Skip to content

[SYCL][E2E] Fix some tests in multi-device mode #13510

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 4 commits into from
Jul 11, 2024
Merged

[SYCL][E2E] Fix some tests in multi-device mode #13510

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
56d6e03
[SYCL][E2E] Fix some tests in multi-device mode
frasercrmck Apr 22, 2024
7ce174a
feedback: remove aspect; unsupported cpu
frasercrmck Apr 25, 2024
264a025
Merge remote-tracking branch 'origin/sycl' into fix-cuda-sycl-backend…
frasercrmck Jul 10, 2024
4dd6916
update: xfail another test
frasercrmck Jul 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
4 changes: 2 additions & 2 deletions sycl/test-e2e/BFloat16/bfloat16_builtins.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,6 @@
// + below sm_80 always uses generic impls

// DEFINE: %{mathflags} = %if cl_options %{/clang:-fno-fast-math%} %else %{-fno-fast-math%}
// REQUIRES: aspect-ext_oneapi_bfloat16_math_functions
// RUN: %clangxx -fsycl -fsycl-targets=%{sycl_triple} %if any-device-is-cuda %{ -Xsycl-target-backend --cuda-gpu-arch=sm_80 %} %s -o %t.out %{mathflags}
// RUN: %{run} %t.out

Expand All @@ -14,7 +13,8 @@
// RUN: %if preview-breaking-changes-supported %{ %{run} %t2.out %}

// Currently the feature isn't supported on FPGA.
// UNSUPPORTED: accelerator
// FIXME: enable opaque pointers support on CPU.
// UNSUPPORTED: accelerator, cpu
#include "bfloat16_builtins.hpp"

int main() {
Expand Down
15 changes: 0 additions & 15 deletions sycl/test-e2e/BFloat16/bfloat16_builtins.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,21 +4,6 @@
// + sm_80 and above uses some native bfloat16 math instructions
// + below sm_80 always uses generic impls

// DEFINE: %{mathflags} = %if cl_options %{/clang:-fno-fast-math%} %else %{-fno-fast-math%}
// REQUIRES: aspect-ext_oneapi_bfloat16_math_functions
// RUN: %clangxx -fsycl -fsycl-targets=%{sycl_triple} %if any-device-is-cuda %{ -Xsycl-target-backend --cuda-gpu-arch=sm_80 %} %s -o %t.out %{mathflags}
// RUN: %{run} %t.out

// Test "new" (ABI breaking) for all platforms ( sm_80/native if CUDA )
// RUN: %if preview-breaking-changes-supported %{ %clangxx -fsycl -fpreview-breaking-changes -fsycl-targets=%{sycl_triple} %if any-device-is-cuda %{ -Xsycl-target-backend --cuda-gpu-arch=sm_80 %} %s -o %t2.out %{mathflags} %}
// RUN: %if preview-breaking-changes-supported %{ %{run} %t2.out %}

// If CUDA, test "new" again for sm_75/generic
// RUN: %if any-device-is-cuda %{ %if preview-breaking-changes-supported %{ %clangxx -fsycl -fpreview-breaking-changes -fsycl-targets=%{sycl_triple} -Xsycl-target-backend --cuda-gpu-arch=sm_75 %s -o %t3.out %{mathflags} %} %}
// RUN: %if any-device-is-cuda %{ %if preview-breaking-changes-supported %{ %{run} %t3.out %} %}

// Currently the feature isn't supported on FPGA.
// UNSUPPORTED: accelerator
#include <sycl/sycl.hpp>

#include <cmath>
Expand Down
3 changes: 2 additions & 1 deletion sycl/test-e2e/BFloat16/bfloat16_builtins_cuda_generic.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,8 @@
// RUN: %if any-device-is-cuda %{ %if preview-breaking-changes-supported %{ %{run} %t3.out %} %}

// Currently the feature isn't supported on FPGA.
// UNSUPPORTED: accelerator
// FIXME: enable opaque pointers support on CPU.
// UNSUPPORTED: accelerator, cpu
#include "bfloat16_builtins.hpp"

int main() {
Expand Down
2 changes: 1 addition & 1 deletion sycl/test-e2e/syclcompat/atomic/atomic_class.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@

// UNSUPPORTED: hip || (windows && level_zero)

// RUN: %clangxx -std=c++20 -fsycl -fsycl-targets=%{sycl_triple} %if any-device-is-cuda %{ -Xsycl-target-backend --cuda-gpu-arch=sm_70 %} %s -o %t.out
// RUN: %clangxx -std=c++20 -fsycl -fsycl-targets=%{sycl_triple} %if any-device-is-cuda %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_70 %} %s -o %t.out
// RUN: %{run} %t.out

#include <sycl/sycl.hpp>
Expand Down
2 changes: 1 addition & 1 deletion sycl/test-e2e/syclcompat/atomic/atomic_memory_acq_rel.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@

// UNSUPPORTED: hip

// RUN: %clangxx -fsycl -fsycl-targets=%{sycl_triple} %if any-device-is-cuda %{ -Xsycl-target-backend --cuda-gpu-arch=sm_70 %} %s -o %t.out
// RUN: %clangxx -fsycl -fsycl-targets=%{sycl_triple} %if any-device-is-cuda %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_70 %} %s -o %t.out
// RUN: %{run} %t.out

#include <iostream>
Expand Down
Loading