mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2026-10-26 06:38:16 +08:00
Update boxFilter, convolutionSeparable, convolutionTexture, dct8x8, delete cuHook
This commit is contained in:
Rob Armstrong
24
Samples/2_Concepts_and_Techniques/dct8x8/CMakeLists.txt
Normal file
24
Samples/2_Concepts_and_Techniques/dct8x8/CMakeLists.txt
Normal file
@@ -0,0 +1,24 @@
|
||||
# Include directories and libraries
|
||||
include_directories(../../../Common)
|
||||
|
||||
# Source file
|
||||
set(SRC_FILES
|
||||
dct8x8.cu
|
||||
BmpUtil.cpp
|
||||
DCT8x8_Gold.cpp
|
||||
)
|
||||
|
||||
# Add target for dct8x8
|
||||
add_executable(dct8x8 ${SRC_FILES})
|
||||
set_target_properties(dct8x8 PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
|
||||
|
||||
target_include_directories(dct8x8 PUBLIC
|
||||
${CUDAToolkit_INCLUDE_DIRS}
|
||||
)
|
||||
|
||||
file(GLOB REF_DATA "teapot512*")
|
||||
add_custom_command(TARGET dct8x8 POST_BUILD
|
||||
COMMAND ${CMAKE_COMMAND} -E copy_if_different
|
||||
${REF_DATA}
|
||||
${CMAKE_CURRENT_BINARY_DIR}
|
||||
)
|
||||
@@ -42,46 +42,43 @@
|
||||
#include "BmpUtil.h"
|
||||
|
||||
/**
|
||||
* This unitary matrix performs DCT of rows of the matrix to the left
|
||||
*/
|
||||
* This unitary matrix performs DCT of rows of the matrix to the left
|
||||
*/
|
||||
const float DCTv8matrix[BLOCK_SIZE2] = {
|
||||
0.3535533905932738f, 0.4903926402016152f, 0.4619397662556434f, 0.4157348061512726f, 0.3535533905932738f, 0.2777851165098011f, 0.1913417161825449f, 0.0975451610080642f,
|
||||
0.3535533905932738f, 0.4157348061512726f, 0.1913417161825449f, -0.0975451610080641f, -0.3535533905932737f, -0.4903926402016152f, -0.4619397662556434f, -0.2777851165098011f,
|
||||
0.3535533905932738f, 0.2777851165098011f, -0.1913417161825449f, -0.4903926402016152f, -0.3535533905932738f, 0.0975451610080642f, 0.4619397662556433f, 0.4157348061512727f,
|
||||
0.3535533905932738f, 0.0975451610080642f, -0.4619397662556434f, -0.2777851165098011f, 0.3535533905932737f, 0.4157348061512727f, -0.1913417161825450f, -0.4903926402016153f,
|
||||
0.3535533905932738f, -0.0975451610080641f, -0.4619397662556434f, 0.2777851165098009f, 0.3535533905932738f, -0.4157348061512726f, -0.1913417161825453f, 0.4903926402016152f,
|
||||
0.3535533905932738f, -0.2777851165098010f, -0.1913417161825452f, 0.4903926402016153f, -0.3535533905932733f, -0.0975451610080649f, 0.4619397662556437f, -0.4157348061512720f,
|
||||
0.3535533905932738f, -0.4157348061512727f, 0.1913417161825450f, 0.0975451610080640f, -0.3535533905932736f, 0.4903926402016152f, -0.4619397662556435f, 0.2777851165098022f,
|
||||
0.3535533905932738f, -0.4903926402016152f, 0.4619397662556433f, -0.4157348061512721f, 0.3535533905932733f, -0.2777851165098008f, 0.1913417161825431f, -0.0975451610080625f
|
||||
};
|
||||
0.3535533905932738f, 0.4903926402016152f, 0.4619397662556434f, 0.4157348061512726f, 0.3535533905932738f, 0.2777851165098011f, 0.1913417161825449f, 0.0975451610080642f,
|
||||
0.3535533905932738f, 0.4157348061512726f, 0.1913417161825449f, -0.0975451610080641f, -0.3535533905932737f, -0.4903926402016152f, -0.4619397662556434f, -0.2777851165098011f,
|
||||
0.3535533905932738f, 0.2777851165098011f, -0.1913417161825449f, -0.4903926402016152f, -0.3535533905932738f, 0.0975451610080642f, 0.4619397662556433f, 0.4157348061512727f,
|
||||
0.3535533905932738f, 0.0975451610080642f, -0.4619397662556434f, -0.2777851165098011f, 0.3535533905932737f, 0.4157348061512727f, -0.1913417161825450f, -0.4903926402016153f,
|
||||
0.3535533905932738f, -0.0975451610080641f, -0.4619397662556434f, 0.2777851165098009f, 0.3535533905932738f, -0.4157348061512726f, -0.1913417161825453f, 0.4903926402016152f,
|
||||
0.3535533905932738f, -0.2777851165098010f, -0.1913417161825452f, 0.4903926402016153f, -0.3535533905932733f, -0.0975451610080649f, 0.4619397662556437f, -0.4157348061512720f,
|
||||
0.3535533905932738f, -0.4157348061512727f, 0.1913417161825450f, 0.0975451610080640f, -0.3535533905932736f, 0.4903926402016152f, -0.4619397662556435f, 0.2777851165098022f,
|
||||
0.3535533905932738f, -0.4903926402016152f, 0.4619397662556433f, -0.4157348061512721f, 0.3535533905932733f, -0.2777851165098008f, 0.1913417161825431f, -0.0975451610080625f};
|
||||
|
||||
