From a9705f91e208de7f93a68218659bc417c5fb2110 Mon Sep 17 00:00:00 2001
From: Fraser Cormack <fraser@codeplay.com>
Date: Mon, 15 Jul 2024 09:15:09 +0100
Subject: [PATCH 1/2] [SYCL][E2E] Remove XFAIL from one test; fix multi-device
 config

Resolves #14562.
---
 sycl/test-e2e/BFloat16/bfloat16_type.cpp | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sycl/test-e2e/BFloat16/bfloat16_type.cpp b/sycl/test-e2e/BFloat16/bfloat16_type.cpp
index 0aef086807f73..28a07a64fea64 100644
--- a/sycl/test-e2e/BFloat16/bfloat16_type.cpp
+++ b/sycl/test-e2e/BFloat16/bfloat16_type.cpp
@@ -1,4 +1,4 @@
-// RUN: %if any-device-is-cuda %{ %{build} -DUSE_CUDA_SM80=1 -Xsycl-target-backend --cuda-gpu-arch=sm_80 -o %t.out %}
+// RUN: %if any-device-is-cuda %{ %{build} -DUSE_CUDA_SM80=1 -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_80 -o %t.out %}
 // RUN: %if cuda %{ %{run} %t.out %}
 // RUN: %{build} -o %t.out
 // RUN: %{run} %t.out
@@ -7,7 +7,6 @@
 // UNSUPPORTED: accelerator
 
 // FIXME: enable opaque pointers support on CPU.
-// XFAIL: cpu
 
 //==----------- bfloat16_type.cpp - SYCL bfloat16 type test ----------------==//
 //

From 2908aca3e4b598d61258d0a01a33b906f9e2a633 Mon Sep 17 00:00:00 2001
From: Fraser Cormack <fraser@codeplay.com>
Date: Mon, 15 Jul 2024 16:04:42 +0100
Subject: [PATCH 2/2] two more tests

---
 sycl/test-e2e/BFloat16/bfloat16_builtins.cpp              | 6 ++----
 sycl/test-e2e/BFloat16/bfloat16_builtins_cuda_generic.cpp | 4 +---
 2 files changed, 3 insertions(+), 7 deletions(-)

diff --git a/sycl/test-e2e/BFloat16/bfloat16_builtins.cpp b/sycl/test-e2e/BFloat16/bfloat16_builtins.cpp
index b96882aa86851..404191f735bc0 100644
--- a/sycl/test-e2e/BFloat16/bfloat16_builtins.cpp
+++ b/sycl/test-e2e/BFloat16/bfloat16_builtins.cpp
@@ -5,17 +5,15 @@
 // + below sm_80 always uses generic impls
 
 // DEFINE: %{mathflags} = %if cl_options %{/clang:-fno-fast-math%} %else %{-fno-fast-math%}
-// 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: %clangxx -fsycl -fsycl-targets=%{sycl_triple} %if any-device-is-cuda %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --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 %{  %clangxx -fsycl -fpreview-breaking-changes -fsycl-targets=%{sycl_triple} %if any-device-is-cuda %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_80 %} %s -o %t2.out %{mathflags} %}
 // 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.
-// XFAIL: cpu
 #include "bfloat16_builtins.hpp"
 
 int main() {
diff --git a/sycl/test-e2e/BFloat16/bfloat16_builtins_cuda_generic.cpp b/sycl/test-e2e/BFloat16/bfloat16_builtins_cuda_generic.cpp
index 06621c8d001ba..739f9603ccff4 100644
--- a/sycl/test-e2e/BFloat16/bfloat16_builtins_cuda_generic.cpp
+++ b/sycl/test-e2e/BFloat16/bfloat16_builtins_cuda_generic.cpp
@@ -7,13 +7,11 @@
 // DEFINE: %{mathflags} = %if cl_options %{/clang:-fno-fast-math%} %else %{-fno-fast-math%}
 
 // 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 %{  %clangxx -fsycl -fpreview-breaking-changes -fsycl-targets=%{sycl_triple}  -Xsycl-target-backend=nvptx64-nvidia-cuda --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
-// FIXME: enable opaque pointers support on CPU.
-// XFAIL: cpu
 #include "bfloat16_builtins.hpp"
 
 int main() {