Skip to content

Commit af557f5

Browse files
github-actions[bot]github-actions[bot]
committed
1 parent 7c4b953 commit af557f5

File tree

60 files changed

+3393
-3
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

60 files changed

+3393
-3
lines changed

‎benchmarks/2025-10-07/3cddf7542f04ebcd45d7cafb816055c2f1f70638/deeplearning/dl-layer-ffn-benchmark.html‎

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
2+
<style>
3+
body{font-family:system-ui,Arial,sans-serif;margin:2rem;max-width:80ch}
4+
table{border-collapse:collapse;margin:1rem 0}
5+
th,td{border:1px solid #bbb;padding:.3rem .6rem;text-align:right}
6+
th{text-align:center;background:#f0f0f0}
7+
tr:nth-child(even){background:#fafafa}
8+
details{border:1px solid #ccc;border-radius:.4rem;padding:.6rem}
9+
summary{font-weight:600;cursor:pointer}
10+
.err{border:2px solid #c00;background:#fee;padding:1rem;border-radius:.5rem}
11+
</style>
12+
13+
<h2>deeplearning/dl-layer-ffn-benchmark.json</h2><p><em>2025-10-07 10:45:51 UTC</em></p>
14+
<h3>dl-layer-ffn-benchmark.json</h3>
15+
<table><tr><th>Name</th><th>Time&nbsp;(ms)</th><th>CPU&nbsp;(ms)</th><th>Iterations</th></tr>
16+
<tr><td style='text-align:left'>DL_LAYER_FFN/Scalar</td><td>0.0675</td><td>0.0675</td><td>10,218</td></tr>
17+
<tr><td style='text-align:left'>DL_LAYER_FFN/Auto_Vectorization</td><td>0.0266</td><td>0.0266</td><td>26,193</td></tr></table>
18+
<details><summary>Console output</summary>
19+
<pre></pre></details>

‎benchmarks/2025-10-07/3cddf7542f04ebcd45d7cafb816055c2f1f70638/deeplearning/dl-layer-rmsnorm-benchmark.html‎

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
2+
<style>
3+
body{font-family:system-ui,Arial,sans-serif;margin:2rem;max-width:80ch}
4+
table{border-collapse:collapse;margin:1rem 0}
5+
th,td{border:1px solid #bbb;padding:.3rem .6rem;text-align:right}
6+
th{text-align:center;background:#f0f0f0}
7+
tr:nth-child(even){background:#fafafa}
8+
details{border:1px solid #ccc;border-radius:.4rem;padding:.6rem}
9+
summary{font-weight:600;cursor:pointer}
10+
.err{border:2px solid #c00;background:#fee;padding:1rem;border-radius:.5rem}
11+
</style>
12+
13+
<h2>deeplearning/dl-layer-rmsnorm-benchmark.json</h2><p><em>2025-10-07 10:45:51 UTC</em></p>
14+
<h3>dl-layer-rmsnorm-benchmark.json</h3>
15+
<table><tr><th>Name</th><th>Time&nbsp;(ms)</th><th>CPU&nbsp;(ms)</th><th>Iterations</th></tr>
16+
<tr><td style='text-align:left'>DL_LAYER_RMSNORM/Scalar</td><td>0.00198</td><td>0.00198</td><td>339,474</td></tr>
17+
<tr><td style='text-align:left'>DL_LAYER_RMSNORM/Auto_Vectorization</td><td>0.000892</td><td>0.000892</td><td>780,156</td></tr></table>
18+
<details><summary>Console output</summary>
19+
<pre></pre></details>

‎benchmarks/2025-10-07/3cddf7542f04ebcd45d7cafb816055c2f1f70638/deeplearning/dl-layer-selfattention-benchmark.html‎

