[SYCL][Matrix] Use KHR cooperative matrix instructions instead of Intel's

[MrSidims]

The usage is currently guarded by __SPIRV_USE_COOPERATIVE_MATRIX macro.

It's a split from #13316

[YuriPlyakhin]

one nit comment from me above. otherwise, LGTM

[againull]

Is it possible to add tests for this new functionality (i.e. for the case when __SPIRV_USE_COOPERATIVE_MATRIX is enabled)?

[MrSidims]

Is it possible to add tests for this new functionality (i.e. for the case when __SPIRV_USE_COOPERATIVE_MATRIX is enabled)?

@againull It's possible and E2E test will be passing in pre-commit on GPU (as pre-commit right now is using the freshest GPU drivers as possible). But it will be failing in nightly as it uses older driver. Also such test won't be passing any time soon on CPU.

For non E2E tests I'll be modifying check_device_code/matrix/matrix_load_store_as.cpp and some of matrix non-E2E tests once #13645 is merged.

Please tell me which option is preferable to you. On my side I'll will be modifying some internal scripts that @YuriPlyakhin has anyway to ensure __SPIRV_USE_COOPERATIVE_MATRIX case is also being validated.

[dkhaldi]

@MrSidims

Please tell me which option is preferable to you. On my side I'll will be modifying some internal scripts that @YuriPlyakhin has anyway to ensure __SPIRV_USE_COOPERATIVE_MATRIX case is also being validated.

The current script works only on PVC.
Will you be able to make them also run on DG2 and SPR?

[againull]

Is it possible to add tests for this new functionality (i.e. for the case when __SPIRV_USE_COOPERATIVE_MATRIX is enabled)?

@againull It's possible and E2E test will be passing in pre-commit on GPU (as pre-commit right now is using the freshest GPU drivers as possible). But it will be failing in nightly as it uses older driver. Also such test won't be passing any time soon on CPU.

For non E2E tests I'll be modifying check_device_code/matrix/matrix_load_store_as.cpp and some of matrix non-E2E tests once #13645 is merged.

Please tell me which option is preferable to you. On my side I'll will be modifying some internal scripts that @YuriPlyakhin has anyway to ensure __SPIRV_USE_COOPERATIVE_MATRIX case is also being validated.

Then in my opinion it will be perfect if we have these E2E tests. It is possible to add REQUIRE statement where you can indicate required minimum driver version and that tests require gpu.

[MrSidims]

Okay, for E2E testing I need to merge #13923 and an extracted llvm-spirv part of #13316

[MrSidims]

@againull apologies for a long delay. I've added the tests. I plan to enable all of the tests for cooperative matrices in the next PR, but first need to have some driver version containing the fix I'm committing right now there.

[YuriPlyakhin]

@MrSidims , If eventually we plan to make SPV Cooperative Matrix a default, I believe, we should enable all Matrix E2E tests in SPVCooperativeMatrix folder, not a subset, to make sure no regressions, when we try to switch the default.

[dkhaldi]

@MrSidims , If eventually we plan to make SPV Cooperative Matrix a default, I believe, we should enable all Matrix E2E tests in SPVCooperativeMatrix folder, not a subset, to make sure no regressions, when we try to switch the default.

Do we really need a new folder?
We can just add a second line of execution with // RUN: %{build} -D__SPIRV_USE_COOPERATIVE_MATRIX -o %t_coop.out
// RUN: %{run} %t_coop.out

To all the existing tests.
I know, to isolate regression, we will need to run both and determine which one is really failing. But since the end goal is to make this the default, it is worthwhile adding the change directly to the tests.

[YuriPlyakhin]

Please, clean-up REQUIRES: gpu that were not present in the original tests here and other tests

Suggested change

	// REQUIRES: gpu, aspect-ext_intel_matrix
	// REQUIRES: aspect-ext_intel_matrix

[MrSidims]

Fixed here an in another cases

[YuriPlyakhin]

Also, it seems you are using outdated set of tests. For example, please compare this file with: https://github.com/intel/llvm/blob/sycl/sycl/test-e2e/Matrix/SG32/joint_matrix_bf16_fill_k_cache.cpp

[MrSidims]

Fixed

[MrSidims]

@YuriPlyakhin went manually through the tests, should be better now.

I've also removed XFAIL from several cpu runs. Few notes: the result of the testing on SPR inconsistent and it depends on the machine I'm running the tests. Not going to internal details: it might make sense. Eventually I expect more tests to pass in the post-commit, so something should be adjusted afterwards.

[YuriPlyakhin]

From my side I only found couple more places to fix.

[dkhaldi]

LGTM except more xfails need to be removed on both cpu and pvc like.
SG32/joint_matrix_apply_two_matrices.cpp

If these are known bugs with the new coop matrix implementation, please create a jira.

[YuriPlyakhin]

LGTM

[MrSidims]

---

Failed Tests (1):
SYCL :: ESIMD/mask_expand_load.cpp

is unrelated.

@intel/llvm-gatekeepers please help with the merge

[steffenlarsen]

Issue reported in #15088.