[SYCL][HIP] Support of AMD matrix core instructions #11485
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
experimental namespace As part of the effort to move joint matrix from experimental namespace to supported. A review of the API is being done as part of intel#7964. This results in the following changes in the syntax: 1- Add Td to joint_matrix_mad as Tc can be different from Td on the GPU, Now, we make D as an input argument to mad. 2- Change “packed” to ext_intel_packed: 3- Move EWOps (get_wi_data, wi_element, get_coord) to detail namespace) 4- add const to joint_matrix in store and mad 5 - add joint_matrix_copy/assignment function 6- add apply with coordination (change existing tests) 7- change get_coord vector type from int32_t to size_t 8- delete explicitly both = and copy ctor.
mmoadeli
requested review from
dkhaldi,
YuriPlyakhin,
yubingex007-a11y and
a team
as code owners
mmoadeli
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
mmoadeli
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
JackAKirk
reviewed
Oct 24, 2023
JackAKirk
reviewed
Oct 24, 2023
JackAKirk
reviewed
Oct 24, 2023
JackAKirk
reviewed
Oct 24, 2023
Use same code for `copy`, `fill` and `apply`. Remove `-DSYCL_EXT_ONEAPI_MATRIX_VERSION=4`
mmoadeli
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
JackAKirk
reviewed
Oct 24, 2023
mmoadeli
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
mmoadeli
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
JackAKirk
reviewed
Oct 24, 2023
JackAKirk
approved these changes
Oct 24, 2023
mmoadeli
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
dkhaldi
reviewed
Oct 24, 2023
mmoadeli
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
mmoadeli
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
mmoadeli
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
maarquitos14
pushed a commit
that referenced
this pull request
Oct 31, 2023
* Support one block AMD matrix core instructions for `__gfx90a__` architecture. * Supports `__builtin_amdgcn_mfma_i32_32x32x8i8`, `__builtin_amdgcn_mfma_i32_16x16x16i8`, `__builtin_amdgcn_mfma_f64_16x16x4f64`, `__builtin_amdgcn_mfma_f32_32x32x8bf16_1k`, `__builtin_amdgcn_mfma_f32_16x16x16bf16_1k`, `__builtin_amdgcn_mfma_f32_32x32x8f16` and `__builtin_amdgcn_mfma_f32_16x16x16f16` instructions. * Add HIP matrix core support into joint_matrix documentation. Should be merged after - #11215 --------- Co-authored-by: Bing1 Yu <[email protected]> Co-authored-by: mmoadeli <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
__gfx90a__architecture.__builtin_amdgcn_mfma_i32_32x32x8i8,__builtin_amdgcn_mfma_i32_16x16x16i8,__builtin_amdgcn_mfma_f64_16x16x4f64,__builtin_amdgcn_mfma_f32_32x32x8bf16_1k,__builtin_amdgcn_mfma_f32_16x16x16bf16_1k,__builtin_amdgcn_mfma_f32_32x32x8f16and__builtin_amdgcn_mfma_f32_16x16x16f16instructions.Should be merged after