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
2+
<style>
3+
body{font-family:system-ui,Arial,sans-serif;margin:2rem;max-width:80ch}
4+
table{border-collapse:collapse;margin:1rem 0}
5+
th,td{border:1px solid #bbb;padding:.3rem .6rem;text-align:right}
6+
th{text-align:center;background:#f0f0f0}
7+
tr:nth-child(even){background:#fafafa}
8+
details{border:1px solid #ccc;border-radius:.4rem;padding:.6rem}
9+
summary{font-weight:600;cursor:pointer}
10+
.err{border:2px solid #c00;background:#fee;padding:1rem;border-radius:.5rem}
11+
</style>
12+
13+
<h2>deeplearning/dl-layer-selfattention-benchmark.json</h2><p><em>2025-10-07 10:45:51 UTC</em></p>
14+
<h3>dl-layer-selfattention-benchmark.json</h3>
15+
<table><tr><th>Name</th><th>Time&nbsp;(ms)</th><th>CPU&nbsp;(ms)</th><th>Iterations</th></tr>
16+
<tr><td style='text-align:left'>DL_LAYER_ATTENTION/Scalar</td><td>4.87</td><td>4.87</td><td>144</td></tr>
17+
<tr><td style='text-align:left'>DL_LAYER_ATTENTION/Auto_Vectorization</td><td>1.59</td><td>1.59</td><td>435</td></tr></table>
18+
<details><summary>Console output</summary>
19+
<pre></pre></details>

‎benchmarks/2025-10-07/3cddf7542f04ebcd45d7cafb816055c2f1f70638/deeplearning/dl-model-lenet-benchmark.html‎

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
2+
<style>
3+
body{font-family:system-ui,Arial,sans-serif;margin:2rem;max-width:80ch}
4+
table{border-collapse:collapse;margin:1rem 0}
5+
th,td{border:1px solid #bbb;padding:.3rem .6rem;text-align:right}
6+
th{text-align:center;background:#f0f0f0}
7+
tr:nth-child(even){background:#fafafa}
8+
details{border:1px solid #ccc;border-radius:.4rem;padding:.6rem}
9+
summary{font-weight:600;cursor:pointer}
10+
.err{border:2px solid #c00;background:#fee;padding:1rem;border-radius:.5rem}
11+
</style>
12+
13+
<h2>deeplearning/dl-model-lenet-benchmark.json</h2><p><em>2025-10-07 10:45:51 UTC</em></p>
14+
<h3>dl-model-lenet-benchmark.json</h3>
15+
<table><tr><th>Name</th><th>Time&nbsp;(ms)</th><th>CPU&nbsp;(ms)</th><th>Iterations</th></tr>
16+
<tr><td style='text-align:left'>DL_MODEL_LENET/Auto_Vectorization</td><td>0.173</td><td>0.173</td><td>4,111</td></tr>
17+
<tr><td style='text-align:left'>DL_MODEL_LENET/Buddy_Vectorization</td><td>0.144</td><td>0.144</td><td>4,846</td></tr></table>
18+
<details><summary>Console output</summary>
19+
<pre></pre></details>

‎benchmarks/2025-10-07/3cddf7542f04ebcd45d7cafb816055c2f1f70638/deeplearning/dl-model-mobilenetv3-benchmark.html‎

Lines changed: 38 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
1+
2+
<style>
3+
body{font-family:system-ui,Arial,sans-serif;margin:2rem;max-width:80ch}
4+
table{border-collapse:collapse;margin:1rem 0}
5+
th,td{border:1px solid #bbb;padding:.3rem .6rem;text-align:right}
6+
th{text-align:center;background:#f0f0f0}
7+
tr:nth-child(even){background:#fafafa}
8+
details{border:1px solid #ccc;border-radius:.4rem;padding:.6rem}
9+
summary{font-weight:600;cursor:pointer}
10+
.err{border:2px solid #c00;background:#fee;padding:1rem;border-radius:.5rem}
11+
</style>
12+
13+
<h2>deeplearning/dl-model-mobilenetv3-benchmark.json</h2><p><em>2025-10-07 10:45:51 UTC</em></p>
14+
<h3>dl-model-mobilenetv3-benchmark.json</h3>
15+
<table><tr><th>Name</th><th>Time&nbsp;(ms)</th><th>CPU&nbsp;(ms)</th><th>Iterations</th></tr>
16+
<tr><td style='text-align:left'>BM_MobileNet_V3/BM_MobileNet_V3_scalar</td><td>39.2</td><td>39.2</td><td>17</td></tr>
17+
<tr><td style='text-align:left'>BM_MobileNet_V3/BM_MobileNet_V3_conv_opt</td><td>34.7</td><td>34.7</td><td>20</td></tr></table>
18+
<details><summary>Console output</summary>
19+
<pre>2025-09-07T12:41:45+00:00
20+
Running ./dl-model-mobilenetv3-benchmark
21+
Run on (24 X 5100 MHz CPU s)
22+
CPU Caches:
23+
L1 Data 48 KiB (x12)
24+
L1 Instruction 32 KiB (x12)
25+
L2 Unified 1280 KiB (x12)
26+
L3 Unified 30720 KiB (x1)
27+
Load Average: 3.67, 4.13, 5.81
28+
***WARNING*** CPU scaling is enabled, the benchmark real time measurements may be noisy and will incur extra overhead.
29+
-----------------------------------------------------------------------------------
30+
Benchmark Time CPU Iterations
31+
-----------------------------------------------------------------------------------
32+
BM_MobileNet_V3/BM_MobileNet_V3_scalar 39.2 ms 39.2 ms 17
33+
BM_MobileNet_V3/BM_MobileNet_V3_conv_opt 34.7 ms 34.7 ms 20
34+
-----------------------------------------------------------
35+
Correctness Verification:
36+
Transform case: PASS
37+
-----------------------------------------------------------
38+
</pre></details>

