Skip to content
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

Jump to bottom

Migrate the math intrinsic functions #1417

Open
jinz2014 opened this issue Nov 10, 2023 · 1 comment
Open

Migrate the math intrinsic functions #1417

jinz2014 opened this issue Nov 10, 2023 · 1 comment
Labels
enhancement New feature or request

Comments

@jinz2014
Copy link
Contributor

jinz2014 commented Nov 10, 2023 •
edited

Syclomatic supports part of the functions in
https://docs.nvidia.com/cuda/cuda-math-api/group__CUDA__MATH__INTRINSIC__SIMD.html

The unsupported functions are listed below. Thanks.

DPCT1007:0: Migration of __viaddmax_s16x2 is not supported.
DPCT1007:1: Migration of __viaddmax_s16x2_relu is not supported.
DPCT1007:2: Migration of __viaddmax_s32 is not supported.
DPCT1007:3: Migration of __viaddmax_s32_relu is not supported.
DPCT1007:4: Migration of __viaddmax_u16x2 is not supported.
DPCT1007:5: Migration of __viaddmax_u32 is not supported.
DPCT1007:6: Migration of __viaddmin_s16x2 is not supported.
DPCT1007:7: Migration of __viaddmin_s16x2_relu is not supported.
DPCT1007:8: Migration of __viaddmin_s32 is not supported.
DPCT1007:9: Migration of __viaddmin_s32_relu is not supported.
DPCT1007:10: Migration of __viaddmin_u16x2 is not supported.
DPCT1007:11: Migration of __viaddmin_u32 is not supported.
DPCT1007:12: Migration of __vibmax_s16x2 is not supported.
DPCT1007:13: Migration of __vibmax_s32 is not supported.
DPCT1007:14: Migration of __vibmax_u16x2 is not supported.
DPCT1007:15: Migration of __vibmax_u32 is not supported.
DPCT1007:16: Migration of __vibmin_s16x2 is not supported.
DPCT1007:17: Migration of __vibmin_s32 is not supported.
DPCT1007:18: Migration of __vibmin_u16x2 is not supported.
DPCT1007:19: Migration of __vibmin_u32 is not supported.
 DPCT1007:20: Migration of __vimax3_s16x2 is not supported.
 DPCT1007:21: Migration of __vimax3_s16x2_relu is not supported.
 DPCT1007:22: Migration of __vimax3_s32 is not supported.
 DPCT1007:23: Migration of __vimax3_s32_relu is not supported.
 DPCT1007:24: Migration of __vimax3_u16x2 is not supported.
 DPCT1007:25: Migration of __vimax3_u32 is not supported.
 DPCT1007:26: Migration of __vimax_s16x2_relu is not supported.
 DPCT1007:27: Migration of __vimax_s32_relu is not supported.
 DPCT1007:28: Migration of __vimin3_s16x2 is not supported.
 DPCT1007:29: Migration of __vimin3_s16x2_relu is not supported.
 DPCT1007:30: Migration of __vimin3_s32 is not supported.
 DPCT1007:31: Migration of __vimin3_s32_relu is not supported.
 DPCT1007:32: Migration of __vimin3_u16x2 is not supported.
 DPCT1007:33: Migration of __vimin3_u32 is not supported.
 DPCT1007:34: Migration of __vimin_s16x2_relu is not supported.
 DPCT1007:35: Migration of __vimin_s32_relu is not supported.
@jinz2014 jinz2014 added the enhancement New feature or request label Nov 10, 2023
@tomflinda
Copy link
Contributor

@jinz2014 thanks for your report, we will double check that whether some of them can been supported from SYCL side.

@jinz2014 jinz2014 changed the title migration of math intrinsic functions Migrate the math intrinsic functions Nov 16, 2023
@jinz2014 jinz2014 mentioned this issue Nov 27, 2023
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@jinz2014 @tomflinda