/**
|
||||
* This unitary matrix performs DCT of columns of the matrix to the right
|
||||
*/
|
||||
* This unitary matrix performs DCT of columns of the matrix to the right
|
||||
*/
|
||||
const float DCTv8matrixT[BLOCK_SIZE2] = {
|
||||
0.3535533905932738f, 0.3535533905932738f, 0.3535533905932738f, 0.3535533905932738f, 0.3535533905932738f, 0.3535533905932738f, 0.3535533905932738f, 0.3535533905932738f,
|
||||
0.4903926402016152f, 0.4157348061512726f, 0.2777851165098011f, 0.0975451610080642f, -0.0975451610080641f, -0.2777851165098010f, -0.4157348061512727f, -0.4903926402016152f,
|
||||
0.4619397662556434f, 0.1913417161825449f, -0.1913417161825449f, -0.4619397662556434f, -0.4619397662556434f, -0.1913417161825452f, 0.1913417161825450f, 0.4619397662556433f,
|
||||
0.4157348061512726f, -0.0975451610080641f, -0.4903926402016152f, -0.2777851165098011f, 0.2777851165098009f, 0.4903926402016153f, 0.0975451610080640f, -0.4157348061512721f,
|
||||
0.3535533905932738f, -0.3535533905932737f, -0.3535533905932738f, 0.3535533905932737f, 0.3535533905932738f, -0.3535533905932733f, -0.3535533905932736f, 0.3535533905932733f,
|
||||
0.2777851165098011f, -0.4903926402016152f, 0.0975451610080642f, 0.4157348061512727f, -0.4157348061512726f, -0.0975451610080649f, 0.4903926402016152f, -0.2777851165098008f,
|
||||
0.1913417161825449f, -0.4619397662556434f, 0.4619397662556433f, -0.1913417161825450f, -0.1913417161825453f, 0.4619397662556437f, -0.4619397662556435f, 0.1913417161825431f,
|
||||
0.0975451610080642f, -0.2777851165098011f, 0.4157348061512727f, -0.4903926402016153f, 0.4903926402016152f, -0.4157348061512720f, 0.2777851165098022f, -0.0975451610080625f
|
||||
};
|
||||
0.3535533905932738f, 0.3535533905932738f, 0.3535533905932738f, 0.3535533905932738f, 0.3535533905932738f, 0.3535533905932738f, 0.3535533905932738f, 0.3535533905932738f,
|
||||
0.4903926402016152f, 0.4157348061512726f, 0.2777851165098011f, 0.0975451610080642f, -0.0975451610080641f, -0.2777851165098010f, -0.4157348061512727f, -0.4903926402016152f,
|
||||
0.4619397662556434f, 0.1913417161825449f, -0.1913417161825449f, -0.4619397662556434f, -0.4619397662556434f, -0.1913417161825452f, 0.1913417161825450f, 0.4619397662556433f,
|
||||
0.4157348061512726f, -0.0975451610080641f, -0.4903926402016152f, -0.2777851165098011f, 0.2777851165098009f, 0.4903926402016153f, 0.0975451610080640f, -0.4157348061512721f,
|
||||
0.3535533905932738f, -0.3535533905932737f, -0.3535533905932738f, 0.3535533905932737f, 0.3535533905932738f, -0.3535533905932733f, -0.3535533905932736f, 0.3535533905932733f,
|
||||
0.2777851165098011f, -0.4903926402016152f, 0.0975451610080642f, 0.4157348061512727f, -0.4157348061512726f, -0.0975451610080649f, 0.4903926402016152f, -0.2777851165098008f,
|
||||
0.1913417161825449f, -0.4619397662556434f, 0.4619397662556433f, -0.1913417161825450f, -0.1913417161825453f, 0.4619397662556437f, -0.4619397662556435f, 0.1913417161825431f,
|
||||
0.0975451610080642f, -0.2777851165098011f, 0.4157348061512727f, -0.4903926402016153f, 0.4903926402016152f, -0.4157348061512720f, 0.2777851165098022f, -0.0975451610080625f};
|
||||
|
||||
/**
|
||||
* JPEG quality=0_of_12 quantization matrix
|
||||
*/
|
||||
float Q[BLOCK_SIZE2] = {
|
||||
32.f, 33.f, 51.f, 81.f, 66.f, 39.f, 34.f, 17.f,
|
||||
33.f, 36.f, 48.f, 47.f, 28.f, 23.f, 12.f, 12.f,
|
||||
51.f, 48.f, 47.f, 28.f, 23.f, 12.f, 12.f, 12.f,
|
||||
81.f, 47.f, 28.f, 23.f, 12.f, 12.f, 12.f, 12.f,
|
||||
66.f, 28.f, 23.f, 12.f, 12.f, 12.f, 12.f, 12.f,
|
||||
39.f, 23.f, 12.f, 12.f, 12.f, 12.f, 12.f, 12.f,
|
||||
34.f, 12.f, 12.f, 12.f, 12.f, 12.f, 12.f, 12.f,
|
||||
17.f, 12.f, 12.f, 12.f, 12.f, 12.f, 12.f, 12.f
|
||||
};
|
||||
* JPEG quality=0_of_12 quantization matrix
|
||||
*/
|
||||
float Q_GOLD[BLOCK_SIZE2] = {
|
||||
32.f, 33.f, 51.f, 81.f, 66.f, 39.f, 34.f, 17.f,
|
||||
33.f, 36.f, 48.f, 47.f, 28.f, 23.f, 12.f, 12.f,
|
||||
51.f, 48.f, 47.f, 28.f, 23.f, 12.f, 12.f, 12.f,
|
||||
81.f, 47.f, 28.f, 23.f, 12.f, 12.f, 12.f, 12.f,
|
||||
66.f, 28.f, 23.f, 12.f, 12.f, 12.f, 12.f, 12.f,
|
||||
39.f, 23.f, 12.f, 12.f, 12.f, 12.f, 12.f, 12.f,
|
||||
34.f, 12.f, 12.f, 12.f, 12.f, 12.f, 12.f, 12.f,
|
||||
17.f, 12.f, 12.f, 12.f, 12.f, 12.f, 12.f, 12.f};
|
||||
|
||||
/**
|
||||
