Skip to content

Instantly share code, notes, and snippets.

@syhw
Created January 12, 2019 16:33
Show Gist options
  • Save syhw/b8067966a498b604b4750e9458f36804 to your computer and use it in GitHub Desktop.
Save syhw/b8067966a498b604b4750e9458f36804 to your computer and use it in GitHub Desktop.
_theoretical_ FLOPS (counting FMA = 2 OPS)
category | model | FLOPS | HPOPS | AVX / cores / cuda cores...
CPU | i9-8950HK (MacBookPro) | 278 GFLOPS | 556 GOPS? | AVX2, 6 cores
CPU | E5-2698 v4 | 704 GFLOPS | 1.4 TOPS? | AVX2, 20 cores
CPU | Xeon Plat. 8160 (~GCP/AWS) | 3.2 TFLOPS | 6.4 TOPS? | AVX512 x2, 24 cores (2.1*24*512/32*2*2)
CPU | Threadripper 2990WX | 1.5 TFLOPS | 3 TOPS? | AVX2, 32 cores (3*32*256/32*2)
GPU | K80 | 8.7 TFLOPS | | 2496 cuda cores x2 (=4992)
GPU | 1080 Ti | 10.6 TFLOPS | | 3584:224:88
GPU | AMD RX Vega 64 | 11.5 TFLOPS | 23 TOPS | 4096:256:64
GPU | M60 | 9.6 TFLOPS | | 2048:128:64 x2 (i.e. x2 GPU dies)
GPU | P100 (NVLink) | 10.6 TFLOPS | 21 TOPS | 3584:224:88?
GPU | V100 (NVLink) | 15.7 TFLOPS | 125 TOPS | 5120:320:128
TPU | TPU v1 (card, = 4 chip) | | 92 TOPS | 1 chip = systolic array 256*256*700mhz/2?
TPU | TPU v2 (card, = 4 chip) | | 180 TOPS | 4x chip
TPU | TPU v3 (card, = 4 chip) | | 420 TOPS | 4x chip
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment