{"id":17,"date":"2009-12-08T11:59:03","date_gmt":"2009-12-08T11:59:03","guid":{"rendered":"http:\/\/blog.soton.ac.uk\/gpgpu\/?p=17"},"modified":"2009-12-08T12:03:53","modified_gmt":"2009-12-08T12:03:53","slug":"hellocl","status":"publish","type":"post","link":"https:\/\/blog.soton.ac.uk\/gpgpu\/2009\/12\/08\/hellocl\/","title":{"rendered":"HelloCL!"},"content":{"rendered":"

(Imagine the post’s title spoken in Leslie Phillips<\/a>‘ drawl. This will probably either amuse you or mean absolutely nothing!)<\/p>\n

OK. It’s party time! I have two Linux boxes, both apparently with OpenCL SDKs, each with a different GPGPU:<\/p>\n

euler – NVidia Tesla 870<\/p>\n

crout – AMD\/ATI FireStream 9270<\/p>\n

The supplied examples work, but they have vendor-specific bits. Can I get a “pure” OpenCL program to compile and run (without modification) on both machines?<\/p>\n

Apple provide an example<\/a> that sets up the environment and runs a small kernel. I had two make two fixes:<\/p>\n

#ifdef __APPLE__
\n#include <OpenCL\/opencl.h>
\n#else
\n#include <CL\/cl.h>
\n#endif<\/p>\n

instead of simply<\/p>\n

#include <OpenCL\/opencl.h><\/p>\n

Second there was a bug in the call to clGetKernelWorkGroupInfo, that Apple fixed yesterday! (I did this a week ago.) (I also changed the extension from .c to .cpp – this is not critical.)<\/p>\n

We also need a Makefile. Both NVidia and AMD provide very complex Makefiles for their examples. Here’s my stripped down version. (Change the commented out paths as needed.)<\/p>\n

# NVIDIA directories
\n# OCLROOTDIR = \/usr\/local\/NVIDIA_GPU_Computing_SDK\/OpenCL
\n# INCLUDEDIR = $(OCLROOTDIR)\/inc
\n# LIBDIR = $(OCLROOTDIR)\/lib<\/p>\n

# ATI directories
\nOCLROOTDIR = \/usr\/local\/ati-stream-sdk-v2.0-beta4-lnx64
\nINCLUDEDIR = $(OCLROOTDIR)\/include
\nLIBDIR = $(OCLROOTDIR)\/lib\/x86_64<\/p>\n

CC = g++
\nCFLAGS = -c -Wall -I$(INCLUDEDIR)
\nLDFLAGS = -L$(LIBDIR) -lOpenCL<\/p>\n

SOURCES = hello.cpp
\nOBJECTS = $(SOURCES:.cpp=.o)
\nEXECUTABLE = hello<\/p>\n

all: $(SOURCES) $(EXECUTABLE)<\/p>\n

$(EXECUTABLE): $(OBJECTS)
\n$(CC) $(LDFLAGS) $(OBJECTS) -o $@<\/p>\n

.cpp.o:
\n$(CC) $(CFLAGS) $< -o $@<\/p>\n

And it works on both machines!<\/p>\n","protected":false},"excerpt":{"rendered":"

(Imagine the post’s title spoken in Leslie Phillips‘ drawl. This will probably either amuse you or mean absolutely nothing!) OK. It’s party time! I have two Linux boxes, both apparently with OpenCL SDKs, each with a different GPGPU: euler – NVidia Tesla 870 crout – AMD\/ATI FireStream 9270 The supplied examples work, but they have […]<\/p>\n","protected":false},"author":53,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-17","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/blog.soton.ac.uk\/gpgpu\/wp-json\/wp\/v2\/posts\/17","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.soton.ac.uk\/gpgpu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.soton.ac.uk\/gpgpu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.soton.ac.uk\/gpgpu\/wp-json\/wp\/v2\/users\/53"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.soton.ac.uk\/gpgpu\/wp-json\/wp\/v2\/comments?post=17"}],"version-history":[{"count":4,"href":"https:\/\/blog.soton.ac.uk\/gpgpu\/wp-json\/wp\/v2\/posts\/17\/revisions"}],"predecessor-version":[{"id":20,"href":"https:\/\/blog.soton.ac.uk\/gpgpu\/wp-json\/wp\/v2\/posts\/17\/revisions\/20"}],"wp:attachment":[{"href":"https:\/\/blog.soton.ac.uk\/gpgpu\/wp-json\/wp\/v2\/media?parent=17"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.soton.ac.uk\/gpgpu\/wp-json\/wp\/v2\/categories?post=17"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.soton.ac.uk\/gpgpu\/wp-json\/wp\/v2\/tags?post=17"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}