maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
326,730 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

4 Commits

Author SHA1 Message Date
Pengfei Wang 244062eece [X86] Enable intrinsics that convert float and bf16 data to each other 
Scalar version :
_mm_cvtsbh_ss , _mm_cvtness_sbh

Vector version:
_mm512_cvtpbh_ps , _mm256_cvtpbh_ps
_mm512_maskz_cvtpbh_ps , _mm256_maskz_cvtpbh_ps
_mm512_mask_cvtpbh_ps , _mm256_mask_cvtpbh_ps

Patch by Shengchen Kan (skan)

Differential Revision: https://reviews.llvm.org/D62363

llvm-svn: 363018
 2019-06-11 01:17:28 +00:00
Craig Topper 20040db9a6 [X86] Stop implicitly enabling avx512vl when avx512bf16 is enabled. 
Previously we were doing this so that the 256 bit selectw builtin could be used in the implementation of the 512->256 bit conversion intrinsic.

After this commit we now use a masked convert builtin that will emit the intrinsic call and the 256-bit select from custom code in CGBuiltin. Then the header only needs to call that one intrinsic.

llvm-svn: 360924
 2019-05-16 18:28:17 +00:00
Craig Topper 58964566e0 [X86] Update doxygen comments for AVX512BF16 to not refer to masks as 'immediates'. Refer to parameter names instead of 'src', 'src1', 'src2'. NFC 
llvm-svn: 360918
 2019-05-16 17:34:35 +00:00
Fangrui Song 041c377a59 [X86] Move files to correct directories after D60552 
llvm-svn: 360022
 2019-05-06 09:24:36 +00:00