mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2024-11-28 14:59:19 +08:00
60 lines
1.9 KiB
Plaintext
60 lines
1.9 KiB
Plaintext
batchCUBLAS Starting...
|
|
|
|
GPU Device 0: "Hopper" with compute capability 9.0
|
|
|
|
|
|
==== Running single kernels ====
|
|
|
|
Testing sgemm
|
|
#### args: ta=0 tb=0 m=128 n=128 k=128 alpha = (0xbf800000, -1) beta= (0x40000000, 2)
|
|
#### args: lda=128 ldb=128 ldc=128
|
|
^^^^ elapsed = 0.00195909 sec GFLOPS=2.14095
|
|
@@@@ sgemm test OK
|
|
Testing dgemm
|
|
#### args: ta=0 tb=0 m=128 n=128 k=128 alpha = (0x0000000000000000, 0) beta= (0x0000000000000000, 0)
|
|
#### args: lda=128 ldb=128 ldc=128
|
|
^^^^ elapsed = 0.00003910 sec GFLOPS=107.269
|
|
@@@@ dgemm test OK
|
|
|
|
==== Running N=10 without streams ====
|
|
|
|
Testing sgemm
|
|
#### args: ta=0 tb=0 m=128 n=128 k=128 alpha = (0xbf800000, -1) beta= (0x00000000, 0)
|
|
#### args: lda=128 ldb=128 ldc=128
|
|
^^^^ elapsed = 0.00016713 sec GFLOPS=250.958
|
|
@@@@ sgemm test OK
|
|
Testing dgemm
|
|
#### args: ta=0 tb=0 m=128 n=128 k=128 alpha = (0xbff0000000000000, -1) beta= (0x0000000000000000, 0)
|
|
#### args: lda=128 ldb=128 ldc=128
|
|
^^^^ elapsed = 0.00144100 sec GFLOPS=29.1069
|
|
@@@@ dgemm test OK
|
|
|
|
==== Running N=10 with streams ====
|
|
|
|
Testing sgemm
|
|
#### args: ta=0 tb=0 m=128 n=128 k=128 alpha = (0x40000000, 2) beta= (0x40000000, 2)
|
|
#### args: lda=128 ldb=128 ldc=128
|
|
^^^^ elapsed = 0.00017214 sec GFLOPS=243.659
|
|
@@@@ sgemm test OK
|
|
Testing dgemm
|
|
#### args: ta=0 tb=0 m=128 n=128 k=128 alpha = (0xbff0000000000000, -1) beta= (0x0000000000000000, 0)
|
|
#### args: lda=128 ldb=128 ldc=128
|
|
^^^^ elapsed = 0.00014997 sec GFLOPS=279.685
|
|
@@@@ dgemm test OK
|
|
|
|
==== Running N=10 batched ====
|
|
|
|
Testing sgemm
|
|
#### args: ta=0 tb=0 m=128 n=128 k=128 alpha = (0x3f800000, 1) beta= (0xbf800000, -1)
|
|
#### args: lda=128 ldb=128 ldc=128
|
|
^^^^ elapsed = 0.00004101 sec GFLOPS=1022.8
|
|
@@@@ sgemm test OK
|
|
Testing dgemm
|
|
#### args: ta=0 tb=0 m=128 n=128 k=128 alpha = (0xbff0000000000000, -1) beta= (0x4000000000000000, 2)
|
|
#### args: lda=128 ldb=128 ldc=128
|
|
^^^^ elapsed = 0.00004506 sec GFLOPS=930.803
|
|
@@@@ dgemm test OK
|
|
|
|
Test Summary
|
|
0 error(s)
|