[v1] RISC-V: Add test cases for RVV FP16 undefined and vlmul trunc

  From: Pan Li <pan2.li@intel.com>

This patch would like to add more tests for RVV FP16 undef and vlmul
trunc, aka

__riscv_vundefined_f16*();
__riscv_vlmul_trunc_v_f16*_f16*();

From the user's perspective, it is reasonable to do above operation
when only ZVFHMIN is enabled. This patch would like to add new test
cases to make sure the RVV FP16 vreinterpret works well as expected.

Signed-off-by: Pan Li <pan2.li@intel.com>

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c: Add test cases.
	* gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c: Ditto.
---
 .../riscv/rvv/base/zvfh-over-zvfhmin.c        | 28 ++++++--
 .../riscv/rvv/base/zvfhmin-intrinsic.c        | 66 +++++++++++++++----
 2 files changed, 78 insertions(+), 16 deletions(-)
  

LGTM.



juzhe.zhong@rivai.ai
 
From: pan2.li
Date: 2023-06-12 10:57
To: gcc-patches
CC: juzhe.zhong; rdapp.gcc; jeffreyalaw; pan2.li; yanzhang.wang; kito.cheng
Subject: [PATCH v1] RISC-V: Add test cases for RVV FP16 undefined and vlmul trunc
From: Pan Li <pan2.li@intel.com>
 
This patch would like to add more tests for RVV FP16 undef and vlmul
trunc, aka
 
__riscv_vundefined_f16*();
__riscv_vlmul_trunc_v_f16*_f16*();
 
From the user's perspective, it is reasonable to do above operation
when only ZVFHMIN is enabled. This patch would like to add new test
cases to make sure the RVV FP16 vreinterpret works well as expected.
 
Signed-off-by: Pan Li <pan2.li@intel.com>
 
gcc/testsuite/ChangeLog:
 
* gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c: Add test cases.
* gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c: Ditto.
---
.../riscv/rvv/base/zvfh-over-zvfhmin.c        | 28 ++++++--
.../riscv/rvv/base/zvfhmin-intrinsic.c        | 66 +++++++++++++++----
2 files changed, 78 insertions(+), 16 deletions(-)
 
