public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc r12-2848] arm/66791: Replace builtins for vdup_n and vmov_n intrinsics.
@ 2021-08-11 10:02 Prathamesh Kulkarni
0 siblings, 0 replies; only message in thread
From: Prathamesh Kulkarni @ 2021-08-11 10:02 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:b8f604da25bfe0fd4dadbc338293885819fe8018
commit r12-2848-gb8f604da25bfe0fd4dadbc338293885819fe8018
Author: prathamesh.kulkarni <prathamesh.kulkarni@linaro.org>
Date: Wed Aug 11 15:30:14 2021 +0530
arm/66791: Replace builtins for vdup_n and vmov_n intrinsics.
gcc/ChangeLog:
PR target/66791
* config/arm/arm_neon.h (vdup_n_s8): Replace call to builtin
with constructor.
(vdup_n_s16): Likewise.
(vdup_n_s32): Likewise.
(vdup_n_s64): Likewise.
(vdup_n_u8): Likewise.
(vdup_n_u16): Likewise.
(vdup_n_u32): Likewise.
(vdup_n_u64): Likewise.
(vdup_n_p8): Likewise.
(vdup_n_p16): Likewise.
(vdup_n_p64): Likewise.
(vdup_n_f16): Likewise.
(vdup_n_f32): Likewise.
(vdupq_n_s8): Likewise.
(vdupq_n_s16): Likewise.
(vdupq_n_s32): Likewise.
(vdupq_n_s64): Likewise.
(vdupq_n_u8): Likewise.
(vdupq_n_u16): Likewise.
(vdupq_n_u32): Likewise.
(vdupq_n_u64): Likewise.
(vdupq_n_p8): Likewise.
(vdupq_n_p16): Likewise.
(vdupq_n_p64): Likewise.
(vdupq_n_f16): Likewise.
(vdupq_n_f32): Likewise.
(vmov_n_s8): Replace call to builtin with call to corresponding
vdup_n intrinsic.
(vmov_n_s16): Likewise.
(vmov_n_s32): Likewise.
(vmov_n_s64): Likewise.
(vmov_n_u8): Likewise.
(vmov_n_u16): Likewise.
(vmov_n_u32): Likewise.
(vmov_n_u64): Likewise.
(vmov_n_p8): Likewise.
(vmov_n_p16): Likewise.
(vmov_n_f16): Likewise.
(vmov_n_f32): Likewise.
(vmovq_n_s8): Likewise.
(vmovq_n_s16): Likewise.
(vmovq_n_s32): Likewise.
(vmovq_n_s64): Likewise.
(vmovq_n_u8): Likewise.
(vmovq_n_u16): Likewise.
(vmovq_n_u32): Likewise.
(vmovq_n_u64): Likewise.
(vmovq_n_p8): Likewise.
(vmovq_n_p16): Likewise.
(vmovq_n_f16): Likewise.
(vmovq_n_f32): Likewise.
* config/arm/arm_neon_builtins.def: Remove entries for vdup_n.
gcc/testsuite/ChangeLog:
PR target/66791
* gcc.target/arm/pr51534.c: Adjust test.
Diff:
---
gcc/config/arm/arm_neon.h | 107 +++++++++++++++++----------------
gcc/config/arm/arm_neon_builtins.def | 3 -
gcc/testsuite/gcc.target/arm/pr51534.c | 26 +++-----
3 files changed, 63 insertions(+), 73 deletions(-)
diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index 5a91d15bf75..3364b37f69d 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -6664,63 +6664,63 @@ __extension__ extern __inline int8x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_s8 (int8_t __a)
{
- return (int8x8_t)__builtin_neon_vdup_nv8qi ((__builtin_neon_qi) __a);
+ return (int8x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}
__extension__ extern __inline int16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_s16 (int16_t __a)
{
- return (int16x4_t)__builtin_neon_vdup_nv4hi ((__builtin_neon_hi) __a);
+ return (int16x4_t) {__a, __a, __a, __a};
}
__extension__ extern __inline int32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_s32 (int32_t __a)
{
- return (int32x2_t)__builtin_neon_vdup_nv2si ((__builtin_neon_si) __a);
+ return (int32x2_t) {__a, __a};
}
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_f32 (float32_t __a)
{
- return (float32x2_t)__builtin_neon_vdup_nv2sf ((__builtin_neon_sf) __a);
+ return (float32x2_t) {__a, __a};
}
__extension__ extern __inline uint8x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_u8 (uint8_t __a)
{
- return (uint8x8_t)__builtin_neon_vdup_nv8qi ((__builtin_neon_qi) __a);
+ return (uint8x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}
__extension__ extern __inline uint16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_u16 (uint16_t __a)
{
- return (uint16x4_t)__builtin_neon_vdup_nv4hi ((__builtin_neon_hi) __a);
+ return (uint16x4_t) {__a, __a, __a, __a};
}
__extension__ extern __inline uint32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_u32 (uint32_t __a)
{
- return (uint32x2_t)__builtin_neon_vdup_nv2si ((__builtin_neon_si) __a);
+ return (uint32x2_t) {__a, __a};
}
