GitHub / Bruce-Lee-LY / cuda_back2back_hgemm
Use tensor core to calculate back-to-back HGEMM (half-precision general matrix multiplication) with MMA PTX instruction.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bruce-Lee-LY%2Fcuda_back2back_hgemm
PURL: pkg:github/Bruce-Lee-LY/cuda_back2back_hgemm
Stars: 11
Forks: 2
Open issues: 0
License: mit
Language: Cuda
Size: 854 KB
Dependencies parsed at: Pending
Created at: almost 2 years ago
Updated at: 9 months ago
Pushed at: over 1 year ago
Last synced at: 3 months ago
Topics: back2back-gemm, back2back-hgemm, cublas, cuda, fused-gemm, fused-hgemm, gemm, gpu, hgemm, matrix-multiply, nvidia, tensor-core