Thank you for the quick reply!
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
A40 and 3090 GEMM performance test data | 0 | 1003 | April 11, 2023 | |
Theoretical TFLOPS for FP16, BF16 and TF32 for tensor and non-tensor | 4 | 5581 | June 21, 2022 | |
How to calculate the Tensor Core FP16 performance of H100? | 9 | 6681 | August 14, 2024 | |
How A30 GPU is faster than A10 GPU? | 3 | 6396 | July 5, 2022 | |
Question about tensor cores performance | 3 | 685 | October 12, 2021 | |
A100: 312 TMAC/s or 312 TFLOP/s | 3 | 546 | January 12, 2023 | |
RTX 3090 Peak Performance | 1 | 7929 | December 14, 2021 | |
TF32 GEMM sample very slow compared to generic GEMM | 5 | 798 | June 30, 2022 | |
Double precision tensor core performance on A100 | 1 | 1008 | July 7, 2023 | |
How cuda core compute fp16 data in different nvidia arch? | 8 | 685 | November 25, 2024 |