derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
223 lines
3.5 KiB
JSON
223 lines
3.5 KiB
JSON
{
|
|
"benchmark_config": {
|
|
"iterations": 1000,
|
|
"cold_iterations": 1000,
|
|
"benchmarks": [
|
|
{
|
|
"name": "gemm",
|
|
"function": "gemm",
|
|
"log_file": "rocblas-gemm_bench.log",
|
|
"dimensions": "sizes",
|
|
"extra_args": {
|
|
"h": {
|
|
"alpha": "1",
|
|
"beta": "0",
|
|
"transposeA": "N"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"name": "gemv",
|
|
"function": "gemv",
|
|
"log_file": "rocblas-gemv_bench.log",
|
|
"dimensions": "separate"
|
|
},
|
|
{
|
|
"name": "ger",
|
|
"function": "ger",
|
|
"log_file": "rocblas-ger_bench.log",
|
|
"dimensions": "separate"
|
|
},
|
|
{
|
|
"name": "dot",
|
|
"function": "dot",
|
|
"log_file": "rocblas-dot_bench.log",
|
|
"dimensions": "simple"
|
|
},
|
|
{
|
|
"name": "gemm_hpa_hgemm",
|
|
"function": "gemm_ex",
|
|
"log_file": "rocblas-gemm_hpa_hgemm_bench.log",
|
|
"dimensions": "sizes",
|
|
"has_compute_type": true
|
|
}
|
|
]
|
|
},
|
|
"gemm": {
|
|
"sizes": [
|
|
2047,
|
|
2048,
|
|
4095,
|
|
4096,
|
|
5503,
|
|
5504,
|
|
5760,
|
|
6143,
|
|
6144,
|
|
7744,
|
|
8191,
|
|
8192
|
|
],
|
|
"transpose": [
|
|
"T",
|
|
"N"
|
|
],
|
|
"precision": [
|
|
"s",
|
|
"d",
|
|
"h"
|
|
],
|
|
"alpha": 1,
|
|
"beta": 0
|
|
},
|
|
"gemv": {
|
|
"m": [
|
|
1000,
|
|
10001
|
|
],
|
|
"n": [
|
|
1000,
|
|
10001
|
|
],
|
|
"lda": [
|
|
1000,
|
|
10002
|
|
],
|
|
"transpose": [
|
|
"N",
|
|
"T"
|
|
],
|
|
"precision": [
|
|
"s",
|
|
"d"
|
|
],
|
|
"gpu_overrides": {
|
|
"gfx110X": {
|
|
"m": [
|
|
30001,
|
|
20001
|
|
],
|
|
"n": [
|
|
30001,
|
|
20001
|
|
],
|
|
"lda": [
|
|
30002,
|
|
20001
|
|
]
|
|
},
|
|
"gfx94X-dcgpu": {
|
|
"m": [
|
|
30001,
|
|
20001
|
|
],
|
|
"n": [
|
|
30001,
|
|
20001
|
|
],
|
|
"lda": [
|
|
30002,
|
|
20001
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"ger": {
|
|
"m": [
|
|
1000,
|
|
10001
|
|
],
|
|
"n": [
|
|
1000,
|
|
10001
|
|
],
|
|
"lda": [
|
|
1000,
|
|
10002
|
|
],
|
|
"precision": [
|
|
"s",
|
|
"d"
|
|
],
|
|
"gpu_overrides": {
|
|
"gfx110X": {
|
|
"m": [
|
|
30001,
|
|
20001
|
|
],
|
|
"n": [
|
|
30001,
|
|
20001
|
|
],
|
|
"lda": [
|
|
30002,
|
|
20001
|
|
]
|
|
},
|
|
"gfx94X-dcgpu": {
|
|
"m": [
|
|
30001,
|
|
20001
|
|
],
|
|
"n": [
|
|
30001,
|
|
20001
|
|
],
|
|
"lda": [
|
|
30002,
|
|
20001
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"dot": {
|
|
"n": [
|
|
1000,
|
|
100001,
|
|
10000002
|
|
],
|
|
"precision": [
|
|
"s",
|
|
"d"
|
|
],
|
|
"gpu_overrides": {
|
|
"gfx110X": {
|
|
"n": [
|
|
1000,
|
|
100000002,
|
|
50000002
|
|
]
|
|
},
|
|
"gfx94X-dcgpu": {
|
|
"n": [
|
|
1000,
|
|
100000002,
|
|
50000002
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"gemm_hpa_hgemm": {
|
|
"sizes": [
|
|
2047,
|
|
2048,
|
|
4095,
|
|
4096,
|
|
5503,
|
|
5504,
|
|
5760,
|
|
6143,
|
|
6144,
|
|
7744,
|
|
8191,
|
|
8192
|
|
],
|
|
"transpose": [
|
|
"T",
|
|
"N"
|
|
],
|
|
"precision": "h",
|
|
"compute_type": "s"
|
|
}
|
|
}
|