From 58c4559e233d0fde0dd4eb6cd7dfd16fcbdbc5ee Mon Sep 17 00:00:00 2001 From: wlandau Date: Sat, 30 Sep 2017 07:40:37 -0400 Subject: [PATCH] Upgrade compute capability I was having problems with Thrust on my Ubuntu box with CUDA 8.0. Then I found BVLC/caffe#138, which contained the solution. Apparently, I just needed to [upgrade the compute capability](https://github.com/BVLC/caffe/issues/138#issuecomment-45017180). --- DESCRIPTION | 2 +- src/Makevars | 6 +++++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/DESCRIPTION b/DESCRIPTION index 30aa3dc..7347a28 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -2,7 +2,7 @@ Package: fbseqCUDA Title: fbseqCUDA Description: Internal CUDA code for package fbseq. URL: https://github.com/wlandau/fbseqCUDA -Version: 0.0 +Version: 0.1 Author: Will Landau Maintainer: Will Landau Depends: diff --git a/src/Makevars b/src/Makevars index 3a291a6..061d956 100644 --- a/src/Makevars +++ b/src/Makevars @@ -6,7 +6,11 @@ R_INC = ${R_HOME}/include NVCC = ${CUDA_HOME}/bin/nvcc CUDA_INC = ${CUDA_HOME}/include PKG_LIBS = -L${CUDA_HOME}/lib64 -Wl,-rpath,${CUDA_HOME}/lib64 -lcuda -lcudart -NVCC_FLAGS = -x cu -I${R_INC} -Xcompiler "-fPIC" -gencode arch=compute_20,code=sm_20 -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 +NVCC_FLAGS = --machine 64 -x cu -I${R_INC} -Xcompiler "-fPIC" \ + -gencode arch=compute_30,code=sm_30 \ + -gencode arch=compute_35,code=sm_35 \ + -gencode arch=compute_50,code=sm_50 \ + -gencode arch=compute_50,code=compute_50 OBJECTS= fbseqCUDA.o