__extension__ extern __inline poly8x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_p8 (poly8_t __a)
{
- return (poly8x8_t)__builtin_neon_vdup_nv8qi ((__builtin_neon_qi) __a);
+ return (poly8x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}
__extension__ extern __inline poly16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_p16 (poly16_t __a)
{
- return (poly16x4_t)__builtin_neon_vdup_nv4hi ((__builtin_neon_hi) __a);
+ return (poly16x4_t) {__a, __a, __a, __a};
}
#pragma GCC push_options
@@ -6729,7 +6729,7 @@ __extension__ extern __inline poly64x1_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_p64 (poly64_t __a)
{
- return (poly64x1_t)__builtin_neon_vdup_ndi ((__builtin_neon_di) __a);
+ return (poly64x1_t) {__a};
}
#pragma GCC pop_options
@@ -6737,14 +6737,14 @@ __extension__ extern __inline int64x1_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_s64 (int64_t __a)
{
- return (int64x1_t)__builtin_neon_vdup_ndi ((__builtin_neon_di) __a);
+ return (int64x1_t) {__a};
}
__extension__ extern __inline uint64x1_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_u64 (uint64_t __a)
{
- return (uint64x1_t)__builtin_neon_vdup_ndi ((__builtin_neon_di) __a);
+ return (uint64x1_t) {__a};
}
#pragma GCC push_options
@@ -6753,7 +6753,7 @@ __extension__ extern __inline poly64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_p64 (poly64_t __a)
{
- return (poly64x2_t)__builtin_neon_vdup_nv2di ((__builtin_neon_di) __a);
+ return (poly64x2_t) {__a, __a};
}
#pragma GCC pop_options
@@ -6761,231 +6761,234 @@ __extension__ extern __inline int8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_s8 (int8_t __a)
{
- return (int8x16_t)__builtin_neon_vdup_nv16qi ((__builtin_neon_qi) __a);
+ return (int8x16_t) {__a, __a, __a, __a, __a, __a, __a, __a,
+ __a, __a, __a, __a, __a, __a, __a, __a};
}
__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_s16 (int16_t __a)
{
- return (int16x8_t)__builtin_neon_vdup_nv8hi ((__builtin_neon_hi) __a);
+ return (int16x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}
__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_s32 (int32_t __a)
{
- return (int32x4_t)__builtin_neon_vdup_nv4si ((__builtin_neon_si) __a);
+ return (int32x4_t) {__a, __a, __a, __a};
}
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_f32 (float32_t __a)
{
- return (float32x4_t)__builtin_neon_vdup_nv4sf ((__builtin_neon_sf) __a);
+ return (float32x4_t) {__a, __a, __a, __a};
}
__extension__ extern __inline uint8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_u8 (uint8_t __a)
{
- return (uint8x16_t)__builtin_neon_vdup_nv16qi ((__builtin_neon_qi) __a);
+ return (uint8x16_t) {__a, __a, __a, __a, __a, __a, __a, __a,
+ __a, __a, __a, __a, __a, __a, __a, __a};
}
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_u16 (uint16_t __a)
{
- return (uint16x8_t)__builtin_neon_vdup_nv8hi ((__builtin_neon_hi) __a);
+ return (uint16x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_u32 (uint32_t __a)
{
- return (uint32x4_t)__builtin_neon_vdup_nv4si ((__builtin_neon_si) __a);
+ return (uint32x4_t) {__a, __a, __a, __a};
}
__extension__ extern __inline poly8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_p8 (poly8_t __a)
{
- return (poly8x16_t)__builtin_neon_vdup_nv16qi ((__builtin_neon_qi) __a);
+ return (poly8x16_t) {__a, __a, __a, __a, __a, __a, __a, __a,
+ __a, __a, __a, __a, __a, __a, __a, __a};
}
__extension__ extern __inline poly16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_p16 (poly16_t __a)
{
- return (poly16x8_t)__builtin_neon_vdup_nv8hi ((__builtin_neon_hi) __a);
+ return (poly16x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}
__extension__ extern __inline int64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_s64 (int64_t __a)
{
- return (int64x2_t)__builtin_neon_vdup_nv2di ((__builtin_neon_di) __a);
+ return (int64x2_t) {__a, __a};
}
__extension__ extern __inline uint64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_u64 (uint64_t __a)
{
- return (uint64x2_t)__builtin_neon_vdup_nv2di ((__builtin_neon_di) __a);
+ return (uint64x2_t) {__a, __a};
}
__extension__ extern __inline int8x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmov_n_s8 (int8_t __a)
{