‎benchmarks/2025-10-07/3cddf7542f04ebcd45d7cafb816055c2f1f70638/deeplearning/dl-model-resnet18-benchmark.html‎

Lines changed: 37 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
1+
2+
<style>
3+
body{font-family:system-ui,Arial,sans-serif;margin:2rem;max-width:80ch}
4+
table{border-collapse:collapse;margin:1rem 0}
5+
th,td{border:1px solid #bbb;padding:.3rem .6rem;text-align:right}
6+
th{text-align:center;background:#f0f0f0}
7+
tr:nth-child(even){background:#fafafa}
8+
details{border:1px solid #ccc;border-radius:.4rem;padding:.6rem}
9+
summary{font-weight:600;cursor:pointer}
10+
.err{border:2px solid #c00;background:#fee;padding:1rem;border-radius:.5rem}
11+
</style>
12+
13+
<h2>deeplearning/dl-model-resnet18-benchmark.json</h2><p><em>2025-10-07 10:45:51 UTC</em></p>
14+
<h3>dl-model-resnet18-benchmark.json</h3>
15+
<table><tr><th>Name</th><th>Time&nbsp;(ms)</th><th>CPU&nbsp;(ms)</th><th>Iterations</th></tr>
16+
<tr><td style='text-align:left'>DL_MODEL_Resnet18/Auto_Vectorization</td><td>767</td><td>767</td><td>1</td></tr>
17+
<tr><td style='text-align:left'>DL_MODEL_Resnet18/Buddy_Vectorization</td><td>771</td><td>770</td><td>1</td></tr></table>
18+
<details><summary>Console output</summary>
19+
<pre>2025-09-07T12:45:27+00:00
20+
Running ./dl-model-resnet18-benchmark
21+
Run on (24 X 5100 MHz CPU s)
22+
CPU Caches:
23+
L1 Data 48 KiB (x12)
24+
L1 Instruction 32 KiB (x12)
25+
L2 Unified 1280 KiB (x12)
26+
L3 Unified 30720 KiB (x1)
27+
Load Average: 2.48, 3.42, 5.17
28+
***WARNING*** CPU scaling is enabled, the benchmark real time measurements may be noisy and will incur extra overhead.
29+
--------------------------------------------------------------------------------
30+
Benchmark Time CPU Iterations
31+
--------------------------------------------------------------------------------
32+
DL_MODEL_Resnet18/Auto_Vectorization 767 ms 767 ms 1
33+
DL_MODEL_Resnet18/Buddy_Vectorization 771 ms 770 ms 1
34+
-----------------------------------------------------------
35+
Correctness Verification: PASS
36+
-----------------------------------------------------------
37+
</pre></details>

‎benchmarks/2025-10-07/3cddf7542f04ebcd45d7cafb816055c2f1f70638/deeplearning/dl-model-tinyllama-benchmark.html‎