**************************************************************************
|
||||
@@ -97,12 +94,16 @@ float Q[BLOCK_SIZE2] = {
|
||||
* \return None
|
||||
*/
|
||||
void mult8x8(const float *M1, int M1Stride, const float *M2, int M2Stride,
|
||||
float *Mres, int MresStride) {
|
||||
for (int i = 0; i < BLOCK_SIZE; i++) {
|
||||
for (int j = 0; j < BLOCK_SIZE; j++) {
|
||||
float *Mres, int MresStride)
|
||||
{
|
||||
for (int i = 0; i < BLOCK_SIZE; i++)
|
||||
{
|
||||
for (int j = 0; j < BLOCK_SIZE; j++)
|
||||
{
|
||||
float accumul = 0;
|
||||
|
||||
for (int k = 0; k < BLOCK_SIZE; k++) {
|
||||
for (int k = 0; k < BLOCK_SIZE; k++)
|
||||
{
|
||||
accumul += M1[i * M1Stride + k] * M2[k * M2Stride + j];
|
||||
}
|
||||
|
||||
@@ -125,13 +126,16 @@ void mult8x8(const float *M1, int M1Stride, const float *M2, int M2Stride,
|
||||
* \return None
|
||||
*/
|
||||
extern "C" void computeDCT8x8Gold1(const float *fSrc, float *fDst, int Stride,
|
||||
ROI Size) {
|
||||
ROI Size)
|
||||
{
|
||||
float tmpblock[BLOCK_SIZE2];
|
||||
|
||||
// perform block wise DCT
|
||||
// DCT(A) = DCTv8matrixT * A * DCTv8matrix
|
||||
for (int i = 0; i + BLOCK_SIZE - 1 < Size.height; i += BLOCK_SIZE) {
|
||||
for (int j = 0; j + BLOCK_SIZE - 1 < Size.width; j += BLOCK_SIZE) {
|
||||
for (int i = 0; i + BLOCK_SIZE - 1 < Size.height; i += BLOCK_SIZE)
|
||||
{
|
||||
for (int j = 0; j + BLOCK_SIZE - 1 < Size.width; j += BLOCK_SIZE)
|
||||
{
|
||||
// tmpblock = DCTv8matrixT * A
|
||||
mult8x8(DCTv8matrixT, BLOCK_SIZE, fSrc + i * Stride + j, Stride, tmpblock,
|
||||
BLOCK_SIZE);
|
||||
@@ -156,13 +160,16 @@ extern "C" void computeDCT8x8Gold1(const float *fSrc, float *fDst, int Stride,
|
||||
* \return None
|
||||
*/
|
||||
extern "C" void computeIDCT8x8Gold1(const float *fSrc, float *fDst, int Stride,
|
||||
ROI Size) {
|
||||
ROI Size)
|
||||
{
|
||||
float tmpblock[BLOCK_SIZE2];
|
||||
|
||||
// perform block wise IDCT
|
||||
// IDCT(A) = DCTv8matrix * A * DCTv8matrixT
|
||||
for (int i = 0; i + BLOCK_SIZE - 1 < Size.height; i += BLOCK_SIZE) {
|
||||
for (int j = 0; j + BLOCK_SIZE - 1 < Size.width; j += BLOCK_SIZE) {
|
||||
for (int i = 0; i + BLOCK_SIZE - 1 < Size.height; i += BLOCK_SIZE)
|
||||
{
|
||||
for (int j = 0; j + BLOCK_SIZE - 1 < Size.width; j += BLOCK_SIZE)
|
||||
{
|
||||
// tmpblock = DCTv8matrix * A
|
||||
mult8x8(DCTv8matrix, BLOCK_SIZE, fSrc + i * Stride + j, Stride, tmpblock,
|
||||
BLOCK_SIZE);
|
||||
@@ -184,16 +191,19 @@ extern "C" void computeIDCT8x8Gold1(const float *fSrc, float *fDst, int Stride,
|
||||
*
|
||||
* \return None
|
||||
*/
|
||||
extern "C" void quantizeGoldFloat(float *fSrcDst, int Stride, ROI Size) {
|
||||
// perform block wise in-place quantization using Q
|
||||
// Q(A) = round(A ./ Q) .* Q;
|
||||
for (int i = 0; i < Size.height; i++) {
|
||||
for (int j = 0; j < Size.width; j++) {
|
||||
extern "C" void quantizeGoldFloat(float *fSrcDst, int Stride, ROI Size)
|
||||
{
|
||||
// perform block wise in-place quantization using Q_GOLD
|
||||
// Q_GOLD(A) = round(A ./ Q_GOLD) .* Q_GOLD;
|
||||
for (int i = 0; i < Size.height; i++)
|
||||
{
|
||||
for (int j = 0; j < Size.width; j++)
|
||||
{
|
||||
int qx = j % BLOCK_SIZE;
|
||||
int qy = i % BLOCK_SIZE;
|
||||
float quantized =
|
||||
round_f(fSrcDst[i * Stride + j] / Q[(qy << BLOCK_SIZE_LOG2) + qx]);
|
||||
fSrcDst[i * Stride + j] = quantized * Q[(qy << BLOCK_SIZE_LOG2) + qx];
|
||||
round_f(fSrcDst[i * Stride + j] / Q_GOLD[(qy << BLOCK_SIZE_LOG2) + qx]);
|
||||
fSrcDst[i * Stride + j] = quantized * Q_GOLD[(qy << BLOCK_SIZE_LOG2) + qx];
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -209,22 +219,28 @@ extern "C" void quantizeGoldFloat(float *fSrcDst, int Stride, ROI Size) {
|
||||
*
|
||||
* \return None
|
||||
*/
|
||||
void quantizeGoldShort(short *fSrcDst, int Stride, ROI Size) {
|
||||
// perform block wise in-place quantization using Q
|
||||
// Q(A) = round(A ./ Q) .* Q;
|
||||
for (int i = 0; i < Size.height; i++) {
|
||||
for (int j = 0; j < Size.width; j++) {
|
||||
void quantizeGoldShort(short *fSrcDst, int Stride, ROI Size)
|
||||
{
|
||||
// perform block wise in-place quantization using Q_GOLD
|
||||
// Q_GOLD(A) = round(A ./ Q_GOLD) .* Q_GOLD;
|
||||
