[clang] [llvm] [X86][AVX10.2] Remove YMM rounding from VCVTTP.*QS (PR #132414)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Mar 21 08:58:12 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-mc
Author: Phoebe Wang (phoebewang)
<details>
<summary>Changes</summary>
Ref: https://cdrdv2.intel.com/v1/dl/getContent/784343
---
Patch is 100.56 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/132414.diff
16 Files Affected:
- (modified) clang/include/clang/Basic/BuiltinsX86.td (+8-8)
- (modified) clang/lib/Headers/avx10_2satcvtdsintrin.h (+48-172)
- (modified) clang/lib/Sema/SemaX86.cpp (-8)
- (removed) clang/test/CodeGen/X86/avx10_2satcvtds-builtins-errors.c (-57)
- (modified) clang/test/CodeGen/X86/avx10_2satcvtds-builtins-x64.c (+12-84)
- (modified) clang/test/CodeGen/X86/avx10_2satcvtds-builtins.c (+14-89)
- (modified) llvm/include/llvm/IR/IntrinsicsX86.td (+24-24)
- (modified) llvm/lib/Target/X86/X86InstrAVX10.td (-5)
- (modified) llvm/lib/Target/X86/X86IntrinsicsInfo.h (+16-16)
- (modified) llvm/test/CodeGen/X86/avx10_2satcvtds-intrinsics.ll (+38-38)
- (modified) llvm/test/MC/Disassembler/X86/avx10.2-satcvtds-32.txt (-48)
- (modified) llvm/test/MC/Disassembler/X86/avx10.2-satcvtds-64.txt (-48)
- (modified) llvm/test/MC/X86/avx10_2satcvtds-32-att.s (-48)
- (modified) llvm/test/MC/X86/avx10_2satcvtds-32-intel.s (-64)
- (modified) llvm/test/MC/X86/avx10_2satcvtds-64-att.s (-48)
- (modified) llvm/test/MC/X86/avx10_2satcvtds-64-intel.s (-64)
``````````diff
diff --git a/clang/include/clang/Basic/BuiltinsX86.td b/clang/include/clang/Basic/BuiltinsX86.td
index ea0d6df4a33c2..583f4534dfab2 100644
--- a/clang/include/clang/Basic/BuiltinsX86.td
+++ b/clang/include/clang/Basic/BuiltinsX86.td
@@ -4615,7 +4615,7 @@ let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<128>] i
}
let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<256>] in {
- def vcvttpd2dqs256_round_mask : X86Builtin<"_Vector<4, int>(_Vector<4, double>, _Vector<4, int>, unsigned char, _Constant int)">;
+ def vcvttpd2dqs256_mask : X86Builtin<"_Vector<4, int>(_Vector<4, double>, _Vector<4, int>, unsigned char)">;
}
let Features = "avx10.2-512", Attributes = [NoThrow, RequiredVectorWidth<512>] in {
@@ -4627,7 +4627,7 @@ let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<128>] i
}
let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<256>] in {
- def vcvttpd2udqs256_round_mask : X86Builtin<"_Vector<4, int>(_Vector<4, double>, _Vector<4, int>, unsigned char, _Constant int)">;
+ def vcvttpd2udqs256_mask : X86Builtin<"_Vector<4, int>(_Vector<4, double>, _Vector<4, int>, unsigned char)">;
}
let Features = "avx10.2-512", Attributes = [NoThrow, RequiredVectorWidth<512>] in {
@@ -4639,7 +4639,7 @@ let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<128>] i
}
let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<256>] in {
- def vcvttpd2qqs256_round_mask : X86Builtin<"_Vector<4, long long int>(_Vector<4, double>, _Vector<4, long long int>, unsigned char, _Constant int)">;
+ def vcvttpd2qqs256_mask : X86Builtin<"_Vector<4, long long int>(_Vector<4, double>, _Vector<4, long long int>, unsigned char)">;
}
let Features = "avx10.2-512", Attributes = [NoThrow, RequiredVectorWidth<512>] in {
@@ -4651,7 +4651,7 @@ let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<128>] i