Lines changed: 39 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,39 @@
1+
2+
<style>
3+
body{font-family:system-ui,Arial,sans-serif;margin:2rem;max-width:80ch}
4+
table{border-collapse:collapse;margin:1rem 0}
5+
th,td{border:1px solid #bbb;padding:.3rem .6rem;text-align:right}
6+
th{text-align:center;background:#f0f0f0}
7+
tr:nth-child(even){background:#fafafa}
8+
details{border:1px solid #ccc;border-radius:.4rem;padding:.6rem}
9+
summary{font-weight:600;cursor:pointer}
10+
.err{border:2px solid #c00;background:#fee;padding:1rem;border-radius:.5rem}
11+
</style>
12+
13+
<h2>deeplearning/dl-model-tinyllama-benchmark.json</h2><p><em>2025-10-07 10:45:51 UTC</em></p>
14+
<h3>dl-model-tinyllama-benchmark.json</h3>
15+
<table><tr><th>Name</th><th>Time&nbsp;(ms)</th><th>CPU&nbsp;(ms)</th><th>Iterations</th></tr>
16+
<tr><td style='text-align:left'>DL_MODEL_TINYLLAMA/scalar</td><td>1.71e+05</td><td>1.71e+05</td><td>1</td></tr>
17+
<tr><td style='text-align:left'>DL_MODEL_TINYLLAMA/matmul_opt</td><td>1.11e+04</td><td>1.11e+04</td><td>1</td></tr>
18+
<tr><td style='text-align:left'>DL_MODEL_TINYLLAMA/matmul_opt_omp</td><td>8.33e+03</td><td>7.73e+03</td><td>1</td></tr></table>
19+
<details><summary>Console output</summary>
20+
<pre>2025-09-07T12:35:22+00:00
21+
Running ./dl-model-tinyllama-benchmark
22+
Run on (24 X 5100 MHz CPU s)
23+
CPU Caches:
24+
L1 Data 48 KiB (x12)
25+
L1 Instruction 32 KiB (x12)
26+
L2 Unified 1280 KiB (x12)
27+
L3 Unified 30720 KiB (x1)
28+
Load Average: 4.90, 5.53, 6.99
29+
***WARNING*** CPU scaling is enabled, the benchmark real time measurements may be noisy and will incur extra overhead.
30+
----------------------------------------------------------------------------
31+
Benchmark Time CPU Iterations
32+
----------------------------------------------------------------------------
33+
DL_MODEL_TINYLLAMA/scalar 171201 ms 171198 ms 1
34+
DL_MODEL_TINYLLAMA/matmul_opt 11144 ms 11135 ms 1
35+
DL_MODEL_TINYLLAMA/matmul_opt_omp 8335 ms 7733 ms 1
36+
---------- Verification ----------
37+
matmul_opt PASS
38+
matmul_opt_omp PASS
39+
</pre></details>

‎benchmarks/2025-10-07/3cddf7542f04ebcd45d7cafb816055c2f1f70638/deeplearning/dl-model-whisper-benchmark.html‎

Lines changed: 34 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,34 @@
1+
2+
<style>
3+
body{font-family:system-ui,Arial,sans-serif;margin:2rem;max-width:80ch}
4+
table{border-collapse:collapse;margin:1rem 0}
5+
th,td{border:1px solid #bbb;padding:.3rem .6rem;text-align:right}
6+
th{text-align:center;background:#f0f0f0}
7+
tr:nth-child(even){background:#fafafa}
8+
details{border:1px solid #ccc;border-radius:.4rem;padding:.6rem}
9+
summary{font-weight:600;cursor:pointer}
10+
.err{border:2px solid #c00;background:#fee;padding:1rem;border-radius:.5rem}
11+
</style>
12+
13+
<h2>deeplearning/dl-model-whisper-benchmark.json</h2><p><em>2025-10-07 10:45:51 UTC</em></p>
14+
<h3>dl-model-whisper-benchmark.json</h3>
15+
<table><tr><th>Name</th><th>Time&nbsp;(ms)</th><th>CPU&nbsp;(ms)</th><th>Iterations</th></tr>
16+
<tr><td style='text-align:left'>DL_MODEL_Whisper/Auto_Vectorization</td><td>8.83e+04</td><td>8.83e+04</td><td>1</td></tr>
17+
<tr><td style='text-align:left'>DL_MODEL_Whisper/Buddy_Vectorization</td><td>4.05e+04</td><td>4.05e+04</td><td>1</td></tr></table>
18+
<details><summary>Console output</summary>
19+
<pre>2025-09-07T12:41:50+00:00
20+
Running ./dl-model-whisper-benchmark
21+
Run on (24 X 5100 MHz CPU s)
22+
CPU Caches:
23+
L1 Data 48 KiB (x12)
24+
L1 Instruction 32 KiB (x12)
25+
L2 Unified 1280 KiB (x12)
26+
L3 Unified 30720 KiB (x1)
27+
Load Average: 3.70, 4.13, 5.80
28+
***WARNING*** CPU scaling is enabled, the benchmark real time measurements may be noisy and will incur extra overhead.
29+
-------------------------------------------------------------------------------
30+
Benchmark Time CPU Iterations
31+
-------------------------------------------------------------------------------
32+
DL_MODEL_Whisper/Auto_Vectorization 88295 ms 88293 ms 1
33+
DL_MODEL_Whisper/Buddy_Vectorization 40466 ms 40458 ms 1
34+
</pre></details>