for (int i = 0; i < Size.height; i++)
|
||||
{
|
||||
for (int j = 0; j < Size.width; j++)
|
||||
{
|
||||
int qx = j % BLOCK_SIZE;
|
||||
int qy = i % BLOCK_SIZE;
|
||||
short temp = fSrcDst[i * Stride + j];
|
||||
short quant = (short)(Q[(qy << BLOCK_SIZE_LOG2) + qx]);
|
||||
short quant = (short)(Q_GOLD[(qy << BLOCK_SIZE_LOG2) + qx]);
|
||||
|
||||
if (temp < 0) {
|
||||
if (temp < 0)
|
||||
{
|
||||
temp = -temp;
|
||||
temp += quant >> 1;
|
||||
temp /= quant;
|
||||
temp = -temp;
|
||||
} else {
|
||||
}
|
||||
else
|
||||
{
|
||||
temp += quant >> 1;
|
||||
temp /= quant;
|
||||
}
|
||||
@@ -235,17 +251,17 @@ void quantizeGoldShort(short *fSrcDst, int Stride, ROI Size) {
|
||||
}
|
||||
|
||||
// Used in forward and inverse DCT.
|
||||
float C_a = 1.387039845322148f; //!< a = (2^0.5) * cos( pi / 16);
|
||||
float C_b = 1.306562964876377f; //!< b = (2^0.5) * cos( pi / 8);
|
||||
float C_c = 1.175875602419359f; //!< c = (2^0.5) * cos(3 * pi / 16);
|
||||
float C_d = 0.785694958387102f; //!< d = (2^0.5) * cos(5 * pi / 16);
|
||||
float C_e = 0.541196100146197f; //!< e = (2^0.5) * cos(3 * pi / 8);
|
||||
float C_f = 0.275899379282943f; //!< f = (2^0.5) * cos(7 * pi / 16);
|
||||
float C_a = 1.387039845322148f; //!< a = (2^0.5) * cos( pi / 16);
|
||||
float C_b = 1.306562964876377f; //!< b = (2^0.5) * cos( pi / 8);
|
||||
float C_c = 1.175875602419359f; //!< c = (2^0.5) * cos(3 * pi / 16);
|
||||
float C_d = 0.785694958387102f; //!< d = (2^0.5) * cos(5 * pi / 16);
|
||||
float C_e = 0.541196100146197f; //!< e = (2^0.5) * cos(3 * pi / 8);
|
||||
float C_f = 0.275899379282943f; //!< f = (2^0.5) * cos(7 * pi / 16);
|
||||
|
||||
/**
|
||||
* Normalization constant that is used in forward and inverse DCT
|
||||
*/
|
||||
float C_norm = 0.3535533905932737f; // 1 / (8^0.5)
|
||||
* Normalization constant that is used in forward and inverse DCT
|
||||
*/
|
||||
float C_norm = 0.3535533905932737f; // 1 / (8^0.5)
|
||||
|
||||
/**
|
||||
**************************************************************************
|
||||
@@ -261,7 +277,8 @@ float C_norm = 0.3535533905932737f; // 1 / (8^0.5)
|
||||
* \return None
|
||||
*/
|
||||
void SubroutineDCTvector(float *FirstIn, int StepIn, float *FirstOut,
|
||||
int StepOut) {
|
||||
int StepOut)
|
||||
{
|
||||
float X07P = FirstIn[0 * StepIn] + FirstIn[7 * StepIn];
|
||||
float X16P = FirstIn[1 * StepIn] + FirstIn[6 * StepIn];
|
||||
float X25P = FirstIn[2 * StepIn] + FirstIn[5 * StepIn];
|
||||
@@ -306,7 +323,8 @@ void SubroutineDCTvector(float *FirstIn, int StepIn, float *FirstOut,
|
||||
* \return None
|
||||
*/
|
||||
void SubroutineIDCTvector(float *FirstIn, int StepIn, float *FirstOut,
|
||||
int StepOut) {
|
||||
int StepOut)
|
||||
{
|
||||
float Y04P = FirstIn[0 * StepIn] + FirstIn[4 * StepIn];
|
||||
float Y2b6eP = C_b * FirstIn[2 * StepIn] + C_e * FirstIn[6 * StepIn];
|
||||
|
||||
@@ -352,17 +370,22 @@ void SubroutineIDCTvector(float *FirstIn, int StepIn, float *FirstOut,
|
||||
* \return None
|
||||
*/
|
||||
extern "C" void computeDCT8x8Gold2(const float *fSrc, float *fDst, int Stride,
|
||||
ROI Size) {
|
||||
for (int i = 0; i + BLOCK_SIZE - 1 < Size.height; i += BLOCK_SIZE) {
|
||||
for (int j = 0; j + BLOCK_SIZE - 1 < Size.width; j += BLOCK_SIZE) {
|
||||
ROI Size)
|
||||
{
|
||||
for (int i = 0; i + BLOCK_SIZE - 1 < Size.height; i += BLOCK_SIZE)
|
||||
{
|
||||
for (int j = 0; j + BLOCK_SIZE - 1 < Size.width; j += BLOCK_SIZE)
|
||||
{
|
||||
// process rows
|
||||
for (int k = 0; k < BLOCK_SIZE; k++) {
|
||||
for (int k = 0; k < BLOCK_SIZE; k++)
|
||||
{
|
||||
SubroutineDCTvector((float *)fSrc + (i + k) * Stride + j, 1,
|
||||
fDst + (i + k) * Stride + j, 1);
|
||||
}
|
||||
|
||||
// process columns
|
||||
for (int k = 0; k < BLOCK_SIZE; k++) {
|
||||
for (int k = 0; k < BLOCK_SIZE; k++)
|
||||
{
|
||||
SubroutineDCTvector(fDst + i * Stride + (j + k), Stride,
|
||||
fDst + i * Stride + (j + k), Stride);
|
||||
}
|
||||
@@ -384,17 +407,22 @@ extern "C" void computeDCT8x8Gold2(const float *fSrc, float *fDst, int Stride,
|
||||
* \return None
|
||||
*/
|
||||
extern "C" void computeIDCT8x8Gold2(const float *fSrc, float *fDst, int Stride,
|
||||
ROI Size) {
|
||||
for (int i = 0; i + BLOCK_SIZE - 1 < Size.height; i += BLOCK_SIZE) {