- return (int8x8_t)__builtin_neon_vdup_nv8qi ((__builtin_neon_qi) __a);
+ return vdup_n_s8 (__a);
}
__extension__ extern __inline int16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmov_n_s16 (int16_t __a)
{
- return (int16x4_t)__builtin_neon_vdup_nv4hi ((__builtin_neon_hi) __a);
+ return vdup_n_s16 (__a);
}
__extension__ extern __inline int32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmov_n_s32 (int32_t __a)
{
- return (int32x2_t)__builtin_neon_vdup_nv2si ((__builtin_neon_si) __a);
+ return vdup_n_s32 (__a);
}
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmov_n_f32 (float32_t __a)
{
- return (float32x2_t)__builtin_neon_vdup_nv2sf ((__builtin_neon_sf) __a);
+ return vdup_n_f32 (__a);
}
__extension__ extern __inline uint8x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmov_n_u8 (uint8_t __a)
{
- return (uint8x8_t)__builtin_neon_vdup_nv8qi ((__builtin_neon_qi) __a);
+ return vdup_n_u8 (__a);
}
__extension__ extern __inline uint16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmov_n_u16 (uint16_t __a)
{
- return (uint16x4_t)__builtin_neon_vdup_nv4hi ((__builtin_neon_hi) __a);
+ return vdup_n_u16 (__a);
}
__extension__ extern __inline uint32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmov_n_u32 (uint32_t __a)
{
- return (uint32x2_t)__builtin_neon_vdup_nv2si ((__builtin_neon_si) __a);
+ return vdup_n_u32 (__a);
}
__extension__ extern __inline poly8x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmov_n_p8 (poly8_t __a)
{
- return (poly8x8_t)__builtin_neon_vdup_nv8qi ((__builtin_neon_qi) __a);
+ return vdup_n_p8 (__a);
}
__extension__ extern __inline poly16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmov_n_p16 (poly16_t __a)
{
- return (poly16x4_t)__builtin_neon_vdup_nv4hi ((__builtin_neon_hi) __a);
+ return vdup_n_p16 (__a);
}
__extension__ extern __inline int64x1_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmov_n_s64 (int64_t __a)
{
- return (int64x1_t)__builtin_neon_vdup_ndi ((__builtin_neon_di) __a);
+ return vdup_n_s64 (__a);
}
__extension__ extern __inline uint64x1_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmov_n_u64 (uint64_t __a)
{
- return (uint64x1_t)__builtin_neon_vdup_ndi ((__builtin_neon_di) __a);
+ return vdup_n_u64 (__a);
}
__extension__ extern __inline int8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmovq_n_s8 (int8_t __a)
{
- return (int8x16_t)__builtin_neon_vdup_nv16qi ((__builtin_neon_qi) __a);
+ return vdupq_n_s8 (__a);
}
__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmovq_n_s16 (int16_t __a)
{
- return (int16x8_t)__builtin_neon_vdup_nv8hi ((__builtin_neon_hi) __a);
+ return vdupq_n_s16 (__a);
}
__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmovq_n_s32 (int32_t __a)
{
- return (int32x4_t)__builtin_neon_vdup_nv4si ((__builtin_neon_si) __a);
+ return vdupq_n_s32 (__a);
}
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmovq_n_f32 (float32_t __a)
{
- return (float32x4_t)__builtin_neon_vdup_nv4sf ((__builtin_neon_sf) __a);
+ return vdupq_n_f32 (__a);
}
__extension__ extern __inline uint8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmovq_n_u8 (uint8_t __a)
{
- return (uint8x16_t)__builtin_neon_vdup_nv16qi ((__builtin_neon_qi) __a);
+ return vdupq_n_u8 (__a);
}
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmovq_n_u16 (uint16_t __a)
{
- return (uint16x8_t)__builtin_neon_vdup_nv8hi ((__builtin_neon_hi) __a);
+ return vdupq_n_u16 (__a);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmovq_n_u32 (uint32_t __a)
{
- return (uint32x4_t)__builtin_neon_vdup_nv4si ((__builtin_neon_si) __a);
+ return vdupq_n_u32 (__a);
}
__extension__ extern __inline poly8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmovq_n_p8 (poly8_t __a)
{
- return (poly8x16_t)__builtin_neon_vdup_nv16qi ((__builtin_neon_qi) __a);
+ return vdupq_n_p8 (__a);
}
__extension__ extern __inline poly16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmovq_n_p16 (poly16_t __a)
{
- return (poly16x8_t)__builtin_neon_vdup_nv8hi ((__builtin_neon_hi) __a);
+ return vdupq_n_p16 (__a);
}