}
let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<256>] in {
- def vcvttpd2uqqs256_round_mask : X86Builtin<"_Vector<4, long long int>(_Vector<4, double>, _Vector<4, long long int>, unsigned char, _Constant int)">;
+ def vcvttpd2uqqs256_mask : X86Builtin<"_Vector<4, long long int>(_Vector<4, double>, _Vector<4, long long int>, unsigned char)">;
}
let Features = "avx10.2-512", Attributes = [NoThrow, RequiredVectorWidth<512>] in {
@@ -4663,7 +4663,7 @@ let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<128>] i
}
let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<256>] in {
- def vcvttps2dqs256_round_mask : X86Builtin<"_Vector<8, int>(_Vector<8, float>, _Vector<8, int>, unsigned char, _Constant int)">;
+ def vcvttps2dqs256_mask : X86Builtin<"_Vector<8, int>(_Vector<8, float>, _Vector<8, int>, unsigned char)">;
}
let Features = "avx10.2-512", Attributes = [NoThrow, RequiredVectorWidth<512>] in {
@@ -4675,7 +4675,7 @@ let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<128>] i
}
let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<256>] in {
- def vcvttps2udqs256_round_mask : X86Builtin<"_Vector<8, int>(_Vector<8, float>, _Vector<8, int>, unsigned char, _Constant int)">;
+ def vcvttps2udqs256_mask : X86Builtin<"_Vector<8, int>(_Vector<8, float>, _Vector<8, int>, unsigned char)">;
}
let Features = "avx10.2-512", Attributes = [NoThrow, RequiredVectorWidth<512>] in {
@@ -4687,7 +4687,7 @@ let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<128>] i
}
let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<256>] in {
- def vcvttps2qqs256_round_mask : X86Builtin<"_Vector<4, long long int>(_Vector<4, float>, _Vector<4, long long int>, unsigned char, _Constant int)">;
+ def vcvttps2qqs256_mask : X86Builtin<"_Vector<4, long long int>(_Vector<4, float>, _Vector<4, long long int>, unsigned char)">;
}
let Features = "avx10.2-512", Attributes = [NoThrow, RequiredVectorWidth<512>] in {
@@ -4699,7 +4699,7 @@ let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<128>] i
}
let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<256>] in {
- def vcvttps2uqqs256_round_mask : X86Builtin<"_Vector<4, long long int>(_Vector<4, float>, _Vector<4, long long int>, unsigned char, _Constant int)">;
+ def vcvttps2uqqs256_mask : X86Builtin<"_Vector<4, long long int>(_Vector<4, float>, _Vector<4, long long int>, unsigned char)">;
}
let Features = "avx10.2-512", Attributes = [NoThrow, RequiredVectorWidth<512>] in {
diff --git a/clang/lib/Headers/avx10_2satcvtdsintrin.h b/clang/lib/Headers/avx10_2satcvtdsintrin.h
index 9dbfed42667ef..6509a4ebf9c77 100644
--- a/clang/lib/Headers/avx10_2satcvtdsintrin.h
+++ b/clang/lib/Headers/avx10_2satcvtdsintrin.h
@@ -92,37 +92,22 @@ _mm_maskz_cvtts_pd_epi32(__mmask16 __U, __m128d __A) {
// 256 Bit : Double -> int
static __inline__ __m128i __DEFAULT_FN_ATTRS256
_mm256_cvtts_pd_epi32(__m256d __A) {
- return ((__m128i)__builtin_ia32_vcvttpd2dqs256_round_mask(
- (__v4df)__A, (__v4si)_mm_undefined_si128(), (__mmask8)-1,
- _MM_FROUND_CUR_DIRECTION));
+ return ((__m128i)__builtin_ia32_vcvttpd2dqs256_mask(
+ (__v4df)__A, (__v4si)_mm_undefined_si128(), (__mmask8)-1));
}
static __inline__ __m128i __DEFAULT_FN_ATTRS256
_mm256_mask_cvtts_pd_epi32(__m128i __W, __mmask8 __U, __m256d __A) {