|
||||
for (int j = 0; j + BLOCK_SIZE - 1 < Size.width; j += BLOCK_SIZE) {
|
||||
ROI Size)
|
||||
{
|
||||
for (int i = 0; i + BLOCK_SIZE - 1 < Size.height; i += BLOCK_SIZE)
|
||||
{
|
||||
for (int j = 0; j + BLOCK_SIZE - 1 < Size.width; j += BLOCK_SIZE)
|
||||
{
|
||||
// process rows
|
||||
for (int k = 0; k < BLOCK_SIZE; k++) {
|
||||
for (int k = 0; k < BLOCK_SIZE; k++)
|
||||
{
|
||||
SubroutineIDCTvector((float *)fSrc + (i + k) * Stride + j, 1,
|
||||
fDst + (i + k) * Stride + j, 1);
|
||||
}
|
||||
|
||||
// process columns
|
||||
for (int k = 0; k < BLOCK_SIZE; k++) {
|
||||
for (int k = 0; k < BLOCK_SIZE; k++)
|
||||
{
|
||||
SubroutineIDCTvector(fDst + i * Stride + (j + k), Stride,
|
||||
fDst + i * Stride + (j + k), Stride);
|
||||
}
|
||||
|
||||
@@ -1,363 +0,0 @@
|
||||
################################################################################
|
||||
# Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved.
|
||||
#
|
||||
# Redistribution and use in source and binary forms, with or without
|
||||
# modification, are permitted provided that the following conditions
|
||||
# are met:
|
||||
# * Redistributions of source code must retain the above copyright
|
||||
# notice, this list of conditions and the following disclaimer.
|
||||
# * Redistributions in binary form must reproduce the above copyright
|
||||
# notice, this list of conditions and the following disclaimer in the
|
||||
# documentation and/or other materials provided with the distribution.
|
||||
# * Neither the name of NVIDIA CORPORATION nor the names of its
|
||||
# contributors may be used to endorse or promote products derived
|
||||
# from this software without specific prior written permission.
|
||||
#
|
||||
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
|
||||
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
|
||||
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
||||
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
||||
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
||||
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
|
||||
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
#
|
||||
################################################################################
|
||||
#
|
||||
# Makefile project only supported on Mac OS X and Linux Platforms)
|
||||
#
|
||||
################################################################################
|
||||
|
||||
# Location of the CUDA Toolkit
|
||||
CUDA_PATH ?= /usr/local/cuda
|
||||
|
||||
##############################
|
||||
# start deprecated interface #
|
||||
##############################
|
||||
ifeq ($(x86_64),1)
|
||||
$(info WARNING - x86_64 variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=x86_64 instead)
|
||||
TARGET_ARCH ?= x86_64
|
||||
endif
|
||||
ifeq ($(ARMv7),1)
|
||||
$(info WARNING - ARMv7 variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=armv7l instead)
|
||||
TARGET_ARCH ?= armv7l
|
||||
endif
|
||||
ifeq ($(aarch64),1)
|
||||
$(info WARNING - aarch64 variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=aarch64 instead)
|
||||
TARGET_ARCH ?= aarch64
|
||||
endif
|
||||
ifeq ($(ppc64le),1)
|
||||
$(info WARNING - ppc64le variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=ppc64le instead)
|
||||
TARGET_ARCH ?= ppc64le
|
||||
endif
|
||||
ifneq ($(GCC),)
|
||||
$(info WARNING - GCC variable has been deprecated)
|
||||
$(info WARNING - please use HOST_COMPILER=$(GCC) instead)
|
||||
HOST_COMPILER ?= $(GCC)
|
||||
endif
|
||||
ifneq ($(abi),)
|
||||
$(error ERROR - abi variable has been removed)
|
||||
endif
|
||||
############################
|
||||
# end deprecated interface #
|
||||
############################
|
||||
|
||||
# architecture
|
||||
HOST_ARCH := $(shell uname -m)
|
||||
TARGET_ARCH ?= $(HOST_ARCH)
|
||||
ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le armv7l))
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le))
|
||||
TARGET_SIZE := 64
|
||||
else ifneq (,$(filter $(TARGET_ARCH),armv7l))
|
||||
TARGET_SIZE := 32
|
||||
endif
|
||||
else
|
||||
TARGET_SIZE := $(shell getconf LONG_BIT)
|
||||
endif
|
||||
else
|
||||
$(error ERROR - unsupported value $(TARGET_ARCH) for TARGET_ARCH!)
