cuda dct 变换

cuda dct 变换In this whitepaper the Discrete Cosine Transform (DCT) is discussed. The two-dimensional variation of the transform that operates on 8x8 blocks (DCT8x8) is widely used in image and video coding because it exhibits high signal decorrelation rates and can be easily implemented on the majority of contemporary computing architectures. The key feature of the DCT8x8 is that any pair of 8x8 blocks can be processed independently. This makes possible fully parallel implementation of DCT8x8 by definition. Most of CPU-based implementations of DCT8x8 are firmly adjusted for operating using fixed point arithmetic but still appear to be rather costly as soon as blocks are processed in the sequential order by the single ALU. Performing DCT8x8 computation on GPU using NVIDIA CUDA technology gives significant performance boost even compared to a modern CPU. The proposed approach is accompanied with the sample code “DCT8x8” in the NVIDIA CUDA SDK.    

doc
dct8x8.pdf
data
barbara.bmp
barbara.ppm
BmpUtil.cpp
BmpUtil.h
Common.h
dct8x8.cu
DCT8x8_Gold.cpp
DCT8x8_Gold.h
dct8x8_kernel_quantization.cuh
dct8x8_kernel_short.cuh
dct8x8_kernel1.cuh
dct8x8_kernel2.cuh
dct8x8_vs2010.sln
dct8x8_vs2010.vcxproj
dct8x8_vs2012.sln
dct8x8_vs2012.vcxproj
dct8x8_vs2013.sln
dct8x8_vs2013.vcxproj
dct8x8_vs2015.sln
dct8x8_vs2015.vcxproj
dct8x8_vs2017.sln
dct8x8_vs2017.vcxproj
readme.txt