NVIDIA Data Center GPUs

Name bits/s Bytes/s
SanDisk Extreme SSD   550MB/s read
USB 3.1 Gen 2 10Gb/s 1.25GB/s
HDMI 10Gb/s 1.25GB/s
HDMI 4K 18Gb/s 2.25GB/s
M1 Macbook Pro 1TB SSD   7.4GB/s read
M1 Pro Memory   200GB/s
M1 Max Memory   400GB/s
NVLink(A100)   600GB/s
HBM(A100 40G)   1.5TB/s
HBM(A100 80G)   1.9TB/s

V100, A100, H100

Streaming Multiprocessor (SM), Compute Unit (AMD)


Compute Nodes: 40ea DGX A100 system(8x A100)

A100 80GB부터는 VRAM이 80GB. V100까지는 16/32GB까지만 제공되어 insufficient memory error가 잦았다.

$ nvidia-smi topo --matrix
	GPU0	GPU1	GPU2	GPU3	GPU4	GPU5	GPU6	GPU7	CPU Affinity	NUMA Affinity
GPU0	 X 	NV1	NV1	NV2	NV2	PHB	PHB	PHB	0-63	0-1
GPU1	NV1	 X 	NV2	NV1	PHB	NV2	PHB	PHB	0-63	0-1
GPU2	NV1	NV2	 X 	NV2	PHB	PHB	NV1	PHB	0-63	0-1
GPU3	NV2	NV1	NV2	 X 	PHB	PHB	PHB	NV1	0-63	0-1
GPU4	NV2	PHB	PHB	PHB	 X 	NV1	NV1	NV2	0-63	0-1
GPU5	PHB	NV2	PHB	PHB	NV1	 X 	NV2	NV1	0-63	0-1
GPU6	PHB	PHB	NV1	PHB	NV1	NV2	 X 	NV2	0-63	0-1
GPU7	PHB	PHB	PHB	NV1	NV2	NV1	NV2	 X 	0-63	0-1


  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks

Last Modified: 2024/04/29 09:55:08

is a collection of Papers I have written.
© 2000 - Sang Park Except where otherwise noted, content on this site is licensed under a CC BY 4.0.
This site design was brought from Distill.