Skip to content

[SYCL][ESIMD] Use passthrough for mask_expand_load #15664

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 3 commits into from
Oct 11, 2024
Merged

[SYCL][ESIMD] Use passthrough for mask_expand_load #15664

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1e8a8c3
[SYCL][ESIMD] Set passthrough for mask_expand_load
sarnex Oct 10, 2024
49b436b
reenable test on pvc
sarnex Oct 10, 2024
8dd6155
use merge as to not break gen12
sarnex Oct 10, 2024
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
11 changes: 9 additions & 2 deletions sycl/include/sycl/ext/intel/esimd/memory.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14257,7 +14257,10 @@ mask_expand_load(const T *p, simd_mask<N> mask, PropertyListT props = {}) {
// becomes an index for compressed store/expanded load operation.
simd<uint32_t, N> offset =
cbit(simd<uint32_t, N>(offsets::value) & pack_mask(mask));
return gather(p, offset * sizeof(T), mask, props);
simd<T, N> pass_thru = 0;
simd<T, N> res = gather(p, offset * sizeof(T), mask, props);
res.merge(pass_thru, !mask);
return res;
}

/// template <typename T, int N, typename AccessorTy,
Expand Down Expand Up @@ -14305,7 +14308,11 @@ mask_expand_load(AccessorTy acc, uint32_t global_offset, simd_mask<N> mask,
// becomes an index for compressed store/expanded load operation.
simd<uint32_t, N> offset =
cbit(simd<uint32_t, N>(offsets::value) & pack_mask(mask));
return gather<T>(acc, offset * sizeof(T) + global_offset, mask, props);
simd<T, N> pass_thru = 0;
simd<T, N> res =
gather<T>(acc, offset * sizeof(T) + global_offset, mask, props);
res.merge(pass_thru, !mask);
return res;
}

/// template <typename T, int N,
Expand Down
3 changes: 0 additions & 3 deletions sycl/test-e2e/ESIMD/mask_expand_load.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,9 +9,6 @@
// RUN: %{build} -fsycl-device-code-split=per_kernel -o %t.out
// RUN: %{run} %t.out

// https://github.com/intel/llvm/issues/14826
// XFAIL: arch-intel_gpu_pvc

// This is a basic test to validate the expanded load API.

#include "esimd_test_utils.hpp"
Expand Down
Loading