Skip to content

Commit 1b2b55c

Browse files
authored
[Benchmarks][CI] add UR SubmitGraph benchmark (#17853)
``` running graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 0 measureCompletion 0, iteration 0... graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 0 measureCompletion 0 complete (graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 0 measureCompletion 0: 14.738 μs). running graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 0 measureCompletion 1, iteration 0... graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 0 measureCompletion 1 complete (graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 0 measureCompletion 1: 15.132 μs). running graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 0 measureCompletion 0, iteration 0... graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 0 measureCompletion 0 complete (graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 0 measureCompletion 0: 29.481 μs). running graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 0 measureCompletion 1, iteration 0... graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 0 measureCompletion 1 complete (graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 0 measureCompletion 1: 30.309 μs). running graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 0 measureCompletion 0, iteration 0... graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 0 measureCompletion 0 complete (graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 0 measureCompletion 0: 85.288 μs). running graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 0 measureCompletion 1, iteration 0... graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 0 measureCompletion 1 complete (graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 0 measureCompletion 1: 85.948 μs). running graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 1 measureCompletion 0, iteration 0... graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 1 measureCompletion 0 complete (graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 1 measureCompletion 0: 15.483 μs). running graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 1 measureCompletion 1, iteration 0... graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 1 measureCompletion 1 complete (graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 1 measureCompletion 1: 16.589 μs). running graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 1 measureCompletion 0, iteration 0... graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 1 measureCompletion 0 complete (graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 1 measureCompletion 0: 31.217 μs). running graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 1 measureCompletion 1, iteration 0... graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 1 measureCompletion 1 complete (graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 1 measureCompletion 1: 31.615 μs). running graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 1 measureCompletion 0, iteration 0... graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 1 measureCompletion 0 complete (graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 1 measureCompletion 0: 86.204 μs). running graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 1 measureCompletion 1, iteration 0... graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 1 measureCompletion 1 complete (graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 1 measureCompletion 1: 86.468 μs). running graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 0 measureCompletion 0, iteration 0... graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 0 measureCompletion 0 complete (graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 0 measureCompletion 0: 11.087 μs). running graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 0 measureCompletion 1, iteration 0... graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 0 measureCompletion 1 complete (graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 0 measureCompletion 1: 11.178 μs). running graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 0 measureCompletion 0, iteration 0... graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 0 measureCompletion 0 complete (graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 0 measureCompletion 0: 21.347 μs). running graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 0 measureCompletion 1, iteration 0... graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 0 measureCompletion 1 complete (graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 0 measureCompletion 1: 22.886 μs). running graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 0 measureCompletion 0, iteration 0... graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 0 measureCompletion 0 complete (graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 0 measureCompletion 0: 61.907 μs). running graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 0 measureCompletion 1, iteration 0... graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 0 measureCompletion 1 complete (graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 0 measureCompletion 1: 63.073 μs). running graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 1 measureCompletion 0, iteration 0... graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 1 measureCompletion 0 complete (graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 1 measureCompletion 0: 11.016 μs). running graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 1 measureCompletion 1, iteration 0... graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 1 measureCompletion 1 complete (graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 1 measureCompletion 1: 14.501 μs). running graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 1 measureCompletion 0, iteration 0... graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 1 measureCompletion 0 complete (graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 1 measureCompletion 0: 21.556 μs). running graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 1 measureCompletion 1, iteration 0... graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 1 measureCompletion 1 complete (graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 1 measureCompletion 1: 21.254 μs). running graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 1 measureCompletion 0, iteration 0... graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 1 measureCompletion 0 complete (graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 1 measureCompletion 0: 67.115 μs). running graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 1 measureCompletion 1, iteration 0... graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 1 measureCompletion 1 complete (graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 1 measureCompletion 1: 63.078 μs). ```
1 parent f365bf0 commit 1b2b55c

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

devops/scripts/benchmarks/benches/compute.py

+2-2
Original file line numberDiff line numberDiff line change
@@ -46,7 +46,7 @@ def git_url(self) -> str:
4646
return "https://github.com/intel/compute-benchmarks.git"
4747

4848
def git_hash(self) -> str:
49-
return "b5cc46acf61766ab00da04e85bd4da4f7591eb21"
49+
return "c10baa895b4364899e253e44127ff128a8efa5d5"
5050

5151
def setup(self):
5252
if options.sycl is None:
@@ -145,7 +145,7 @@ def benchmarks(self) -> list[Benchmark]:
145145
benches.append(UllsKernelSwitch(self, runtime, 8, 200, 0, 0, 1, 1))
146146

147147
# Add GraphApiSubmitGraph benchmarks
148-
for runtime in self.enabled_runtimes([RUNTIMES.SYCL]):
148+
for runtime in self.enabled_runtimes([RUNTIMES.SYCL, RUNTIMES.UR]):
149149
for in_order_queue in [0, 1]:
150150
for num_kernels in [4, 10, 32]:
151151
for measure_completion_time in [0, 1]:

0 commit comments

Comments
 (0)