Add 'projects/rccl/' from commit '1f2f9f33bac3e8ecfd84c69af6063d7352c362fc'

git-subtree-dir: projects/rccl
git-subtree-mainline: 3fd8a0d393
git-subtree-split: 1f2f9f33ba
Esse commit está contido em:
Ameya Keshava Mallya
2025-12-11 20:46:05 +00:00
682 arquivos alterados com 293338 adições e 0 exclusões
@@ -0,0 +1,24 @@
collective,size_bytes,algorithm,protocol,channels,nodes,ranks,pipeOps,regBuff,cost_metric,bandwidth_gbps,latency_us
allreduce,1024,tree,simple,2,1,8,-1,-1,0.15,45.2,12.5
allreduce,1024,ring,simple,4,1,8,-1,-1,0.12,52.1,10.8
allreduce,1024,tree,ll,2,1,8,-1,-1,0.18,41.3,15.2
allreduce,1024,ring,ll,4,1,8,-1,-1,0.14,48.7,12.1
allreduce,32768,tree,simple,2,1,8,-1,-1,0.25,156.8,25.3
allreduce,32768,ring,simple,4,1,8,-1,-1,0.18,189.2,18.4
allreduce,32768,ring,ll128,8,1,8,-1,-1,0.16,201.5,16.2
allreduce,1048576,ring,simple,4,1,8,-1,-1,0.45,425.6,45.1
allreduce,1048576,ring,ll128,8,1,8,-1,-1,0.38,482.3,38.7
allreduce,1048576,nvls,simple,16,1,8,-1,-1,0.32,551.2,32.1
broadcast,1024,tree,simple,2,1,8,-1,-1,0.08,89.4,8.2
broadcast,1024,ring,simple,4,1,8,-1,-1,0.12,71.3,12.1
broadcast,32768,tree,simple,2,1,8,-1,-1,0.18,234.7,18.5
broadcast,32768,ring,ll128,4,1,8,-1,-1,0.15,267.8,15.2
broadcast,1048576,ring,simple,4,1,8,-1,-1,0.35,612.4,35.1
broadcast,1048576,ring,ll128,8,1,8,-1,-1,0.28,702.1,28.3
allreduce,1024,tree,simple,2,2,16,-1,-1,0.22,38.1,22.4
allreduce,1024,ring,simple,4,2,16,-1,-1,0.19,42.7,19.6
allreduce,32768,ring,simple,4,2,16,-1,-1,0.28,145.2,28.1
allreduce,32768,ring,ll128,8,2,16,-1,-1,0.24,167.8,24.3
allreduce,1048576,ring,simple,4,2,16,-1,-1,0.58,387.5,58.2
allreduce,1048576,ring,ll128,8,2,16,-1,-1,0.48,456.9,48.1
allreduce,1048576,nvls,simple,16,2,16,-1,-1,0.42,512.6,42.3
1 collective size_bytes algorithm protocol channels nodes ranks pipeOps regBuff cost_metric bandwidth_gbps latency_us
2 allreduce 1024 tree simple 2 1 8 -1 -1 0.15 45.2 12.5
3 allreduce 1024 ring simple 4 1 8 -1 -1 0.12 52.1 10.8
4 allreduce 1024 tree ll 2 1 8 -1 -1 0.18 41.3 15.2
5 allreduce 1024 ring ll 4 1 8 -1 -1 0.14 48.7 12.1
6 allreduce 32768 tree simple 2 1 8 -1 -1 0.25 156.8 25.3
7 allreduce 32768 ring simple 4 1 8 -1 -1 0.18 189.2 18.4
8 allreduce 32768 ring ll128 8 1 8 -1 -1 0.16 201.5 16.2
9 allreduce 1048576 ring simple 4 1 8 -1 -1 0.45 425.6 45.1
10 allreduce 1048576 ring ll128 8 1 8 -1 -1 0.38 482.3 38.7
11 allreduce 1048576 nvls simple 16 1 8 -1 -1 0.32 551.2 32.1
12 broadcast 1024 tree simple 2 1 8 -1 -1 0.08 89.4 8.2
13 broadcast 1024 ring simple 4 1 8 -1 -1 0.12 71.3 12.1
14 broadcast 32768 tree simple 2 1 8 -1 -1 0.18 234.7 18.5
15 broadcast 32768 ring ll128 4 1 8 -1 -1 0.15 267.8 15.2
16 broadcast 1048576 ring simple 4 1 8 -1 -1 0.35 612.4 35.1
17 broadcast 1048576 ring ll128 8 1 8 -1 -1 0.28 702.1 28.3
18 allreduce 1024 tree simple 2 2 16 -1 -1 0.22 38.1 22.4
19 allreduce 1024 ring simple 4 2 16 -1 -1 0.19 42.7 19.6
20 allreduce 32768 ring simple 4 2 16 -1 -1 0.28 145.2 28.1
21 allreduce 32768 ring ll128 8 2 16 -1 -1 0.24 167.8 24.3
22 allreduce 1048576 ring simple 4 2 16 -1 -1 0.58 387.5 58.2
23 allreduce 1048576 ring ll128 8 2 16 -1 -1 0.48 456.9 48.1
24 allreduce 1048576 nvls simple 16 2 16 -1 -1 0.42 512.6 42.3