.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/avl_single-84.c
index a584dd97dc0..5cd0f285029 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/avl_single-84.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/avl_single-84.c
@@ -17,6 +17,6 @@ double f0 (int8_t * restrict in, int8_t * restrict out, int n, int m, unsigned c
}
/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-Oz" no-opts "-O1" no-opts "-g" no-opts "-funroll-loops" } } } } */
-/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*zero,\s*e64,\s*m1,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-Oz" no-opts "-O1" no-opts "-g" no-opts "-funroll-loops" } } } } */
-/* { dg-final { scan-assembler-times {vsetvli} 3 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-Oz" no-opts "-g" no-opts "-funroll-loops" } } } } */
-
+/* { dg-final { scan-assembler-not {vsetvli\s+zero,\s*zero} { target { no-opts "-O0" no-opts "-Os" no-opts "-Oz" no-opts "-O1" no-opts "-g" no-opts "-funroll-loops" } } } } */
+/* { dg-final { scan-assembler-times {vsetvli} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-Oz" no-opts "-g" no-opts "-funroll-loops" } } } } */
+/* { dg-final { scan-assembler-times {vsetivli} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-Oz" no-opts "-g" no-opts "-funroll-loops" } } } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/pr111037-3.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/pr111037-3.c
index 0f40642c8b6..13344ecdd3b 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/pr111037-3.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/pr111037-3.c
@@ -13,4 +13,4 @@ void foo(_Float16 y, int16_t z, int64_t *i64p)
}
/* { dg-final { scan-assembler-times {vsetivli\s+zero,\s*1,\s*e64,\s*m1,\s*t[au],\s*m[au]} 1 } } */
-/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*zero,\s*e16,\s*m1,\s*t[au],\s*m[au]} 1 } } */
+/* { dg-final { scan-assembler-times {vsetivli\s+zero,\s*1,\s*e16,\s*m1,\s*t[au],\s*m[au]} 1 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/pr112776.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/pr112776.c
new file mode 100644
index 00000000000..853690178ac
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/pr112776.c
@@ -0,0 +1,36 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+void
+foo (float *r, const float *x)
+{
+ int i, k;
+
+ vfloat32m4_t x_vec;
+ vfloat32m4_t x_forward_vec;
+ vfloat32m4_t temp_vec;
+ vfloat32m1_t dst_vec;
+ vfloat32m1_t src_vec;
+
+ float result = 0.0f;
+ float shift_prev = 0.0f;
+
+ size_t n = 64;
+ for (size_t vl; n > 0; n -= vl)
+ {
+ vl = __riscv_vsetvl_e32m4 (n);
+ x_vec = __riscv_vle32_v_f32m4 (&x[0], vl);
+ x_forward_vec = __riscv_vle32_v_f32m4 (&x[0], vl);
+ temp_vec = __riscv_vfmul_vv_f32m4 (x_vec, x_forward_vec, vl);
+ src_vec = __riscv_vfmv_s_tu (src_vec, 0.0f, vl);
+ dst_vec = __riscv_vfmv_s_tu (dst_vec, 0.0f, vl);
+ dst_vec = __riscv_vfredosum_tu (dst_vec, temp_vec, src_vec, vl);
+ r[0] = __riscv_vfmv_f_s_f32m1_f32 (dst_vec);
+ }
+}
+
+/* { dg-final { scan-assembler-times {vsetvli} 1 } } */
+/* { dg-final { scan-assembler-not {vsetivli} } } */
+/* { dg-final { scan-assembler-times {vsetvli\t[a-x0-9]+,\s*[a-x0-9]+,\s*e32,\s*m4,\s*tu,\s*m[au]} 1 } } */
--
2.36.3
@@ -1497,9 +1497,6 @@ private:
{
gcc_assert (prev.valid_p () && next.valid_p ());
- if (prev.get_ratio () != next.get_ratio ())
- return false;
-
if (next.has_vl () && next.vl_used_by_non_rvv_insn_p ())
return false;
@@ -2188,7 +2185,7 @@ private:
return true;
}
- bool preds_has_same_avl_p (const vsetvl_info &curr_info)
+ bool preds_all_same_avl_and_ratio_p (const vsetvl_info &curr_info)
{
gcc_assert (
!bitmap_empty_p (m_vsetvl_def_in[curr_info.get_bb ()->index ()]));
@@ -2200,7 +2197,8 @@ private:
{
const vsetvl_info &prev_info = *m_vsetvl_def_exprs[expr_index];
if (!prev_info.valid_p ()
- || !m_dem.avl_available_p (prev_info, curr_info))
+ || !m_dem.avl_available_p (prev_info, curr_info)
+ || prev_info.get_ratio () != curr_info.get_ratio ())
return false;
}
@@ -3171,7 +3169,7 @@ pre_vsetvl::pre_global_vsetvl_info ()
curr_info = block_info.local_infos[0];
}
if (curr_info.valid_p () && !curr_info.vl_used_by_non_rvv_insn_p ()
- && preds_has_same_avl_p (curr_info))
+ && preds_all_same_avl_and_ratio_p (curr_info))
curr_info.set_change_vtype_only ();
vsetvl_info prev_info = vsetvl_info ();
@@ -3179,7 +3177,8 @@ pre_vsetvl::pre_global_vsetvl_info ()
for (auto &curr_info : block_info.local_infos)
{
if (prev_info.valid_p () && curr_info.valid_p ()
- && m_dem.avl_available_p (prev_info, curr_info))
+ && m_dem.avl_available_p (prev_info, curr_info)
+ && prev_info.get_ratio () == curr_info.get_ratio ())
curr_info.set_change_vtype_only ();
prev_info = curr_info;
}
@@ -17,6 +17,6 @@ double f0 (int8_t * restrict in, int8_t * restrict out, int n, int m, unsigned c
}
/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-Oz" no-opts "-O1" no-opts "-g" no-opts "-funroll-loops" } } } } */
-/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*zero,\s*e64,\s*m1,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-Oz" no-opts "-O1" no-opts "-g" no-opts "-funroll-loops" } } } } */
-/* { dg-final { scan-assembler-times {vsetvli} 3 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-Oz" no-opts "-g" no-opts "-funroll-loops" } } } } */
-
+/* { dg-final { scan-assembler-not {vsetvli\s+zero,\s*zero} { target { no-opts "-O0" no-opts "-Os" no-opts "-Oz" no-opts "-O1" no-opts "-g" no-opts "-funroll-loops" } } } } */
+/* { dg-final { scan-assembler-times {vsetvli} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-Oz" no-opts "-g" no-opts "-funroll-loops" } } } } */
+/* { dg-final { scan-assembler-times {vsetivli} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-Oz" no-opts "-g" no-opts "-funroll-loops" } } } } */
@@ -13,4 +13,4 @@ void foo(_Float16 y, int16_t z, int64_t *i64p)
}
/* { dg-final { scan-assembler-times {vsetivli\s+zero,\s*1,\s*e64,\s*m1,\s*t[au],\s*m[au]} 1 } } */
-/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*zero,\s*e16,\s*m1,\s*t[au],\s*m[au]} 1 } } */
+/* { dg-final { scan-assembler-times {vsetivli\s+zero,\s*1,\s*e16,\s*m1,\s*t[au],\s*m[au]} 1 } } */
new file mode 100644
@@ -0,0 +1,36 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+void
+foo (float *r, const float *x)
+{
+ int i, k;
+
+ vfloat32m4_t x_vec;
+ vfloat32m4_t x_forward_vec;
+ vfloat32m4_t temp_vec;
+ vfloat32m1_t dst_vec;
+ vfloat32m1_t src_vec;
+
+ float result = 0.0f;
+ float shift_prev = 0.0f;
+
+ size_t n = 64;
+ for (size_t vl; n > 0; n -= vl)
+ {
+ vl = __riscv_vsetvl_e32m4 (n);
+ x_vec = __riscv_vle32_v_f32m4 (&x[0], vl);
+ x_forward_vec = __riscv_vle32_v_f32m4 (&x[0], vl);
+ temp_vec = __riscv_vfmul_vv_f32m4 (x_vec, x_forward_vec, vl);
+ src_vec = __riscv_vfmv_s_tu (src_vec, 0.0f, vl);
+ dst_vec = __riscv_vfmv_s_tu (dst_vec, 0.0f, vl);
+ dst_vec = __riscv_vfredosum_tu (dst_vec, temp_vec, src_vec, vl);
+ r[0] = __riscv_vfmv_f_s_f32m1_f32 (dst_vec);
+ }
+}
+
+/* { dg-final { scan-assembler-times {vsetvli} 1 } } */
+/* { dg-final { scan-assembler-not {vsetivli} } } */
+/* { dg-final { scan-assembler-times {vsetvli\t[a-x0-9]+,\s*[a-x0-9]+,\s*e32,\s*m4,\s*tu,\s*m[au]} 1 } } */