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c b/gcc/testsuite/gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c
index ff9e0156a68..c3ed4191a36 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c
@@ -45,15 +45,33 @@ vfloat16m8_t test_vlmul_ext_v_f16mf4_f16m8(vfloat16mf4_t op1) {
   return __riscv_vlmul_ext_v_f16mf4_f16m8(op1);
}
+vfloat16mf4_t test_vlmul_trunc_v_f16mf2_f16mf4(vfloat16mf2_t op1) {
+  return __riscv_vlmul_trunc_v_f16mf2_f16mf4(op1);
+}
+
+vfloat16m4_t test_vlmul_trunc_v_f16m8_f16m4(vfloat16m8_t op1) {
+  return __riscv_vlmul_trunc_v_f16m8_f16m4(op1);
+}
+
+vfloat16mf4_t test_vundefined_f16mf4() {
+  return __riscv_vundefined_f16mf4();
+}
+
+vfloat16m8_t test_vundefined_f16m8() {
+  return __riscv_vundefined_f16m8();
+}
+
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m4,\s*t[au],\s*m[au]} 2 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m8,\s*t[au],\s*m[au]} 1 } } */
-/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 6 } } */
-/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 1 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 8 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 2 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*m8,\s*t[au],\s*m[au]} 1 } } */
/* { dg-final { scan-assembler-times {vfwcvt\.f\.f\.v\s+v[0-9]+,\s*v[0-9]+} 2 } } */
/* { dg-final { scan-assembler-times {vfncvt\.f\.f\.w\s+v[0-9]+,\s*v[0-9]+} 2 } } */
-/* { dg-final { scan-assembler-times {vle16\.v\s+v[0-9]+,\s*0\([0-9ax]+\)} 6 } } */
-/* { dg-final { scan-assembler-times {vse16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
+/* { dg-final { scan-assembler-times {vle16\.v\s+v[0-9]+,\s*0\([0-9ax]+\)} 7 } } */
+/* { dg-final { scan-assembler-times {vse16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 6 } } */
+/* { dg-final { scan-assembler-times {vl4re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 1 } } */
/* { dg-final { scan-assembler-times {vl8re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 1 } } */
-/* { dg-final { scan-assembler-times {vs8r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
+/* { dg-final { scan-assembler-times {vs4r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 1 } } */
+/* { dg-final { scan-assembler-times {vs8r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 5 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c b/gcc/testsuite/gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c
index 68720e64926..8d39a2ed4c2 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c
@@ -121,26 +121,70 @@ vfloat16m8_t test_vlmul_ext_v_f16mf4_f16m8(vfloat16mf4_t op1) {
   return __riscv_vlmul_ext_v_f16mf4_f16m8(op1);
}
+vfloat16mf4_t test_vlmul_trunc_v_f16mf2_f16mf4(vfloat16mf2_t op1) {
+  return __riscv_vlmul_trunc_v_f16mf2_f16mf4(op1);
+}
+
+vfloat16mf4_t test_vlmul_trunc_v_f16m1_f16mf4(vfloat16m1_t op1) {
+  return __riscv_vlmul_trunc_v_f16m1_f16mf4(op1);
+}
+
+vfloat16mf2_t test_vlmul_trunc_v_f16m1_f16mf2(vfloat16m1_t op1) {
+  return __riscv_vlmul_trunc_v_f16m1_f16mf2(op1);
+}
+
+vfloat16mf4_t test_vlmul_trunc_v_f16m2_f16mf4(vfloat16m2_t op1) {
+  return __riscv_vlmul_trunc_v_f16m2_f16mf4(op1);
+}
+
+vfloat16m1_t test_vlmul_trunc_v_f16m2_f16m1(vfloat16m2_t op1) {
+  return __riscv_vlmul_trunc_v_f16m2_f16m1(op1);
+}
+
+vfloat16mf4_t test_vlmul_trunc_v_f16m4_f16mf4(vfloat16m4_t op1) {
+  return __riscv_vlmul_trunc_v_f16m4_f16mf4(op1);
+}
+
+vfloat16m2_t test_vlmul_trunc_v_f16m4_f16m2(vfloat16m4_t op1) {
+  return __riscv_vlmul_trunc_v_f16m4_f16m2(op1);
+}
+
+vfloat16mf4_t test_vlmul_trunc_v_f16m8_f16mf4(vfloat16m8_t op1) {
+  return __riscv_vlmul_trunc_v_f16m8_f16mf4(op1);
+}
+
+vfloat16m4_t test_vlmul_trunc_v_f16m8_f16m4(vfloat16m8_t op1) {
+  return __riscv_vlmul_trunc_v_f16m8_f16m4(op1);
+}
+
+vfloat16mf4_t test_vundefined_f16mf4() {
+  return __riscv_vundefined_f16mf4();
+}
+
+vfloat16m8_t test_vundefined_f16m8() {
+  return __riscv_vundefined_f16m8();
+}
+
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 2 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m1,\s*t[au],\s*m[au]} 2 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m2,\s*t[au],\s*m[au]} 2 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m4,\s*t[au],\s*m[au]} 2 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m8,\s*t[au],\s*m[au]} 1 } } */
-/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 12 } } */
-/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 4 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 18 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 6 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*m2,\s*t[au],\s*m[au]} 1 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*m4,\s*t[au],\s*m[au]} 1 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*m8,\s*t[au],\s*m[au]} 5 } } */
/* { dg-final { scan-assembler-times {vfwcvt\.f\.f\.v\s+v[0-9]+,\s*v[0-9]+} 5 } } */
/* { dg-final { scan-assembler-times {vfncvt\.f\.f\.w\s+v[0-9]+,\s*v[0-9]+} 5 } } */
-/* { dg-final { scan-assembler-times {vle16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 14 } } */
-/* { dg-final { scan-assembler-times {vse16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 8 } } */
-/* { dg-final { scan-assembler-times {vl1re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 2 } } */
-/* { dg-final { scan-assembler-times {vl2re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 2 } } */
+/* { dg-final { scan-assembler-times {vle16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 20 } } */
+/* { dg-final { scan-assembler-times {vse16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 15 } } */
+/* { dg-final { scan-assembler-times {vl1re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
+/* { dg-final { scan-assembler-times {vl2re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
/* { dg-final { scan-assembler-times {vl8re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
-/* { dg-final { scan-assembler-times {vl4re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 2 } } */
-/* { dg-final { scan-assembler-times {vs1r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
-/* { dg-final { scan-assembler-times {vs2r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
-/* { dg-final { scan-assembler-times {vs4r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
-/* { dg-final { scan-assembler-times {vs8r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 11 } } */
+/* { dg-final { scan-assembler-times {vl4re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
+/* { dg-final { scan-assembler-times {vs1r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
+/* { dg-final { scan-assembler-times {vs2r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
+/* { dg-final { scan-assembler-times {vs4r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
+/* { dg-final { scan-assembler-times {vs8r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 12 } } */
-- 
2.34.1
  