- return ((__m128i)__builtin_ia32_vcvttpd2dqs256_round_mask(
- (__v4df)__A, (__v4si)__W, __U, _MM_FROUND_CUR_DIRECTION));
+ return ((__m128i)__builtin_ia32_vcvttpd2dqs256_mask(
+ (__v4df)__A, (__v4si)__W, __U));
}
static __inline__ __m128i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtts_pd_epi32(__mmask8 __U, __m256d __A) {
- return ((__m128i)__builtin_ia32_vcvttpd2dqs256_round_mask(
- (__v4df)__A, (__v4si)_mm_setzero_si128(), __U, _MM_FROUND_CUR_DIRECTION));
+ return ((__m128i)__builtin_ia32_vcvttpd2dqs256_mask(
+ (__v4df)__A, (__v4si)_mm_setzero_si128(), __U));
}
-#define _mm256_cvtts_roundpd_epi32(__A, __R) \
- ((__m128i)__builtin_ia32_vcvttpd2dqs256_round_mask( \
- (__v4df)(__m256d)__A, (__v4si)(__m128i)_mm_undefined_si128(), \
- (__mmask8) - 1, (int)(__R)))
-
-#define _mm256_mask_cvtts_roundpd_epi32(__W, __U, __A, __R) \
- ((__m128i)__builtin_ia32_vcvttpd2dqs256_round_mask( \
- (__v4df)(__m256d)__A, (__v4si)(__m128i)__W, (__mmask8)__U, (int)(__R)))
-
-#define _mm256_maskz_cvtts_roundpd_epi32(__U, __A, __R) \
- ((__m128i)__builtin_ia32_vcvttpd2dqs256_round_mask( \
- (__v4df)(__m256d)__A, (__v4si)(__m128i)_mm_setzero_si128(), \
- (__mmask8)__U, (int)(__R)))
-
// 128 Bit : Double -> uint
static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_cvtts_pd_epu32(__m128d __A) {
@@ -145,37 +130,22 @@ _mm_maskz_cvtts_pd_epu32(__mmask8 __U, __m128d __A) {
// 256 Bit : Double -> uint
static __inline__ __m128i __DEFAULT_FN_ATTRS256
_mm256_cvtts_pd_epu32(__m256d __A) {
- return ((__m128i)__builtin_ia32_vcvttpd2udqs256_round_mask(
- (__v4df)__A, (__v4si)_mm_undefined_si128(), (__mmask8)-1,
- _MM_FROUND_CUR_DIRECTION));
+ return ((__m128i)__builtin_ia32_vcvttpd2udqs256_mask(
+ (__v4df)__A, (__v4si)_mm_undefined_si128(), (__mmask8)-1));
}
static __inline__ __m128i __DEFAULT_FN_ATTRS256
_mm256_mask_cvtts_pd_epu32(__m128i __W, __mmask8 __U, __m256d __A) {
- return ((__m128i)__builtin_ia32_vcvttpd2udqs256_round_mask(
- (__v4df)__A, (__v4si)__W, __U, _MM_FROUND_CUR_DIRECTION));
+ return ((__m128i)__builtin_ia32_vcvttpd2udqs256_mask(
+ (__v4df)__A, (__v4si)__W, __U));
}
static __inline__ __m128i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtts_pd_epu32(__mmask8 __U, __m256d __A) {
- return ((__m128i)__builtin_ia32_vcvttpd2udqs256_round_mask(
- (__v4df)__A, (__v4si)_mm_setzero_si128(), __U, _MM_FROUND_CUR_DIRECTION));
+ return ((__m128i)__builtin_ia32_vcvttpd2udqs256_mask(
+ (__v4df)__A, (__v4si)_mm_setzero_si128(), __U));
}
-#define _mm256_cvtts_roundpd_epu32(__A, __R) \
- ((__m128i)__builtin_ia32_vcvttpd2udqs256_round_mask( \
- (__v4df)(__m256d)__A, (__v4si)(__m128i)_mm_undefined_si128(), \
- (__mmask8) - 1, (int)(__R)))
-
-#define _mm256_mask_cvtts_roundpd_epu32(__W, __U, __A, __R) \
- ((__m128i)__builtin_ia32_vcvttpd2udqs256_round_mask( \
- (__v4df)(__m256d)__A, (__v4si)(__m128i)__W, (__mmask8)__U, (int)(__R)))
-
-#define _mm256_maskz_cvtts_roundpd_epu32(__U, __A, __R) \
- ((__m128i)__builtin_ia32_vcvttpd2udqs256_round_mask( \
- (__v4df)(__m256d)__A, (__v4si)(__m128i)_mm_setzero_si128(), \
- (__mmask8)__U, (int)(__R)))
-
// 128 Bit : Double -> long
static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_cvtts_pd_epi64(__m128d __A) {
@@ -198,37 +168,22 @@ _mm_maskz_cvtts_pd_epi64(__mmask8 __U, __m128d __A) {
