mirror of
https://github.com/slsdetectorgroup/aare.git
synced 2026-11-10 21:23:55 +01:00
Add nsys probe scripts for ClusterFinderCUDA
Per-engine GPU time, duty cycle and roofline on the campaign configs (3x3 cap 3000, 9x9 cap 1700, 1 and 4 streams, 20k frames).
This commit is contained in:
kferjaoui committed
1 parent
5d20e1d65e
commit
da3f563872
10 files changed
+535
-11
No files matched your search
@@ -141,7 +141,7 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Pedestal (1000 frames): 1.23s\n"
|
||||
"Pedestal (1000 frames): 1.34s\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -175,7 +175,7 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Reading 100000 frames: 33.56s (2,980 FPS, 32.00 GB at 0.95 GB/s)\n"
|
||||
"Reading 100000 frames: 82.39s (1,214 FPS, 32.00 GB at 0.39 GB/s)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -207,14 +207,14 @@
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████████████████████████████████████████████| 100000/100000 [00:23<00:00, 4249.96it/s]\n"
|
||||
"100%|██████████████████████████████████████████████████| 100000/100000 [00:23<00:00, 4191.14it/s]\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"CPU MT (24 threads): 23.53s 4,249 FPS 233,099,227 clusters (2331.0/frame)\n"
|
||||
"CPU MT (24 threads): 23.86s 4,190 FPS 233,099,227 clusters (2331.0/frame)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -309,10 +309,10 @@
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
" s FPS us/frame clusters\n",
|
||||
"CPU MT (24 thr) 23.53 4,249 235.3 233,099,227\n",
|
||||
"CUDA batched 3.53 28,325 35.3 233,093,554\n",
|
||||
"CPU MT (24 thr) 23.86 4,190 238.6 233,099,227\n",
|
||||
"CUDA batched 3.34 29,926 33.4 233,093,554\n",
|
||||
"\n",
|
||||
"speedup: 6.67x\n"
|
||||
"speedup: 7.14x\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -413,10 +413,26 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 10,
|
||||
"id": "sets",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"CPU 233,099,227 clusters\n",
|
||||
"CUDA 233,093,554 clusters net -5,673 (0.0024%)\n",
|
||||
"\n",
|
||||
"exact-position mismatches CPU-only 135,742 CUDA-only 130,069\n",
|
||||
" of which shifted by 1 px 104,347 104,198\n",
|
||||
" genuine add / drop 31,395 25,871\n",
|
||||
"\n",
|
||||
"frames touched by a genuine difference: 41,569 of 100,000\n",
|
||||
"[40.6s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"def cluster_keys(vectors):\n",
|
||||
" \"\"\"One int64 key per cluster: frame * rows*cols + y * cols + x.\n",
|
||||
@@ -501,10 +517,29 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 11,
|
||||
"id": "drift",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"image/png":
|
||||
"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 truncated
|
||||
"text/plain": [
|
||||
"<Figure size 900x360 with 1 Axes>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"first half: -2,032 second half: -3,641\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"cnt_cpu = np.bincount(fr_cpu, minlength=N)\n",
|
||||
"cnt_cuda = np.bincount(fr_cuda, minlength=N)\n",
|
||||
|
||||
Reference in new issue
Block a user