__extension__ extern __inline int64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmovq_n_s64 (int64_t __a)
{
- return (int64x2_t)__builtin_neon_vdup_nv2di ((__builtin_neon_di) __a);
+ return vdupq_n_s64 (__a);
}
__extension__ extern __inline uint64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmovq_n_u64 (uint64_t __a)
{
- return (uint64x2_t)__builtin_neon_vdup_nv2di ((__builtin_neon_di) __a);
+ return vdupq_n_u64 (__a);
}
__extension__ extern __inline int8x8_t
@@ -18005,14 +18008,14 @@ __extension__ extern __inline float16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_f16 (float16_t __a)
{
- return __builtin_neon_vdup_nv4hf (__a);
+ return (float16x4_t) {__a, __a, __a, __a};
}
__extension__ extern __inline float16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_f16 (float16_t __a)
{
- return __builtin_neon_vdup_nv8hf (__a);
+ return (float16x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}
__extension__ extern __inline float16x4_t
@@ -18047,14 +18050,14 @@ __extension__ extern __inline float16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmov_n_f16 (float16_t __a)
{
- return __builtin_neon_vdup_nv4hf (__a);
+ return vdup_n_f16 (__a);
}
__extension__ extern __inline float16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmovq_n_f16 (float16_t __a)
{
- return __builtin_neon_vdup_nv8hf (__a);
+ return vdupq_n_f16 (__a);
}
__extension__ extern __inline float16x4_t
@@ -18978,14 +18981,14 @@ __extension__ extern __inline bfloat16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdup_n_bf16 (bfloat16_t __a)
{
- return __builtin_neon_vdup_nv4bf (__a);
+ return (bfloat16x4_t) {__a, __a, __a, __a};
}
__extension__ extern __inline bfloat16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vdupq_n_bf16 (bfloat16_t __a)
{
- return __builtin_neon_vdup_nv8bf (__a);
+ return (bfloat16x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}
__extension__ extern __inline bfloat16x4_t
diff --git a/gcc/config/arm/arm_neon_builtins.def b/gcc/config/arm/arm_neon_builtins.def
index fb6d66e594a..fafb5c6fc51 100644
--- a/gcc/config/arm/arm_neon_builtins.def
+++ b/gcc/config/arm/arm_neon_builtins.def
@@ -211,9 +211,6 @@ VAR10 (GETLANE, vget_lane,
VAR6 (GETLANE, vget_laneu, v8qi, v4hi, v2si, v16qi, v8hi, v4si)
VAR10 (SETLANE, vset_lane,
v8qi, v4hi, v2si, v2sf, di, v16qi, v8hi, v4si, v4sf, v2di)
-VAR10 (UNOP, vdup_n,
- v8qi, v4hi, v2si, v2sf, di, v16qi, v8hi, v4si, v4sf, v2di)
-VAR4 (UNOP, vdup_n, v8hf, v4hf, v8bf, v4bf)
VAR10 (GETLANE, vdup_lane,
v8qi, v4hi, v2si, v2sf, di, v16qi, v8hi, v4si, v4sf, v2di)
VAR4 (GETLANE, vdup_lane, v8hf, v4hf, v8bf, v4bf)
diff --git a/gcc/testsuite/gcc.target/arm/pr51534.c b/gcc/testsuite/gcc.target/arm/pr51534.c
index 3711b45eed9..ac7f1ea4722 100644
--- a/gcc/testsuite/gcc.target/arm/pr51534.c
+++ b/gcc/testsuite/gcc.target/arm/pr51534.c
@@ -35,29 +35,17 @@ GEN_COND_TESTS(vceq)
/* Scan for expected outputs. */
/* { dg-final { scan-assembler "vcgt\.s8\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" } } */
-/* { dg-final { scan-assembler-times "vcgt\.u8\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, \[dD\]\[0-9\]+" 2 } } */
/* { dg-final { scan-assembler "vcgt\.s16\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" } } */
-/* { dg-final { scan-assembler-times "vcgt\.u16\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, \[dD\]\[0-9\]+" 2 } } */
/* { dg-final { scan-assembler "vcgt\.s32\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" } } */
-/* { dg-final { scan-assembler-times "vcgt\.u32\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, \[dD\]\[0-9\]+" 2 } } */
/* { dg-final { scan-assembler "vcgt\.s8\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" } } */
-/* { dg-final { scan-assembler-times "vcgt\.u8\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+" 2 } } */
/* { dg-final { scan-assembler "vcgt\.s16\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" } } */
-/* { dg-final { scan-assembler-times "vcgt\.u16\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+" 2 } } */
/* { dg-final { scan-assembler "vcgt\.s32\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" } } */