// 256 Bit : Double -> long
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvtts_pd_epi64(__m256d __A) {
- return ((__m256i)__builtin_ia32_vcvttpd2qqs256_round_mask(
- (__v4df)__A, (__v4di)_mm256_undefined_si256(), (__mmask8)-1,
- _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttpd2qqs256_mask(
+ (__v4df)__A, (__v4di)_mm256_undefined_si256(), (__mmask8)-1));
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvtts_pd_epi64(__m256i __W, __mmask8 __U, __m256d __A) {
- return ((__m256i)__builtin_ia32_vcvttpd2qqs256_round_mask(
- (__v4df)__A, (__v4di)__W, __U, _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttpd2qqs256_mask(
+ (__v4df)__A, (__v4di)__W, __U));
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtts_pd_epi64(__mmask8 __U, __m256d __A) {
- return ((__m256i)__builtin_ia32_vcvttpd2qqs256_round_mask(
- (__v4df)__A, (__v4di)_mm256_setzero_si256(), __U,
- _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttpd2qqs256_mask(
+ (__v4df)__A, (__v4di)_mm256_setzero_si256(), __U));
}
-#define _mm256_cvtts_roundpd_epi64(__A, __R) \
- ((__m256i)__builtin_ia32_vcvttpd2qqs256_round_mask( \
- (__v4df)__A, (__v4di)_mm256_undefined_si256(), (__mmask8) - 1, \
- (int)__R))
-
-#define _mm256_mask_cvtts_roundpd_epi64(__W, __U, __A, __R) \
- ((__m256i)__builtin_ia32_vcvttpd2qqs256_round_mask((__v4df)__A, (__v4di)__W, \
- (__mmask8)__U, (int)__R))
-
-#define _mm256_maskz_cvtts_roundpd_epi64(__U, __A, __R) \
- ((__m256i)__builtin_ia32_vcvttpd2qqs256_round_mask( \
- (__v4df)__A, (__v4di)_mm256_setzero_si256(), (__mmask8)__U, (int)__R))
-
// 128 Bit : Double -> ulong
static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_cvtts_pd_epu64(__m128d __A) {
@@ -252,37 +207,22 @@ _mm_maskz_cvtts_pd_epu64(__mmask8 __U, __m128d __A) {
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvtts_pd_epu64(__m256d __A) {
- return ((__m256i)__builtin_ia32_vcvttpd2uqqs256_round_mask(
- (__v4df)__A, (__v4di)_mm256_undefined_si256(), (__mmask8)-1,
- _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttpd2uqqs256_mask(
+ (__v4df)__A, (__v4di)_mm256_undefined_si256(), (__mmask8)-1));
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvtts_pd_epu64(__m256i __W, __mmask8 __U, __m256d __A) {
- return ((__m256i)__builtin_ia32_vcvttpd2uqqs256_round_mask(
- (__v4df)__A, (__v4di)__W, __U, _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttpd2uqqs256_mask(
+ (__v4df)__A, (__v4di)__W, __U));
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtts_pd_epu64(__mmask8 __U, __m256d __A) {
- return ((__m256i)__builtin_ia32_vcvttpd2uqqs256_round_mask(
- (__v4df)__A, (__v4di)_mm256_setzero_si256(), __U,
- _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttpd2uqqs256_mask(
+ (__v4df)__A, (__v4di)_mm256_setzero_si256(), __U));
}
-#define _mm256_cvtts_roundpd_epu64(__A, __R) \
- ((__m256i)__builtin_ia32_vcvttpd2uqqs256_round_mask( \
- (__v4df)__A, (__v4di)_mm256_undefined_si256(), (__mmask8) - 1, \
- (int)__R))
-
-#define _mm256_mask_cvtts_roundpd_epu64(__W, __U, __A, __R) \
- ((__m256i)__builtin_ia32_vcvttpd2uqqs256_round_mask( \
- (__v4df)__A, (__v4di)__W, (__mmask8)__U, (int)__R))
-
-#define _mm256_maskz_cvtts_roundpd_epu64(__U, __A, __R) \
- ((__m256i)__builtin_ia32_vcvttpd2uqqs256_round_mask( \
