Production GPU Clusters

Zone Nodes Total Memory (GB) APU Architecture GPU Architecture Total GPUs GPUs per compute node Cores/ Node Total Cores Memory/ Node GPU peak performance (TFLOP/s double precision) GPU global memory (GB) Switch Peak PFLOPs (GPUs) Peak PFLOPS (CPUs+GPUs)
El Capitan SCF 11,520 5,701,632 AMD MI300A CDNA 3 [APU: AMD MI300A] 44,544 4 96 1,069,056 62.00 512 HPE Slingshot 11 2792.900
Matrix CZ 30 8,064 NVIDIA H100 112 4 112 1,792 504 30.00 320 IB 3.800 4.000
RZAdams RZ 128 65,536 AMD MI300A CDNA 3 [APU: AMD MI300A] 512 4 96 12,288 512 62.00 128 HPE Slingshot 11 31.744 32.102
RZVector RZ 16 8,064 NVIDIA H100 64 4 112 1,792 504 30.00 320 IB
RZVernal RZ 38 16,384 AMD MI-250X 152 4 64 2,432 45.00 128 HPE Slingshot 11 6.840 6.916
RZWhamo RZ 37 9,472 AMD Mi60 64 2 64 2,368 256 24.00 2 Mellanox HDR / Cray Slingshot 0.761 0.843
Tenaya SCF 24 16,384 AMD MI-250X 96 4 64 1,536 512 45.00 128 HPE Slingshot 11 4.320 4.368
Tioga CZ 32 12,288 AMD MI-250X 128 4 64 2,048 512 45.00 128 HPE Slingshot 11 5.760 5.824
Tuolumne CZ 1,152 589,824 AMD MI300A CDNA 3 [APU: AMD MI300A] 4,608 4 96 110,592 68.00 512 HPE Slingshot 11 288.920 294.230
Vertex SCF 40 12,256 NVIDIA Tesla 128 4 16 1,024 383 32 1.003 1.031