|
||||
endif
|
||||
|
||||
# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
|
||||
ifeq ($(HOST_ARCH),aarch64)
|
||||
ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null))
|
||||
HOST_ARCH := sbsa
|
||||
TARGET_ARCH := sbsa
|
||||
endif
|
||||
endif
|
||||
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifeq (,$(filter $(HOST_ARCH)-$(TARGET_ARCH),aarch64-armv7l x86_64-armv7l x86_64-aarch64 x86_64-sbsa x86_64-ppc64le))
|
||||
$(error ERROR - cross compiling from $(HOST_ARCH) to $(TARGET_ARCH) is not supported!)
|
||||
endif
|
||||
endif
|
||||
|
||||
# When on native aarch64 system with userspace of 32-bit, change TARGET_ARCH to armv7l
|
||||
ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_SIZE),aarch64-aarch64-32)
|
||||
TARGET_ARCH = armv7l
|
||||
endif
|
||||
|
||||
# operating system
|
||||
HOST_OS := $(shell uname -s 2>/dev/null | tr "[:upper:]" "[:lower:]")
|
||||
TARGET_OS ?= $(HOST_OS)
|
||||
ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
|
||||
$(error ERROR - unsupported value $(TARGET_OS) for TARGET_OS!)
|
||||
endif
|
||||
|
||||
# host compiler
|
||||
ifdef HOST_COMPILER
|
||||
CUSTOM_HOST_COMPILER = 1
|
||||
endif
|
||||
|
||||
ifeq ($(TARGET_OS),darwin)
|
||||
ifeq ($(shell expr `xcodebuild -version | grep -i xcode | awk '{print $$2}' | cut -d'.' -f1` \>= 5),1)
|
||||
HOST_COMPILER ?= clang++
|
||||
endif
|
||||
else ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-armv7l)
|
||||
ifeq ($(TARGET_OS),linux)
|
||||
HOST_COMPILER ?= arm-linux-gnueabihf-g++
|
||||
else ifeq ($(TARGET_OS),qnx)
|
||||
ifeq ($(QNX_HOST),)
|
||||
$(error ERROR - QNX_HOST must be passed to the QNX host toolchain)
|
||||
endif
|
||||
ifeq ($(QNX_TARGET),)
|
||||
$(error ERROR - QNX_TARGET must be passed to the QNX target toolchain)
|
||||
endif
|
||||
export QNX_HOST
|
||||
export QNX_TARGET
|
||||
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/arm-unknown-nto-qnx6.6.0eabi-g++
|
||||
else ifeq ($(TARGET_OS),android)
|
||||
HOST_COMPILER ?= arm-linux-androideabi-g++
|
||||
endif
|
||||
else ifeq ($(TARGET_ARCH),aarch64)
|
||||
ifeq ($(TARGET_OS), linux)
|
||||
HOST_COMPILER ?= aarch64-linux-gnu-g++
|
||||
else ifeq ($(TARGET_OS),qnx)
|
||||
ifeq ($(QNX_HOST),)
|
||||
$(error ERROR - QNX_HOST must be passed to the QNX host toolchain)
|
||||
endif
|
||||
ifeq ($(QNX_TARGET),)
|
||||
$(error ERROR - QNX_TARGET must be passed to the QNX target toolchain)
|
||||
endif
|
||||
export QNX_HOST
|
||||
export QNX_TARGET
|
||||
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++
|
||||
else ifeq ($(TARGET_OS), android)
|
||||
HOST_COMPILER ?= aarch64-linux-android-clang++
|
||||
endif
|
||||
else ifeq ($(TARGET_ARCH),sbsa)
|
||||
HOST_COMPILER ?= aarch64-linux-gnu-g++
|
||||
else ifeq ($(TARGET_ARCH),ppc64le)
|
||||
HOST_COMPILER ?= powerpc64le-linux-gnu-g++
|
||||
endif
|
||||
endif
|
||||
HOST_COMPILER ?= g++
|
||||
NVCC := $(CUDA_PATH)/bin/nvcc -ccbin $(HOST_COMPILER)
|
||||
|
||||
# internal flags
|
||||
NVCCFLAGS := -m${TARGET_SIZE}
|
||||
CCFLAGS :=
|
||||
LDFLAGS :=
|
||||
|
||||
# build flags
|
||||
|
||||
# Link flag for customized HOST_COMPILER with gcc realpath
|
||||
GCC_PATH := $(shell which gcc)
|
||||
ifeq ($(CUSTOM_HOST_COMPILER),1)
|
||||
ifneq ($(filter /%,$(HOST_COMPILER)),)
|
||||
ifneq ($(findstring gcc,$(HOST_COMPILER)),)
|
||||
ifneq ($(GCC_PATH),$(HOST_COMPILER))
|
||||
LDFLAGS += -lstdc++
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
|
||||
ifeq ($(TARGET_OS),darwin)
|
||||
LDFLAGS += -rpath $(CUDA_PATH)/lib
|
||||
CCFLAGS += -arch $(HOST_ARCH)
|
||||
else ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_OS),x86_64-armv7l-linux)
|
||||
LDFLAGS += --dynamic-linker=/lib/ld-linux-armhf.so.3
|
||||
CCFLAGS += -mfloat-abi=hard
|
||||
else ifeq ($(TARGET_OS),android)
|
||||
LDFLAGS += -pie
|
||||
CCFLAGS += -fpie -fpic -fexceptions
|
||||
endif
|
||||
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
|
||||
ifneq ($(TARGET_FS),)
|
||||
GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6)
|
||||
ifeq ($(GCCVERSIONLTEQ46),1)
|
||||
CCFLAGS += --sysroot=$(TARGET_FS)
|
||||
endif
|
||||
LDFLAGS += --sysroot=$(TARGET_FS)
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/arm-linux-gnueabihf
|
||||
endif