- (__v4df)__A, (__v4di)_mm256_setzero_si256(), (__mmask8)__U, (int)__R))
-
// 128 Bit : float -> int
static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_cvtts_ps_epi32(__m128 __A) {
return ((__m128i)__builtin_ia32_vcvttps2dqs128_mask(
@@ -304,38 +244,22 @@ _mm_maskz_cvtts_ps_epi32(__mmask8 __U, __m128 __A) {
// 256 Bit : float -> int
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvtts_ps_epi32(__m256 __A) {
- return ((__m256i)__builtin_ia32_vcvttps2dqs256_round_mask(
- (__v8sf)__A, (__v8si)_mm256_undefined_si256(), (__mmask8)-1,
- _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttps2dqs256_mask(
+ (__v8sf)__A, (__v8si)_mm256_undefined_si256(), (__mmask8)-1));
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvtts_ps_epi32(__m256i __W, __mmask8 __U, __m256 __A) {
- return ((__m256i)__builtin_ia32_vcvttps2dqs256_round_mask(
- (__v8sf)__A, (__v8si)__W, __U, _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttps2dqs256_mask(
+ (__v8sf)__A, (__v8si)__W, __U));
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtts_ps_epi32(__mmask8 __U, __m256 __A) {
- return ((__m256i)__builtin_ia32_vcvttps2dqs256_round_mask(
- (__v8sf)__A, (__v8si)_mm256_setzero_si256(), __U,
- _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttps2dqs256_mask(
+ (__v8sf)__A, (__v8si)_mm256_setzero_si256(), __U));
}
-#define _mm256_cvtts_roundps_epi32(__A, __R) \
- ((__m256i)__builtin_ia32_vcvttps2dqs256_round_mask( \
- (__v8sf)(__m256)__A, (__v8si)(__m256i)_mm256_undefined_si256(), \
- (__mmask8) - 1, (int)(__R)))
-
-#define _mm256_mask_cvtts_roundps_epi32(__W, __U, __A, __R) \
- ((__m256i)__builtin_ia32_vcvttps2dqs256_round_mask( \
- (__v8sf)(__m256)__A, (__v8si)(__m256i)__W, (__mmask8)__U, (int)(__R)))
-
-#define _mm256_maskz_cvtts_roundps_epi32(__U, __A, __R) \
- ((__m256i)__builtin_ia32_vcvttps2dqs256_round_mask( \
- (__v8sf)(__m256)__A, (__v8si)(__m256i)_mm256_setzero_si256(), \
- (__mmask8)__U, (int)(__R)))
-
// 128 Bit : float -> uint
static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_cvtts_ps_epu32(__m128 __A) {
return ((__m128i)__builtin_ia32_vcvttps2udqs128_mask(
@@ -358,38 +282,22 @@ _mm_maskz_cvtts_ps_epu32(__mmask8 __U, __m128 __A) {
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvtts_ps_epu32(__m256 __A) {
- return ((__m256i)__builtin_ia32_vcvttps2udqs256_round_mask(
- (__v8sf)__A, (__v8si)_mm256_undefined_si256(), (__mmask8)-1,
- _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttps2udqs256_mask(
+ (__v8sf)__A, (__v8si)_mm256_undefined_si256(), (__mmask8)-1));
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvtts_ps_epu32(__m256i __W, __mmask8 __U, __m256 __A) {
- return ((__m256i)__builtin_ia32_vcvttps2udqs256_round_mask(
- (__v8sf)__A, (__v8si)__W, __U, _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttps2udqs256_mask(
+ (__v8sf)__A, (__v8si)__W, __U));
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtts_ps_epu32(__mmask8 __U, __m256 __A) {
- return ((__m256i)__builtin_ia32_vcvttps2udqs256_round_mask(
- (__v8sf)__A, (__v8si)_mm256_setzero_si256(), __U,
- _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttps2udqs256_mask(
+ (__v8sf)__A, (__v8si)_mm256_setzero_si256(), __U));
}
-#define _mm256_cvtts_roundps_epu32(__A, __R) \
- ((__m256i)__builtin_ia32_vcvttps2udqs256_round_mask( \
