cuda-samples/bin/x86_64/linux/release/APM_matrixMulCUBLAS.txt

13 lines
521 B
Plaintext
Raw Normal View History

2023-03-01 09:41:29 +08:00
[Matrix Multiply CUBLAS] - Starting...
GPU Device 0: "Hopper" with compute capability 9.0
GPU Device 0: "NVIDIA H100 PCIe" with compute capability 9.0
MatrixA(640,480), MatrixB(480,320), MatrixC(640,320)
Computing result using CUBLAS...done.
Performance= 10873.05 GFlop/s, Time= 0.018 msec, Size= 196608000 Ops
Computing result using host CPU...done.
Comparing CUBLAS Matrix Multiply with CPU results: PASS
NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.