-/* { dg-final { scan-assembler-times "vcgt\.u32\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+" 2 } } */
/* { dg-final { scan-assembler "vcge\.s8\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" } } */
-/* { dg-final { scan-assembler-times "vcge\.u8\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, \[dD\]\[0-9\]+" 2 } } */
/* { dg-final { scan-assembler "vcge\.s16\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" } } */
-/* { dg-final { scan-assembler-times "vcge\.u16\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, \[dD\]\[0-9\]+" 2 } } */
/* { dg-final { scan-assembler "vcge\.s32\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" } } */
-/* { dg-final { scan-assembler-times "vcge\.u32\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, \[dD\]\[0-9\]+" 2 } } */
/* { dg-final { scan-assembler "vcge\.s8\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" } } */
-/* { dg-final { scan-assembler-times "vcge\.u8\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+" 2 } } */
/* { dg-final { scan-assembler "vcge\.s16\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" } } */
-/* { dg-final { scan-assembler-times "vcge\.u16\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+" 2 } } */
/* { dg-final { scan-assembler "vcge\.s32\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" } } */
-/* { dg-final { scan-assembler-times "vcge\.u32\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+" 2 } } */
/* { dg-final { scan-assembler "vclt\.s8\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" } } */
/* { dg-final { scan-assembler "vclt\.s16\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" } } */
/* { dg-final { scan-assembler "vclt\.s32\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" } } */
@@ -70,12 +58,14 @@ GEN_COND_TESTS(vceq)
/* { dg-final { scan-assembler "vcle\.s8\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" } } */
/* { dg-final { scan-assembler "vcle\.s16\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" } } */
/* { dg-final { scan-assembler "vcle\.s32\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" } } */
-/* { dg-final { scan-assembler-times "vceq\.i8\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" 2 } } */
-/* { dg-final { scan-assembler-times "vceq\.i16\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" 2 } } */
-/* { dg-final { scan-assembler-times "vceq\.i32\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" 2 } } */
-/* { dg-final { scan-assembler-times "vceq\.i8\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" 2 } } */
-/* { dg-final { scan-assembler-times "vceq\.i16\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" 2 } } */
-/* { dg-final { scan-assembler-times "vceq\.i32\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" 2 } } */
+/* { dg-final { scan-assembler-times "vceq\.i8\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" 4 } } */
+/* { dg-final { scan-assembler-times "vceq\.i16\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" 4 } } */
+/* { dg-final { scan-assembler-times "vceq\.i32\[ \]+\[dD\]\[0-9\]+, \[dD\]\[0-9\]+, #0" 4 } } */
+/* { dg-final { scan-assembler-times "vceq\.i8\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" 4 } } */
+/* { dg-final { scan-assembler-times "vceq\.i16\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" 4 } } */
+/* { dg-final { scan-assembler-times "vceq\.i32\[ \]+\[qQ\]\[0-9\]+, \[qQ\]\[0-9\]+, #0" 4 } } */
+/* { dg-final { scan-assembler-times "vmov\.i32\[ \]+\[dD\]\[0-9\]+, #0xffffffff" 3 } } */
+/* { dg-final { scan-assembler-times "vmov\.i32\[ \]+\[qQ\]\[0-9\]+, #4294967295" 3 } } */
/* And ensure we don't have unexpected output too. */
/* { dg-final { scan-assembler-not "vc\[gl\]\[te\]\.u\[0-9\]+\[ \]+\[qQdD\]\[0-9\]+, \[qQdD\]\[0-9\]+, #0" } } */
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2021-08-11 10:02 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-08-11 10:02 [gcc r12-2848] arm/66791: Replace builtins for vdup_n and vmov_n intrinsics Prathamesh Kulkarni
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).