forked from OSchip/llvm-project
[Headers][X86] Fix stream_load (movntdqa) to accept const*.
Per Intel intrinsics guide: - _mm256_stream_load_si256 takes `__m256i const *' - _mm_stream_load_si128 takes `__m128i *', for no good reason. Let's accept const* for both. llvm-svn: 249213
This commit is contained in:
parent
a45373f193
commit
7dfaaf3891
|
@ -390,7 +390,7 @@ TARGET_BUILTIN(__builtin_ia32_roundsd, "V2dV2dV2di", "", "sse4.1")
|
|||
TARGET_BUILTIN(__builtin_ia32_roundpd, "V2dV2di", "", "sse4.1")
|
||||
TARGET_BUILTIN(__builtin_ia32_dpps, "V4fV4fV4fIc", "", "sse4.1")
|
||||
TARGET_BUILTIN(__builtin_ia32_dppd, "V2dV2dV2dIc", "", "sse4.1")
|
||||
TARGET_BUILTIN(__builtin_ia32_movntdqa, "V2LLiV2LLi*", "", "sse4.1")
|
||||
TARGET_BUILTIN(__builtin_ia32_movntdqa, "V2LLiV2LLiC*", "", "sse4.1")
|
||||
TARGET_BUILTIN(__builtin_ia32_ptestz128, "iV2LLiV2LLi", "", "sse4.1")
|
||||
TARGET_BUILTIN(__builtin_ia32_ptestc128, "iV2LLiV2LLi", "", "sse4.1")
|
||||
TARGET_BUILTIN(__builtin_ia32_ptestnzc128, "iV2LLiV2LLi", "", "sse4.1")
|
||||
|
@ -594,7 +594,7 @@ TARGET_BUILTIN(__builtin_ia32_psrldi256, "V8iV8ii", "", "avx2")
|
|||
TARGET_BUILTIN(__builtin_ia32_psrld256, "V8iV8iV4i", "", "avx2")
|
||||
TARGET_BUILTIN(__builtin_ia32_psrlqi256, "V4LLiV4LLii", "", "avx2")
|
||||
TARGET_BUILTIN(__builtin_ia32_psrlq256, "V4LLiV4LLiV2LLi", "", "avx2")
|
||||
TARGET_BUILTIN(__builtin_ia32_movntdqa256, "V4LLiV4LLi*", "", "avx2")
|
||||
TARGET_BUILTIN(__builtin_ia32_movntdqa256, "V4LLiV4LLiC*", "", "avx2")
|
||||
TARGET_BUILTIN(__builtin_ia32_permvarsi256, "V8iV8iV8i", "", "avx2")
|
||||
TARGET_BUILTIN(__builtin_ia32_permvarsf256, "V8fV8fV8f", "", "avx2")
|
||||
TARGET_BUILTIN(__builtin_ia32_permti256, "V4LLiV4LLiV4LLiIc", "", "avx2")
|
||||
|
|
|
@ -754,9 +754,9 @@ _mm256_xor_si256(__m256i __a, __m256i __b)
|
|||
}
|
||||
|
||||
static __inline__ __m256i __DEFAULT_FN_ATTRS
|
||||
_mm256_stream_load_si256(__m256i *__V)
|
||||
_mm256_stream_load_si256(__m256i const *__V)
|
||||
{
|
||||
return (__m256i)__builtin_ia32_movntdqa256((__v4di *)__V);
|
||||
return (__m256i)__builtin_ia32_movntdqa256((const __v4di *)__V);
|
||||
}
|
||||
|
||||
static __inline__ __m128 __DEFAULT_FN_ATTRS
|
||||
|
|
|
@ -151,9 +151,9 @@ _mm_mul_epi32 (__m128i __V1, __m128i __V2)
|
|||
|
||||
/* SSE4 Streaming Load Hint Instruction. */
|
||||
static __inline__ __m128i __DEFAULT_FN_ATTRS
|
||||
_mm_stream_load_si128 (__m128i *__V)
|
||||
_mm_stream_load_si128 (__m128i const *__V)
|
||||
{
|
||||
return (__m128i) __builtin_ia32_movntdqa ((__v2di *) __V);
|
||||
return (__m128i) __builtin_ia32_movntdqa ((const __v2di *) __V);
|
||||
}
|
||||
|
||||
/* SSE4 Packed Integer Min/Max Instructions. */
|
||||
|
|
|
@ -728,7 +728,7 @@ __m256i test_mm256_unpacklo_epi64(__m256i a, __m256i b) {
|
|||
return _mm256_unpacklo_epi64(a, b);
|
||||
}
|
||||
|
||||
__m256i test_mm256_stream_load_si256(__m256i *a) {
|
||||
__m256i test_mm256_stream_load_si256(__m256i const *a) {
|
||||
// CHECK: @llvm.x86.avx2.movntdqa
|
||||
// CHECK-ASM: vmovntdqa (%rdi), %ymm{{.*}}
|
||||
return _mm256_stream_load_si256(a);
|
||||
|
|
|
@ -385,7 +385,7 @@ __m128 test_mm_round_ss(__m128 x, __m128 y) {
|
|||
return _mm_round_ss(x, y, 2);
|
||||
}
|
||||
|
||||
__m128i test_mm_stream_load_si128(__m128i *a) {
|
||||
__m128i test_mm_stream_load_si128(__m128i const *a) {
|
||||
// CHECK-LABEL: test_mm_stream_load_si128
|
||||
// CHECK: call <2 x i64> @llvm.x86.sse41.movntdqa
|
||||
// CHECK-ASM: movntdqa
|
||||
|
|
Loading…
Reference in New Issue