LGTM

juzhe.zhong@rivai.ai <juzhe.zhong@rivai.ai> 於 2023年6月12日 週一 10:58 寫道：

> LGTM.
>
>
>
> juzhe.zhong@rivai.ai
>
> From: pan2.li
> Date: 2023-06-12 10:57
> To: gcc-patches
> CC: juzhe.zhong; rdapp.gcc; jeffreyalaw; pan2.li; yanzhang.wang;
> kito.cheng
> Subject: [PATCH v1] RISC-V: Add test cases for RVV FP16 undefined and
> vlmul trunc
> From: Pan Li <pan2.li@intel.com>
>
> This patch would like to add more tests for RVV FP16 undef and vlmul
> trunc, aka
>
> __riscv_vundefined_f16*();
> __riscv_vlmul_trunc_v_f16*_f16*();
>
> From the user's perspective, it is reasonable to do above operation
> when only ZVFHMIN is enabled. This patch would like to add new test
> cases to make sure the RVV FP16 vreinterpret works well as expected.
>
> Signed-off-by: Pan Li <pan2.li@intel.com>
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c: Add test cases.
> * gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c: Ditto.
> ---
> .../riscv/rvv/base/zvfh-over-zvfhmin.c        | 28 ++++++--
> .../riscv/rvv/base/zvfhmin-intrinsic.c        | 66 +++++++++++++++----
> 2 files changed, 78 insertions(+), 16 deletions(-)
>
> diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c
> b/gcc/testsuite/gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c
> index ff9e0156a68..c3ed4191a36 100644
> --- a/gcc/testsuite/gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c
> +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c
> @@ -45,15 +45,33 @@ vfloat16m8_t
> test_vlmul_ext_v_f16mf4_f16m8(vfloat16mf4_t op1) {
>    return __riscv_vlmul_ext_v_f16mf4_f16m8(op1);
> }
> +vfloat16mf4_t test_vlmul_trunc_v_f16mf2_f16mf4(vfloat16mf2_t op1) {
> +  return __riscv_vlmul_trunc_v_f16mf2_f16mf4(op1);
> +}
> +
> +vfloat16m4_t test_vlmul_trunc_v_f16m8_f16m4(vfloat16m8_t op1) {
> +  return __riscv_vlmul_trunc_v_f16m8_f16m4(op1);
> +}
> +
> +vfloat16mf4_t test_vundefined_f16mf4() {
> +  return __riscv_vundefined_f16mf4();
> +}
> +
> +vfloat16m8_t test_vundefined_f16m8() {
> +  return __riscv_vundefined_f16m8();
> +}
> +
> /* { dg-final { scan-assembler-times
> {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 } } */
> /* { dg-final { scan-assembler-times
> {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m4,\s*t[au],\s*m[au]} 2 } } */
> /* { dg-final { scan-assembler-times
> {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m8,\s*t[au],\s*m[au]} 1 } } */
> -/* { dg-final { scan-assembler-times
> {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 6 } } */
> -/* { dg-final { scan-assembler-times
> {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 1 } } */
> +/* { dg-final { scan-assembler-times
> {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 8 } } */
> +/* { dg-final { scan-assembler-times
> {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 2 } } */
> /* { dg-final { scan-assembler-times
> {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*m8,\s*t[au],\s*m[au]} 1 } } */
> /* { dg-final { scan-assembler-times
> {vfwcvt\.f\.f\.v\s+v[0-9]+,\s*v[0-9]+} 2 } } */
> /* { dg-final { scan-assembler-times
> {vfncvt\.f\.f\.w\s+v[0-9]+,\s*v[0-9]+} 2 } } */
> -/* { dg-final { scan-assembler-times
> {vle16\.v\s+v[0-9]+,\s*0\([0-9ax]+\)} 6 } } */
> -/* { dg-final { scan-assembler-times
> {vse16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
> +/* { dg-final { scan-assembler-times
> {vle16\.v\s+v[0-9]+,\s*0\([0-9ax]+\)} 7 } } */
> +/* { dg-final { scan-assembler-times
> {vse16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 6 } } */
> +/* { dg-final { scan-assembler-times
> {vl4re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 1 } } */
> /* { dg-final { scan-assembler-times
> {vl8re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 1 } } */
> -/* { dg-final { scan-assembler-times
> {vs8r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
> +/* { dg-final { scan-assembler-times
> {vs4r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 1 } } */
> +/* { dg-final { scan-assembler-times
> {vs8r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 5 } } */
> diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c
> b/gcc/testsuite/gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c
> index 68720e64926..8d39a2ed4c2 100644
> --- a/gcc/testsuite/gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c
> +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c
> @@ -121,26 +121,70 @@ vfloat16m8_t
> test_vlmul_ext_v_f16mf4_f16m8(vfloat16mf4_t op1) {
>    return __riscv_vlmul_ext_v_f16mf4_f16m8(op1);
> }
> +vfloat16mf4_t test_vlmul_trunc_v_f16mf2_f16mf4(vfloat16mf2_t op1) {
> +  return __riscv_vlmul_trunc_v_f16mf2_f16mf4(op1);
> +}
> +
> +vfloat16mf4_t test_vlmul_trunc_v_f16m1_f16mf4(vfloat16m1_t op1) {
> +  return __riscv_vlmul_trunc_v_f16m1_f16mf4(op1);
> +}
> +
