This directory contains sample code with no purpose other than to
illustrate the code generated for atomic operations on global and
shared memory.
To see the generated machine code, compile with:
nvcc --cubin --gpu-architecture sm_xx <filename>
then disassemble the compiled microcode with cudumpobj:
cudumpobj --dump-sass <filename>.cubin
Memory Operand File
Global int atomic32.cu
Global unsigned long long atomic64.cu
Global float atomicFloat.cu
Shared int atomic32Shared.cu
Shared unsigned long long atomic64Shared.cu
Shared float atomicFloatShared.cu
CUDA专家手册源代码 （199个子文件） 
nbody_CPU_AOS_tiled.cpp 5KB nbody_CPU_SSE_threaded.cpp 4KB chDrv.cpp 4KB saxpyDrv.cpp 4KB tex1dfetch_int2float.cpp 4KB nbody_CPU_SSE_openmp.cpp 3KB nbody_CPU_SSE.cpp 3KB nbody_CPU_SOA.cpp 3KB nbody_CPU_NEON_openmp.cpp 3KB nbody_CPU_AltiVec_openmp.cpp 3KB nbody_CPU_NEON.cpp 3KB nbody_CPU_AltiVec.cpp 3KB nbody_CPU_AOS.cpp 3KB memcpy16.cpp 2KB nbody.cu 24KB normalizedCrossCorrelation.cu 22KB testScanBlock.cu 15KB histogram.cu 14KB testScanWarp.cu 12KB reductionTemplated.cu 12KB globalCopy2.cu 11KB tex2d_opengl.cu 11KB globalReadTex.cu 10KB globalCopy.cu 10KB tex1dfetch_big.cu 10KB globalRead.cu 9KB tex1d_addressing.cu 9KB globalRead.cu 9KB win32GPULoad.cu 9KB linuxGPULoad.cu 9KB reduction.cu 9KB peer2peerMemcpyDrv.cu 8KB stream1Device.cu 8KB globalWrite.cu 8KB globalWrite.cu 8KB surf2Dmemset.cu 8KB spinlockReduction.cu 7KB radixSort.cu 7KB peer2peerMemcpy.cu 7KB stream3Streams.cu 7KB win32NullKernelStreamCallback.cu 7KB float_to_float16.cu 7KB peer2peerMemcpy.cu 7KB surf2Dmemset_shmoo.cu 7KB tex2d_memset.cu 7KB stream2Async.cu 6KB timeStreamCompact_odd.cu 6KB tex2d_addressing_device.cu 6KB tex2d_shmoo.cu 6KB testStreamCompact_odd.cu 6KB pageableMemcpyHtoD16Synchronous.cu 6KB pageableMemcpyHtoD16Broken.cu 6KB reportClocks.cu 6KB pageableMemcpyHtoD16Blocking.cu 6KB tex2d_addressing.cu 6KB pageableMemcpyHtoD16.cu 6KB timeScan.cu 6KB testScan.cu 6KB pageableMemcpyHtoD.cu 6KB testFunnelShift.cu 5KB tex1d_9bit.cu 5KB stream5MappedXfer.cu 5KB stream4Mapped.cu 5KB tex1d_unnormalized.cu 5KB AOStoSOA.cu 5KB tex1dfetch_htod.cu 5KB concurrencyMemcpyKernel.cu 4KB tex1dfetch_int2float.cu 4KB concurrencyKernelKernel.cu 4KB nbody_multiGPU_threaded.cu 4KB nbody_multiGPU.cu 4KB concurrencyMemcpyKernelMapped.cu 4KB concurrencyKernelMapped.cu 4KB tex1dfetch_offset.cu 4KB pgm.cu 4KB nbody_GPU_shared.cu 4KB surf1Dmemset.cu 4KB eventRecord.cu 4KB mallocSpeed.cu 3KB managedOverhead.cu 3KB tex1dfetch.cu 3KB tex1dfetch_host.cu 3KB breakevenDtoHMemcpy.cu 3KB breakevenHtoDMemcpy.cu 3KB solveQuadratic.cu 3KB nullDtoHMemcpySync.cu 3KB breakevenKernelAsync.cu 3KB nullDtoHMemcpyAsync.cu 3KB nullHtoDMemcpyAsync.cu 3KB testShuffle.cu 3KB nullKernelSync.cu 2KB nullKernelAsync.cu 2KB atomic64Shared.cu 2KB atomic32Shared.cu 2KB atomic32.cu 2KB atomicFloatShared.cu 2KB atomicFloat.cu 2KB atomic64.cu 2KB saxpy.cu 2KB nbody_GPU_AOS_tiled_const.cuh 9KB共 199 条
- 1
- 2
资源评论
CouchDB2017-06-25在github上可以直接下载，但是还是要感谢分享 https://github.com/ArchaeaSoftware/cudahandbook
rgbitfkiiiu2017-12-21CUDA专家手册GPU编程权威指南
