Skip to content

[X86][AVX10.2] Fix wrong mask bits in cvtpbf8_ph intrinsics #120927

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Dec 23, 2024
Merged

[X86][AVX10.2] Fix wrong mask bits in cvtpbf8_ph intrinsics #120927

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions clang/lib/Headers/avx10_2_512convertintrin.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -308,13 +308,13 @@ static __inline __m512h __DEFAULT_FN_ATTRS512 _mm512_cvtpbf8_ph(__m256i __A) {
}

static __inline __m512h __DEFAULT_FN_ATTRS512
_mm512_mask_cvtpbf8_ph(__m512h __S, __mmask16 __U, __m256i __A) {
_mm512_mask_cvtpbf8_ph(__m512h __S, __mmask32 __U, __m256i __A) {
return _mm512_castsi512_ph(
_mm512_mask_slli_epi16((__m512i)__S, __U, _mm512_cvtepi8_epi16(__A), 8));
}

static __inline __m512h __DEFAULT_FN_ATTRS512
_mm512_maskz_cvtpbf8_ph(__mmask16 __U, __m256i __A) {
_mm512_maskz_cvtpbf8_ph(__mmask32 __U, __m256i __A) {
return _mm512_castsi512_ph(
_mm512_slli_epi16(_mm512_maskz_cvtepi8_epi16(__U, __A), 8));
}
Expand Down
4 changes: 2 additions & 2 deletions clang/lib/Headers/avx10_2convertintrin.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -580,13 +580,13 @@ static __inline__ __m256h __DEFAULT_FN_ATTRS256 _mm256_cvtpbf8_ph(__m128i __A) {
}

static __inline__ __m256h __DEFAULT_FN_ATTRS256
_mm256_mask_cvtpbf8_ph(__m256h __S, __mmask8 __U, __m128i __A) {
_mm256_mask_cvtpbf8_ph(__m256h __S, __mmask16 __U, __m128i __A) {
return _mm256_castsi256_ph(
_mm256_mask_slli_epi16((__m256i)__S, __U, _mm256_cvtepi8_epi16(__A), 8));
}

static __inline__ __m256h __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtpbf8_ph(__mmask8 __U, __m128i __A) {
_mm256_maskz_cvtpbf8_ph(__mmask16 __U, __m128i __A) {
return _mm256_castsi256_ph(
_mm256_slli_epi16(_mm256_maskz_cvtepi8_epi16(__U, __A), 8));
}
Expand Down
4 changes: 2 additions & 2 deletions clang/test/CodeGen/X86/avx10_2_512convert-builtins.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -299,7 +299,7 @@ __m512h test_mm512_cvtpbf8_ph(__m256i A) {
return _mm512_cvtpbf8_ph(A);
}

__m512h test_mm512_mask_cvtpbf8_ph(__m512h S, __mmask16 M, __m256i A) {
__m512h test_mm512_mask_cvtpbf8_ph(__m512h S, __mmask32 M, __m256i A) {
// CHECK-LABEL: @test_mm512_mask_cvtpbf8_ph
// CHECK: sext <32 x i8> %{{.*}} to <32 x i16>
// CHECK: @llvm.x86.avx512.pslli.w.512
Expand All @@ -308,7 +308,7 @@ __m512h test_mm512_mask_cvtpbf8_ph(__m512h S, __mmask16 M, __m256i A) {
return _mm512_mask_cvtpbf8_ph(S, M, A);
}

__m512h test_mm512_maskz_cvtpbf8_ph(__mmask16 M, __m256i A) {
__m512h test_mm512_maskz_cvtpbf8_ph(__mmask32 M, __m256i A) {
// CHECK-LABEL: @test_mm512_maskz_cvtpbf8_ph
// CHECK: sext <32 x i8> %{{.*}} to <32 x i16>
// CHECK: select <32 x i1> %{{.*}}, <32 x i16> %{{.*}}, <32 x i16> %{{.*}}
Expand Down
Loading