> +vfloat16mf2_t test_vlmul_trunc_v_f16m1_f16mf2(vfloat16m1_t op1) {
> +  return __riscv_vlmul_trunc_v_f16m1_f16mf2(op1);
> +}
> +
> +vfloat16mf4_t test_vlmul_trunc_v_f16m2_f16mf4(vfloat16m2_t op1) {
> +  return __riscv_vlmul_trunc_v_f16m2_f16mf4(op1);
> +}
> +
> +vfloat16m1_t test_vlmul_trunc_v_f16m2_f16m1(vfloat16m2_t op1) {
> +  return __riscv_vlmul_trunc_v_f16m2_f16m1(op1);
> +}
> +
> +vfloat16mf4_t test_vlmul_trunc_v_f16m4_f16mf4(vfloat16m4_t op1) {
> +  return __riscv_vlmul_trunc_v_f16m4_f16mf4(op1);
> +}
> +
> +vfloat16m2_t test_vlmul_trunc_v_f16m4_f16m2(vfloat16m4_t op1) {
> +  return __riscv_vlmul_trunc_v_f16m4_f16m2(op1);
> +}
> +
> +vfloat16mf4_t test_vlmul_trunc_v_f16m8_f16mf4(vfloat16m8_t op1) {
> +  return __riscv_vlmul_trunc_v_f16m8_f16mf4(op1);
> +}
> +
> +vfloat16m4_t test_vlmul_trunc_v_f16m8_f16m4(vfloat16m8_t op1) {
> +  return __riscv_vlmul_trunc_v_f16m8_f16m4(op1);
> +}
> +
> +vfloat16mf4_t test_vundefined_f16mf4() {
> +  return __riscv_vundefined_f16mf4();
> +}
> +
> +vfloat16m8_t test_vundefined_f16m8() {
> +  return __riscv_vundefined_f16m8();
> +}
> +
> /* { dg-final { scan-assembler-times
> {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 } } */
> /* { dg-final { scan-assembler-times
> {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 2 } } */
> /* { dg-final { scan-assembler-times
> {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m1,\s*t[au],\s*m[au]} 2 } } */
> /* { dg-final { scan-assembler-times
> {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m2,\s*t[au],\s*m[au]} 2 } } */
> /* { dg-final { scan-assembler-times
> {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m4,\s*t[au],\s*m[au]} 2 } } */
> /* { dg-final { scan-assembler-times
> {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m8,\s*t[au],\s*m[au]} 1 } } */
> -/* { dg-final { scan-assembler-times
> {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 12 } } */
> -/* { dg-final { scan-assembler-times
> {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 4 } } */
> +/* { dg-final { scan-assembler-times
> {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 18 } } */
> +/* { dg-final { scan-assembler-times
> {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 6 } } */
> /* { dg-final { scan-assembler-times
> {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*m2,\s*t[au],\s*m[au]} 1 } } */
> /* { dg-final { scan-assembler-times
> {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*m4,\s*t[au],\s*m[au]} 1 } } */
> /* { dg-final { scan-assembler-times
> {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*m8,\s*t[au],\s*m[au]} 5 } } */
> /* { dg-final { scan-assembler-times
> {vfwcvt\.f\.f\.v\s+v[0-9]+,\s*v[0-9]+} 5 } } */
> /* { dg-final { scan-assembler-times
> {vfncvt\.f\.f\.w\s+v[0-9]+,\s*v[0-9]+} 5 } } */
> -/* { dg-final { scan-assembler-times
> {vle16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 14 } } */
> -/* { dg-final { scan-assembler-times
> {vse16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 8 } } */
> -/* { dg-final { scan-assembler-times
> {vl1re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 2 } } */
> -/* { dg-final { scan-assembler-times
> {vl2re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 2 } } */
> +/* { dg-final { scan-assembler-times
> {vle16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 20 } } */
> +/* { dg-final { scan-assembler-times
> {vse16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 15 } } */
> +/* { dg-final { scan-assembler-times
> {vl1re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
> +/* { dg-final { scan-assembler-times
> {vl2re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
> /* { dg-final { scan-assembler-times
> {vl8re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
> -/* { dg-final { scan-assembler-times
> {vl4re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 2 } } */
> -/* { dg-final { scan-assembler-times
> {vs1r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
> -/* { dg-final { scan-assembler-times
> {vs2r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
> -/* { dg-final { scan-assembler-times
> {vs4r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
> -/* { dg-final { scan-assembler-times
> {vs8r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 11 } } */
> +/* { dg-final { scan-assembler-times
> {vl4re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
> +/* { dg-final { scan-assembler-times
> {vs1r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
> +/* { dg-final { scan-assembler-times
> {vs2r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
> +/* { dg-final { scan-assembler-times
> {vs4r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
> +/* { dg-final { scan-assembler-times
> {vs8r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 12 } } */
> --
> 2.34.1
>
>
>
  