- (__v8sf)(__m256)__A, (__v8si)(__m256i)_mm256_undefined_si256(), \
- (__mmask8) - 1, (int)(__R)))
-
-#define _mm256_mask_cvtts_roundps_epu32(__W, __U, __A, __R) \
- ((__m256i)__builtin_ia32_vcvttps2udqs256_round_mask( \
- (__v8sf)(__m256)__A, (__v8si)(__m256i)__W, (__mmask8)__U, (int)(__R)))
-
-#define _mm256_maskz_cvtts_roundps_epu32(__U, __A, __R) \
- ((__m256i)__builtin_ia32_vcvttps2udqs256_round_mask( \
- (__v8sf)(__m256)__A, (__v8si)(__m256i)_mm256_setzero_si256(), \
- (__mmask8)__U, (int)(__R)))
-
// 128 bit : float -> long
static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_cvtts_ps_epi64(__m128 __A) {
return ((__m128i)__builtin_ia32_vcvttps2qqs128_mask(
@@ -411,37 +319,21 @@ _mm_maskz_cvtts_ps_epi64(__mmask8 __U, __m128 __A) {
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvtts_ps_epi64(__m128 __A) {
- return ((__m256i)__builtin_ia32_vcvttps2qqs256_round_mask(
- (__v4sf)__A, (__v4di)_mm256_undefined_si256(), (__mmask8)-1,
- _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttps2qqs256_mask(
+ (__v4sf)__A, (__v4di)_mm256_undefined_si256(), (__mmask8)-1));
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvtts_ps_epi64(__m256i __W, __mmask8 __U, __m128 __A) {
- return ((__m256i)__builtin_ia32_vcvttps2qqs256_round_mask(
- (__v4sf)__A, (__v4di)__W, __U, _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttps2qqs256_mask(
+ (__v4sf)__A, (__v4di)__W, __U));
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtts_ps_epi64(__mmask8 __U, __m128 __A) {
- return ((__m256i)__builtin_ia32_vcvttps2qqs256_round_mask(
- (__v4sf)__A, (__v4di)_mm256_setzero_si256(), __U,
- _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttps2qqs256_mask(
+ (__v4sf)__A, (__v4di)_mm256_setzero_si256(), __U));
}
-#define _mm256_cvtts_roundps_epi64(__A, __R) \
- ((__m256i)__builtin_ia32_vcvttps2qqs256_round_mask( \
- (__v4sf)(__m128)__A, (__v4di)_mm256_undefined_si256(), (__mmask8) - 1, \
- (int)__R))
-
-#define _mm256_mask_cvtts_roundps_epi64(__W, __U, __A, __R) \
- ((__m256i)__builtin_ia32_vcvttps2qqs256_round_mask( \
- (__v4sf)(__m128)__A, (__v4di)__W, (__mmask8)__U, (int)__R))
-
-#define _mm256_maskz_cvtts_roundps_epi64(__U, __A, __R) \
- ((__m256i)__builtin_ia32_vcvttps2qqs256_round_mask( \
- (__v4sf)(__m128)__A, (__v4di)_mm256_setzero_si256(), (__mmask8)__U, \
- (int)__R))
-
// 128 bit : float -> ulong
static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_cvtts_ps_epu64(__m128 __A) {
return ((__m128i)__builtin_ia32_vcvttps2uqqs128_mask(
@@ -463,38 +355,22 @@ _mm_maskz_cvtts_ps_epu64(__mmask8 __U, __m128 __A) {
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvtts_ps_epu64(__m128 __A) {
- return ((__m256i)__builtin_ia32_vcvttps2uqqs256_round_mask(
- (__v4sf)__A, (__v4di)_mm256_undefined_si256(), (__mmask8)-1,
- _MM_FROUND_CUR_DIRECTION));
+ return ((__m256i)__builtin_ia32_vcvttps2uqqs256_mask(
+ (__v4sf)__A, (__v4di)_mm256_undefined_si256(), (__mmask8)-1));
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvtts_ps_epu64(__m256i __W, __mmask8 __U, __m128 __A) {
- return ((__m256i)__builtin_ia32_vcvttps2uqqs256_round_mask(
- (__v4sf)__A, (__v4di)__W, __U, _MM_FROUND_CUR_DIRECTION));
+ return ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/132414
More information about the llvm-commits
mailing list