‎benchmarks/2025-10-07/3cddf7542f04ebcd45d7cafb816055c2f1f70638/deeplearning/dl-op-linalg-arithaddf-benchmark.html‎

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
2+
<style>
3+
body{font-family:system-ui,Arial,sans-serif;margin:2rem;max-width:80ch}
4+
table{border-collapse:collapse;margin:1rem 0}
5+
th,td{border:1px solid #bbb;padding:.3rem .6rem;text-align:right}
6+
th{text-align:center;background:#f0f0f0}
7+
tr:nth-child(even){background:#fafafa}
8+
details{border:1px solid #ccc;border-radius:.4rem;padding:.6rem}
9+
summary{font-weight:600;cursor:pointer}
10+
.err{border:2px solid #c00;background:#fee;padding:1rem;border-radius:.5rem}
11+
</style>
12+
13+
<h2>deeplearning/dl-op-linalg-arithaddf-benchmark.json</h2><p><em>2025-10-07 10:45:51 UTC</em></p>
14+
<h3>dl-op-linalg-arithaddf-benchmark.json</h3>
15+
<table><tr><th>Name</th><th>Time&nbsp;(ms)</th><th>CPU&nbsp;(ms)</th><th>Iterations</th></tr>
16+
<tr><td style='text-align:left'>BM_ADDF_SCALAR</td><td>0.0311</td><td>0.0311</td><td>22,527</td></tr>
17+
<tr><td style='text-align:left'>BM_ADDF_AutoVectorization</td><td>0.00488</td><td>0.00488</td><td>169,988</td></tr></table>
18+
<details><summary>Console output</summary>
19+
<pre></pre></details>

‎benchmarks/2025-10-07/3cddf7542f04ebcd45d7cafb816055c2f1f70638/deeplearning/dl-op-linalg-arithdivf-benchmark.html‎

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
2+
<style>
3+
body{font-family:system-ui,Arial,sans-serif;margin:2rem;max-width:80ch}
4+
table{border-collapse:collapse;margin:1rem 0}
5+
th,td{border:1px solid #bbb;padding:.3rem .6rem;text-align:right}
6+
th{text-align:center;background:#f0f0f0}
7+
tr:nth-child(even){background:#fafafa}
8+
details{border:1px solid #ccc;border-radius:.4rem;padding:.6rem}
9+
summary{font-weight:600;cursor:pointer}
10+
.err{border:2px solid #c00;background:#fee;padding:1rem;border-radius:.5rem}
11+
</style>
12+
13+
<h2>deeplearning/dl-op-linalg-arithdivf-benchmark.json</h2><p><em>2025-10-07 10:45:51 UTC</em></p>
14+
<h3>dl-op-linalg-arithdivf-benchmark.json</h3>
15+
<table><tr><th>Name</th><th>Time&nbsp;(ms)</th><th>CPU&nbsp;(ms)</th><th>Iterations</th></tr>
16+
<tr><td style='text-align:left'>BM_DIVF_SCALAR</td><td>0.0321</td><td>0.0321</td><td>22,003</td></tr>
17+
<tr><td style='text-align:left'>BM_DIVF_AutoVectorization</td><td>0.0106</td><td>0.0106</td><td>69,823</td></tr></table>
18+
<details><summary>Console output</summary>
19+
<pre></pre></details>

0 commit comments

Comments
 (0)