altis
altis copied to clipboard
A benchmarking suite for heterogeneous systems. The primary goal of this project is to improve and update aspects of existing benchmarking suites which are either insufficient or outdated.
My system specifications: GPU : NVIDIA GeForce RTX 2080 CUDA Version: 12.2 -------- I tried the following steps: ``` $ git clone "https://github.com/utcs-scea/altis" $ cd altis/ $ ./setup.sh -- The...
I tried to build the benchmark and the compiler reports the errors cd yolo/src nvcc -I../include -O3 *.c *.cu ``` compare.c: In function ‘train_compare’: compare.c:17:19: error: invalid initializer 17 |...
Hi, I'm trying to build Altis on my server and on docker container, but both encounter the same errors. The following descriptions only show a part of the error messages....
./gemm -s 5 --passes 30 --uvm Chose device: name='NVIDIA GeForce RTX 3090' index=0 Running GEMM Running single precision test Running double precision test Running half preicsion test /workspace/benchmark/altis/src/cuda/level1/gemm/Gemm.cu(238) : CUDA...
I'm using gtx1650 on my computer, with cuda 11.6, cmake 3.13.0. How can i solve the problem Run Build Command:"/usr/bin/make" "cmTC_a1746/fast" /usr/bin/make -f CMakeFiles/cmTC_a1746.dir/build.make CMakeFiles/cmTC_a1746.dir/build make[1]: Entering directory '/home/ming/gpgpu/altis/CMakeFiles/CMakeTmp' Building...
allows Altis to build with Cuda 10.1's nvcc
has anyone tried using Altis with GPGPUsim I am facing the following error ```cudaGetDeviceCount() failed: CUDA driver version is insufficient for CUDA runtime version cudaGetDeviceCount() failed: CUDA driver version is...
- [x] Upgrade device-memory benchmark to CUDA 12 (eliminate `texture` in favor of `cudaTextureObject_t`); fixes #24 - [x] Auto-detect native SM version