most citedDissecting Tensor Cores via Microbenchmarks: Latency, Throughput and Numeric Behaviors

53 citations · 53 across the 1 of their papers we have counts for

collaborators

1 paper

cs.AR2022★ 53 cited

Dissecting Tensor Cores via Microbenchmarks: Latency, Throughput and Numeric Behaviors

Wei Sun, Ang Li, Tong Geng +2

Tensor Cores have been an important unit to accelerate Fused Matrix Multiplication Accumulation (MMA) in all NVIDIA GPUs since Volta Architecture. To program Tensor Cores, users ha…