Committed, thanks Kito and Juzhe.

Pan

From: Kito Cheng <kito.cheng@gmail.com>
Sent: Monday, June 12, 2023 11:32 AM
To: 钟居哲 <juzhe.zhong@rivai.ai>
Cc: Li, Pan2 <pan2.li@intel.com>; gcc-patches <gcc-patches@gcc.gnu.org>; Robin Dapp <rdapp.gcc@gmail.com>; jeffreyalaw <jeffreyalaw@gmail.com>; Wang, Yanzhang <yanzhang.wang@intel.com>
Subject: Re: [PATCH v1] RISC-V: Add test cases for RVV FP16 undefined and vlmul trunc

LGTM

juzhe.zhong@rivai.ai<mailto:juzhe.zhong@rivai.ai> <juzhe.zhong@rivai.ai<mailto:juzhe.zhong@rivai.ai>> 於 2023年6月12日 週一 10:58 寫道：
LGTM.



juzhe.zhong@rivai.ai<mailto:juzhe.zhong@rivai.ai>

From: pan2.li<http://pan2.li>
Date: 2023-06-12 10:57
To: gcc-patches
CC: juzhe.zhong; rdapp.gcc; jeffreyalaw; pan2.li<http://pan2.li>; yanzhang.wang; kito.cheng
Subject: [PATCH v1] RISC-V: Add test cases for RVV FP16 undefined and vlmul trunc
From: Pan Li <pan2.li@intel.com<mailto:pan2.li@intel.com>>

This patch would like to add more tests for RVV FP16 undef and vlmul
trunc, aka

__riscv_vundefined_f16*();
__riscv_vlmul_trunc_v_f16*_f16*();

From the user's perspective, it is reasonable to do above operation
when only ZVFHMIN is enabled. This patch would like to add new test
cases to make sure the RVV FP16 vreinterpret works well as expected.

