cpy1Dto2D_shl    1004 source/common/pixel.cpp     p.cu[BLOCK_ ## W ## x ## H].cpy1Dto2D_shl = cpy1Dto2D_shl<W>; \
cpy1Dto2D_shl     272 source/common/primitives.h         cpy1Dto2D_shl_t cpy1Dto2D_shl;
cpy1Dto2D_shl     566 source/common/quant.cpp         primitives.cu[sizeIdx].cpy1Dto2D_shl(residual, coeff, resiStride, 0);
cpy1Dto2D_shl     598 source/common/quant.cpp             primitives.cu[sizeIdx].cpy1Dto2D_shl(residual, m_resiDctCoeff, resiStride, -transformShift);
cpy1Dto2D_shl     957 source/common/x86/asm-primitives.cpp         ALL_LUMA_TU_S(cpy1Dto2D_shl, cpy1Dto2D_shl_, sse2);
cpy1Dto2D_shl    1574 source/common/x86/asm-primitives.cpp         ALL_LUMA_TU_S(cpy1Dto2D_shl, cpy1Dto2D_shl_, avx2);
cpy1Dto2D_shl    2302 source/common/x86/asm-primitives.cpp         ALL_LUMA_TU_S(cpy1Dto2D_shl, cpy1Dto2D_shl_, sse2);
cpy1Dto2D_shl    2909 source/common/x86/asm-primitives.cpp         ALL_LUMA_TU_S(cpy1Dto2D_shl, cpy1Dto2D_shl_, avx2);
cpy1Dto2D_shl      36 source/common/x86/blockcopy8.h FUNCDEF_TU_S(void, cpy1Dto2D_shl, sse2, int16_t* dst, const int16_t* src, intptr_t srcStride, int shift);
cpy1Dto2D_shl      37 source/common/x86/blockcopy8.h FUNCDEF_TU_S(void, cpy1Dto2D_shl, sse4, int16_t* dst, const int16_t* src, intptr_t srcStride, int shift);
cpy1Dto2D_shl      38 source/common/x86/blockcopy8.h FUNCDEF_TU_S(void, cpy1Dto2D_shl, avx2, int16_t* dst, const int16_t* src, intptr_t srcStride, int shift);
cpy1Dto2D_shl    2421 source/test/pixelharness.cpp             if (opt.cu[i].cpy1Dto2D_shl)
cpy1Dto2D_shl    2423 source/test/pixelharness.cpp                 if (!check_cpy1Dto2D_shl_t(ref.cu[i].cpy1Dto2D_shl, opt.cu[i].cpy1Dto2D_shl))
cpy1Dto2D_shl    3053 source/test/pixelharness.cpp         if ((i < BLOCK_64x64) && opt.cu[i].cpy1Dto2D_shl)
cpy1Dto2D_shl    3056 source/test/pixelharness.cpp             REPORT_SPEEDUP(opt.cu[i].cpy1Dto2D_shl, ref.cu[i].cpy1Dto2D_shl, sbuf1, sbuf2, STRIDE, 64);