|
||||
endif
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
|
||||
ifneq ($(TARGET_FS),)
|
||||
GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6)
|
||||
ifeq ($(GCCVERSIONLTEQ46),1)
|
||||
CCFLAGS += --sysroot=$(TARGET_FS)
|
||||
endif
|
||||
LDFLAGS += --sysroot=$(TARGET_FS)
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/lib -L$(TARGET_FS)/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/lib/aarch64-linux-gnu -L$(TARGET_FS)/lib/aarch64-linux-gnu
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
|
||||
LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
|
||||
CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm
|
||||
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
|
||||
endif
|
||||
endif
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
|
||||
NVCCFLAGS += -D_QNX_SOURCE
|
||||
NVCCFLAGS += --qpp-config 8.3.0,gcc_ntoaarch64le
|
||||
CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
|
||||
LDFLAGS += -lsocket
|
||||
LDFLAGS += -L/usr/lib/aarch64-qnx-gnu
|
||||
CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu"
|
||||
ifdef TARGET_OVERRIDE
|
||||
LDFLAGS += -lslog2
|
||||
endif
|
||||
|
||||
ifneq ($(TARGET_FS),)
|
||||
LDFLAGS += -L$(TARGET_FS)/usr/lib
|
||||
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
|
||||
LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
|
||||
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
|
||||
CCFLAGS += -I$(TARGET_FS)/../include
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
|
||||
ifdef TARGET_OVERRIDE # cuda toolkit targets override
|
||||
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
|
||||
endif
|
||||
|
||||
# Install directory of different arch
|
||||
CUDA_INSTALL_TARGET_DIR :=
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-gnueabihf/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),sbsa-linux)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/sbsa-linux/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-android)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-androideabi/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-android)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux-androideabi/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-qnx)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/ARMv7-linux-QNX/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/aarch64-qnx/
|
||||
else ifeq ($(TARGET_ARCH),ppc64le)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/ppc64le-linux/
|
||||
endif
|
||||
|
||||
# Debug build flags
|
||||
ifeq ($(dbg),1)
|
||||
NVCCFLAGS += -g -G
|
||||
BUILD_TYPE := debug
|
||||
else
|
||||
BUILD_TYPE := release
|
||||
endif
|
||||
|
||||
ALL_CCFLAGS :=
|
||||
ALL_CCFLAGS += $(NVCCFLAGS)
|
||||
ALL_CCFLAGS += $(EXTRA_NVCCFLAGS)
|
||||
ALL_CCFLAGS += $(addprefix -Xcompiler ,$(CCFLAGS))
|
||||
ALL_CCFLAGS += $(addprefix -Xcompiler ,$(EXTRA_CCFLAGS))
|
||||
|
||||
SAMPLE_ENABLED := 1
|
||||
|
||||
ALL_LDFLAGS :=
|
||||
ALL_LDFLAGS += $(ALL_CCFLAGS)
|
||||
ALL_LDFLAGS += $(addprefix -Xlinker ,$(LDFLAGS))
|
||||
ALL_LDFLAGS += $(addprefix -Xlinker ,$(EXTRA_LDFLAGS))
|
||||
|
||||
# Common includes and paths for CUDA
|
||||
INCLUDES := -I../../../Common
|
||||
LIBRARIES :=
|
||||
|
||||
################################################################################
|
||||
|
||||
# Gencode arguments
|
||||
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
|
||||
SMS ?= 53 61 70 72 75 80 86 87 90
|
||||
else
|
||||
SMS ?= 50 52 60 61 70 75 80 86 89 90
|
||||
endif
|
||||
|
||||
ifeq ($(SMS),)
|
||||
$(info >>> WARNING - no SM architectures have been specified - waiving sample <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
|
||||
ifeq ($(GENCODE_FLAGS),)
|
||||
# Generate SASS code for each SM architecture listed in $(SMS)
|
||||
$(foreach sm,$(SMS),$(eval GENCODE_FLAGS += -gencode arch=compute_$(sm),code=sm_$(sm)))
|
||||
|
||||
# Generate PTX code from the highest SM architecture in $(SMS) to guarantee forward-compatibility
|
||||
HIGHEST_SM := $(lastword $(sort $(SMS)))
|
||||
ifneq ($(HIGHEST_SM),)
|
||||
GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
|
||||
endif
|
||||
endif
|
||||
|
||||
ALL_CCFLAGS += --threads 0 --std=c++11
|
||||
|
||||