Signed-off-by: Pan Li <pan2.li@intel.com<mailto:pan2.li@intel.com>>

gcc/testsuite/ChangeLog:

* gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c: Add test cases.
* gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c: Ditto.
---
.../riscv/rvv/base/zvfh-over-zvfhmin.c        | 28 ++++++--
.../riscv/rvv/base/zvfhmin-intrinsic.c        | 66 +++++++++++++++----
2 files changed, 78 insertions(+), 16 deletions(-)

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c b/gcc/testsuite/gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c
index ff9e0156a68..c3ed4191a36 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/zvfh-over-zvfhmin.c
@@ -45,15 +45,33 @@ vfloat16m8_t test_vlmul_ext_v_f16mf4_f16m8(vfloat16mf4_t op1) {
   return __riscv_vlmul_ext_v_f16mf4_f16m8(op1);
}
+vfloat16mf4_t test_vlmul_trunc_v_f16mf2_f16mf4(vfloat16mf2_t op1) {
+  return __riscv_vlmul_trunc_v_f16mf2_f16mf4(op1);
+}
+
+vfloat16m4_t test_vlmul_trunc_v_f16m8_f16m4(vfloat16m8_t op1) {
+  return __riscv_vlmul_trunc_v_f16m8_f16m4(op1);
+}
+
+vfloat16mf4_t test_vundefined_f16mf4() {
+  return __riscv_vundefined_f16mf4();
+}
+
+vfloat16m8_t test_vundefined_f16m8() {
+  return __riscv_vundefined_f16m8();
+}
+
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m4,\s*t[au],\s*m[au]} 2 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m8,\s*t[au],\s*m[au]} 1 } } */
-/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 6 } } */
-/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 1 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 8 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 2 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*m8,\s*t[au],\s*m[au]} 1 } } */
/* { dg-final { scan-assembler-times {vfwcvt\.f\.f\.v\s+v[0-9]+,\s*v[0-9]+} 2 } } */
/* { dg-final { scan-assembler-times {vfncvt\.f\.f\.w\s+v[0-9]+,\s*v[0-9]+} 2 } } */
-/* { dg-final { scan-assembler-times {vle16\.v\s+v[0-9]+,\s*0\([0-9ax]+\)} 6 } } */
-/* { dg-final { scan-assembler-times {vse16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
+/* { dg-final { scan-assembler-times {vle16\.v\s+v[0-9]+,\s*0\([0-9ax]+\)} 7 } } */
+/* { dg-final { scan-assembler-times {vse16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 6 } } */
+/* { dg-final { scan-assembler-times {vl4re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 1 } } */
/* { dg-final { scan-assembler-times {vl8re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 1 } } */
-/* { dg-final { scan-assembler-times {vs8r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
+/* { dg-final { scan-assembler-times {vs4r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 1 } } */
+/* { dg-final { scan-assembler-times {vs8r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 5 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c b/gcc/testsuite/gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c
index 68720e64926..8d39a2ed4c2 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/zvfhmin-intrinsic.c
@@ -121,26 +121,70 @@ vfloat16m8_t test_vlmul_ext_v_f16mf4_f16m8(vfloat16mf4_t op1) {
   return __riscv_vlmul_ext_v_f16mf4_f16m8(op1);
}
+vfloat16mf4_t test_vlmul_trunc_v_f16mf2_f16mf4(vfloat16mf2_t op1) {
+  return __riscv_vlmul_trunc_v_f16mf2_f16mf4(op1);
+}
+
+vfloat16mf4_t test_vlmul_trunc_v_f16m1_f16mf4(vfloat16m1_t op1) {
+  return __riscv_vlmul_trunc_v_f16m1_f16mf4(op1);
+}
+
+vfloat16mf2_t test_vlmul_trunc_v_f16m1_f16mf2(vfloat16m1_t op1) {
+  return __riscv_vlmul_trunc_v_f16m1_f16mf2(op1);
+}
+
+vfloat16mf4_t test_vlmul_trunc_v_f16m2_f16mf4(vfloat16m2_t op1) {
+  return __riscv_vlmul_trunc_v_f16m2_f16mf4(op1);
+}
+
+vfloat16m1_t test_vlmul_trunc_v_f16m2_f16m1(vfloat16m2_t op1) {
