File tree 4 files changed +21
-8
lines changed
test/e2e_test_requirements
test-e2e/KernelAndProgram
4 files changed +21
-8
lines changed Original file line number Diff line number Diff line change 1
- // for CUDA and HIP the failure happens at compile time, not during runtime
2
1
// UNSUPPORTED: target-nvidia || target-amd
2
+ // UNSUPPORTED-INTENDED: The test looks for an exception thrown during the
3
+ // compilation of the kernel, but for CUDA the failure is not thrown, but comes
4
+ // from ptxas that crashes clang. The JIT part is not relevant, because the
5
+ // flow is such that the AOT compilation still happens, it’s just that if we
6
+ // request JIT, it will do the thing again at the run time.
7
+ //
3
8
// TODO: rewrite this into a unit-test
4
9
5
10
// RUN: %{build} -DGPU -o %t_gpu.out
Original file line number Diff line number Diff line change 1
- // for CUDA and HIP the failure happens at compile time, not during runtime
2
- // UNSUPPORTED: target-nvidia || target-amd || ze_debug
1
+ // UNSUPPORTED: target-nvidia || target-amd
2
+ // UNSUPPORTED-INTENDED: The test looks for an exception thrown during the
3
+ // compilation of the kernel, but for CUDA the failure is not thrown, but comes
4
+ // from ptxas that crashes clang. The JIT part is not relevant, because the
5
+ // flow is such that the AOT compilation still happens, it’s just that if we
6
+ // request JIT, it will do the thing again at the run time.
7
+ //
8
+ // UNSUPPORTED: ze_debug
3
9
4
10
// RUN: %{build} -DSYCL_DISABLE_FALLBACK_ASSERT=1 -o %t.out
5
11
// RUN: %{build} -DSYCL_DISABLE_FALLBACK_ASSERT=1 -DGPU -o %t_gpu.out
Original file line number Diff line number Diff line change 1
- // for CUDA and HIP the failure happens at compile time, not during runtime
2
1
// UNSUPPORTED: target-nvidia || target-amd
3
-
2
+ // UNSUPPORTED-INTENDED: The test looks for an exception thrown during the
3
+ // compilation of the kernel, but for CUDA the failure is not thrown, but comes
4
+ // from ptxas that crashes clang. The JIT part is not relevant, because the
5
+ // flow is such that the AOT compilation still happens, it’s just that if we
6
+ // request JIT, it will do the thing again at the run time.
7
+ //
4
8
// RUN: %{build} -o %t.out
5
9
// RUN: %{run} %t.out
6
10
//
Original file line number Diff line number Diff line change 54
54
// tests to match the required format and in that case you should just update
55
55
// (i.e. reduce) the number and the list below.
56
56
//
57
- // NUMBER-OF-UNSUPPORTED-WITHOUT-INFO: 282
57
+ // NUMBER-OF-UNSUPPORTED-WITHOUT-INFO: 280
58
58
//
59
59
// List of improperly UNSUPPORTED tests.
60
60
// Remove the CHECK once the test has been properly UNSUPPORTED.
208
208
// CHECK-NEXT: InvokeSimd/Feature/popcnt.cpp
209
209
// CHECK-NEXT: InvokeSimd/Regression/ImplicitSubgroup/call_vadd_1d_spill.cpp
210
210
// CHECK-NEXT: InvokeSimd/Regression/call_vadd_1d_spill.cpp
211
- // CHECK-NEXT: KernelAndProgram/build-log.cpp
212
211
// CHECK-NEXT: KernelAndProgram/cache-build-result.cpp
213
212
// CHECK-NEXT: KernelAndProgram/free_function_apis.cpp
214
213
// CHECK-NEXT: KernelAndProgram/free_function_kernels.cpp
218
217
// CHECK-NEXT: KernelAndProgram/multiple-kernel-linking.cpp
219
218
// CHECK-NEXT: KernelAndProgram/spec_constants_after_link.cpp
220
219
// CHECK-NEXT: KernelAndProgram/spec_constants_after_link.cpp
221
- // CHECK-NEXT: KernelAndProgram/undefined-symbol.cpp
222
220
// CHECK-NEXT: Matrix/SG32/element_wise_abc.cpp
223
221
// CHECK-NEXT: Matrix/SG32/element_wise_all_ops.cpp
224
222
// CHECK-NEXT: Matrix/SG32/element_wise_all_ops_half.cpp
You can’t perform that action at this time.
0 commit comments