ifeq ($(SAMPLE_ENABLED),0)
|
||||
EXEC ?= @echo "[@]"
|
||||
endif
|
||||
|
||||
################################################################################
|
||||
|
||||
# Target rules
|
||||
all: build
|
||||
|
||||
build: dct8x8
|
||||
|
||||
check.deps:
|
||||
ifeq ($(SAMPLE_ENABLED),0)
|
||||
@echo "Sample will be waived due to the above missing dependencies"
|
||||
else
|
||||
@echo "Sample is ready - all dependencies have been met"
|
||||
endif
|
||||
|
||||
BmpUtil.o:BmpUtil.cpp
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
DCT8x8_Gold.o:DCT8x8_Gold.cpp
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
dct8x8.o:dct8x8.cu
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
dct8x8: BmpUtil.o DCT8x8_Gold.o dct8x8.o
|
||||
$(EXEC) $(NVCC) $(ALL_LDFLAGS) $(GENCODE_FLAGS) -o $@ $+ $(LIBRARIES)
|
||||
$(EXEC) mkdir -p ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)
|
||||
$(EXEC) cp $@ ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)
|
||||
|
||||
run: build
|
||||
$(EXEC) ./dct8x8
|
||||
|
||||
testrun: build
|
||||
|
||||
clean:
|
||||
rm -f dct8x8 BmpUtil.o DCT8x8_Gold.o dct8x8.o
|
||||
rm -rf ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/dct8x8
|
||||
|
||||
clobber: clean
|
||||
@@ -1,89 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
||||
<entry>
|
||||
<name>dct8x8</name>
|
||||
<cuda_api_list>
|
||||
<toolkit>cudaMallocArray</toolkit>
|
||||
<toolkit>cudaFreeArray</toolkit>
|
||||
<toolkit>cudaFree</toolkit>
|
||||
<toolkit>cudaMallocPitch</toolkit>
|
||||
<toolkit>cudaDestroyTextureObject</toolkit>
|
||||
<toolkit>cudaDeviceSynchronize</toolkit>
|
||||
<toolkit>cudaCreateTextureObject</toolkit>
|
||||
</cuda_api_list>
|
||||
<description><![CDATA[This sample demonstrates how Discrete Cosine Transform (DCT) for blocks of 8 by 8 pixels can be performed using CUDA: a naive implementation by definition and a more traditional approach used in many libraries. As opposed to implementing DCT in a fragment shader, CUDA allows for an easier and more efficient implementation.]]></description>
|
||||
<devicecompilation>whole</devicecompilation>
|
||||
<files>
|
||||
<file>data\teapot512.bmp</file>
|
||||
</files>
|
||||
<includepaths>
|
||||
<path>./</path>
|
||||
<path>../</path>
|
||||
<path>../../../Common</path>
|
||||
</includepaths>
|
||||
<keyconcepts>
|
||||
<concept level="advanced">Image Processing</concept>
|
||||
<concept level="advanced">Video Compression</concept>
|
||||
</keyconcepts>
|
||||
<keywords>
|
||||
<keyword>CUDA</keyword>
|
||||
<keyword>Image Processing</keyword>
|
||||
<keyword>DCT</keyword>
|
||||
<keyword>Discrete Cosine Transfrom</keyword>
|
||||
</keywords>
|
||||
<libraries>
|
||||
</libraries>
|
||||
<librarypaths>
|
||||
</librarypaths>
|
||||
<nsight_eclipse>true</nsight_eclipse>
|
||||
<primary_file>dct8x8.cu</primary_file>
|
||||
<scopes>
|
||||
<scope>1:CUDA Advanced Topics</scope>
|
||||
<scope>2:Image Processing</scope>
|
||||
<scope>2:Data Compression</scope>
|
||||
<scope>2:Video Codecs</scope>
|
||||
<scope>2:Computer Vision</scope>
|
||||
</scopes>
|
||||
<sm-arch>sm50</sm-arch>
|
||||
<sm-arch>sm52</sm-arch>
|
||||
<sm-arch>sm53</sm-arch>
|
||||
<sm-arch>sm60</sm-arch>
|
||||
<sm-arch>sm61</sm-arch>
|
||||
<sm-arch>sm70</sm-arch>
|
||||
<sm-arch>sm72</sm-arch>
|
||||
<sm-arch>sm75</sm-arch>
|
||||
<sm-arch>sm80</sm-arch>
|
||||
<sm-arch>sm86</sm-arch>
|
||||
<sm-arch>sm87</sm-arch>
|
||||
<sm-arch>sm89</sm-arch>
|
||||
<sm-arch>sm90</sm-arch>
|
||||
<supported_envs>
|
||||
<env>
|
||||
<arch>x86_64</arch>
|
||||
<platform>linux</platform>
|
||||
</env>
|
||||
<env>
|
||||
<platform>windows7</platform>
|
||||
</env>
|
||||
<env>
|
||||
<arch>x86_64</arch>
|
||||
<platform>macosx</platform>
|
||||
</env>
|
||||
<env>
|
||||
<arch>arm</arch>
|
||||
</env>
|
||||
<env>
|
||||
<arch>sbsa</arch>
|
||||
</env>
|
||||
<env>
|
||||
<arch>ppc64le</arch>
|
||||
<platform>linux</platform>
|
||||
</env>
|
||||
</supported_envs>
|
||||
<supported_sm_architectures>
|
||||
<include>all</include>
|
||||
</supported_sm_architectures>
|
||||
<title>DCT8x8</title>
|
||||
<type>exe</type>
|
||||
<whitepaper>doc\dct8x8.pdf</whitepaper>
|
||||
</entry>
|
||||
Reference in New Issue
Block a user