Source code of the PPoPP '22 paper: "TileSpGEMM: A Tiled Algorithm for Parallel Sparse General Matrix-Matrix Multiplication on GPUs" by Yuyao Niu, Zhengyang Lu, Haonan Ji, Shuhui Song, Zhou Jin, and Weifeng Liu.
Hi Niu!
You've done a great work in SpGEMM using Tile strategy . While I want to do some experiment in my own environment, I met with some error after 'make'. I'm testing on a NVIDIA GeForce RTX 2080 Ti with compute capacity of 7.5 in unbuntu20.04 with cuda-11.4 .
error output:
@Server:~/TileSpGEMM/src$ make
nvcc -O3 -w -arch=compute_61 -code=sm_75 -gencode=arch=compute_61,code=sm_75 -Xcompiler -fopenmp -Xcompiler -mfma main.cu -o test -I/home/zhanglx/cuda-11.4/include -L/home/zhanglx/cuda-11.4/lib64 -lcudart -lcusparse -D VALUE_TYPE=double
/usr/lib/gcc/x86_64-linux-gnu/9/include/avx512fintrin.h(9146): error: identifier "__builtin_ia32_rndscaless_round" is undefined
/usr/lib/gcc/x86_64-linux-gnu/9/include/avx512fintrin.h(9155): error: identifier "__builtin_ia32_rndscalesd_round" is undefined
/usr/lib/gcc/x86_64-linux-gnu/9/include/avx512fintrin.h(14797): error: identifier "__builtin_ia32_rndscaless_round" is undefined
/usr/lib/gcc/x86_64-linux-gnu/9/include/avx512fintrin.h(14806): error: identifier "__builtin_ia32_rndscalesd_round" is undefined
/usr/lib/gcc/x86_64-linux-gnu/9/include/avx512dqintrin.h(1365): error: identifier "__builtin_ia32_fpclassss" is undefined
/usr/lib/gcc/x86_64-linux-gnu/9/include/avx512dqintrin.h(1372): error: identifier "__builtin_ia32_fpclasssd" is undefined
6 errors detected in the compilation of "main.cu".
make: *** [Makefile:29: make] Error 1
1、maybe it's because of the compute capacity not matching with yours. 2、maybe it's because of the gcc --version not matching.
It would be highly appreciated if you can provide further information of your environment or give me some suggestion to solve the compilation error
Hi Niu! You've done a great work in SpGEMM using Tile strategy . While I want to do some experiment in my own environment, I met with some error after 'make'. I'm testing on a NVIDIA GeForce RTX 2080 Ti with compute capacity of 7.5 in unbuntu20.04 with cuda-11.4 . error output:
1、maybe it's because of the compute capacity not matching with yours. 2、maybe it's because of the gcc --version not matching. It would be highly appreciated if you can provide further information of your environment or give me some suggestion to solve the compilation error