先輸入:
- sudo vim /etc/profile
然後在該檔案增加下面兩行
- export PATH=/usr/local/cuda-10.0/bin${PATH:+:${PATH}}
- export LD_LIBRARY_PATH=/usr/local/cuda-10.0/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
請輸入,查看是否安裝正確
- nvcc -V
成功的話會出現:
接著切換目錄和編譯:
- cd /usr/local/cuda/samples/7_CUDALibraries/batchCUBLAS/
- sudo make
成功會出現:
"/usr/local/cuda-10.0"/bin/nvcc -ccbin g++ -I../../common/inc -m64 -gencode arch=compute_30,code=compute_30 -o batchCUBLAS.o -c batchCUBLAS.cpp
"/usr/local/cuda-10.0"/bin/nvcc -ccbin g++ -m64 -gencode arch=compute_30,code=compute_30 -o batchCUBLAS batchCUBLAS.o -lcublas
mkdir -p ../../bin/x86_64/linux/release
cp batchCUBLAS ../../bin/x86_64/linux/release
cd /usr/local/cuda/samples/bin/x86_64/linux/release/
./batchCUBLAS
batchCUBLAS Starting...
GPU Device 0: "GeForce GTX 650 Ti" with compute capability 3.0
==== 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 = 0.00007510 sec GFLOPS=55.8482
@@@@ 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 = 0.00013709 sec GFLOPS=30.5951
@@@@ 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 = 0.00040197 sec GFLOPS=104.343
@@@@ 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 = 0.00115895 sec GFLOPS=36.1905
@@@@ 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 = 0.00038314 sec GFLOPS=109.472
@@@@ 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 = 0.00095820 sec GFLOPS=43.7725
@@@@ 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 = 0.00020599 sec GFLOPS=203.613
@@@@ 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 = 0.00105596 sec GFLOPS=39.7204
@@@@ dgemm test OK
Test Summary
0 error(s)
如果有錯誤請輸入:
- ./batchCUBLAS: error while loading shared libraries: libcublas.so.10.0: cannot open shared object file: No such file or directory
- sudo ln -s /usr/local/cuda-10.0/lib64/libcublas.so.10.0 /usr/lib/libcublas.so.10.0
- sudo ln -s /usr/local/cuda-10.0/lib64/libcufft.so.10.0 /usr/lib/libcufft.so.10.0