+  return __riscv_vlmul_trunc_v_f16m2_f16m1(op1);
+}
+
+vfloat16mf4_t test_vlmul_trunc_v_f16m4_f16mf4(vfloat16m4_t op1) {
+  return __riscv_vlmul_trunc_v_f16m4_f16mf4(op1);
+}
+
+vfloat16m2_t test_vlmul_trunc_v_f16m4_f16m2(vfloat16m4_t op1) {
+  return __riscv_vlmul_trunc_v_f16m4_f16m2(op1);
+}
+
+vfloat16mf4_t test_vlmul_trunc_v_f16m8_f16mf4(vfloat16m8_t op1) {
+  return __riscv_vlmul_trunc_v_f16m8_f16mf4(op1);
+}
+
+vfloat16m4_t test_vlmul_trunc_v_f16m8_f16m4(vfloat16m8_t op1) {
+  return __riscv_vlmul_trunc_v_f16m8_f16m4(op1);
+}
+
+vfloat16mf4_t test_vundefined_f16mf4() {
+  return __riscv_vundefined_f16mf4();
+}
+
+vfloat16m8_t test_vundefined_f16m8() {
+  return __riscv_vundefined_f16m8();
+}
+
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 2 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m1,\s*t[au],\s*m[au]} 2 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m2,\s*t[au],\s*m[au]} 2 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m4,\s*t[au],\s*m[au]} 2 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e16,\s*m8,\s*t[au],\s*m[au]} 1 } } */
-/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 12 } } */
-/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 4 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 18 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 6 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*m2,\s*t[au],\s*m[au]} 1 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*m4,\s*t[au],\s*m[au]} 1 } } */
/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*m8,\s*t[au],\s*m[au]} 5 } } */
/* { dg-final { scan-assembler-times {vfwcvt\.f\.f\.v\s+v[0-9]+,\s*v[0-9]+} 5 } } */
/* { dg-final { scan-assembler-times {vfncvt\.f\.f\.w\s+v[0-9]+,\s*v[0-9]+} 5 } } */
-/* { dg-final { scan-assembler-times {vle16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 14 } } */
-/* { dg-final { scan-assembler-times {vse16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 8 } } */
-/* { dg-final { scan-assembler-times {vl1re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 2 } } */
-/* { dg-final { scan-assembler-times {vl2re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 2 } } */
+/* { dg-final { scan-assembler-times {vle16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 20 } } */
+/* { dg-final { scan-assembler-times {vse16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 15 } } */
+/* { dg-final { scan-assembler-times {vl1re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
+/* { dg-final { scan-assembler-times {vl2re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
/* { dg-final { scan-assembler-times {vl8re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
-/* { dg-final { scan-assembler-times {vl4re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 2 } } */
-/* { dg-final { scan-assembler-times {vs1r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
-/* { dg-final { scan-assembler-times {vs2r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
-/* { dg-final { scan-assembler-times {vs4r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
-/* { dg-final { scan-assembler-times {vs8r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 11 } } */
+/* { dg-final { scan-assembler-times {vl4re16\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 3 } } */
+/* { dg-final { scan-assembler-times {vs1r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
+/* { dg-final { scan-assembler-times {vs2r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
+/* { dg-final { scan-assembler-times {vs4r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 4 } } */
+/* { dg-final { scan-assembler-times {vs8r\.v\s+v[0-9]+,\s*0\([a-x][0-9]+\)} 12 } } */
--
2.34.1