mirror of
https://github.com/opencv/opencv.git
synced 2024-12-16 10:29:11 +08:00
6e3ea8b49d
* dnn: Add a Vulkan based backend This commit adds a new backend "DNN_BACKEND_VKCOM" and a new target "DNN_TARGET_VULKAN". VKCOM means vulkan based computation library. This backend uses Vulkan API and SPIR-V shaders to do the inference computation for layers. The layer types that implemented in DNN_BACKEND_VKCOM include: Conv, Concat, ReLU, LRN, PriorBox, Softmax, MaxPooling, AvePooling, Permute This is just a beginning work for Vulkan in OpenCV DNN, more layer types will be supported and performance tuning is on the way. Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com> * dnn/vulkan: Add FindVulkan.cmake to detect Vulkan SDK In order to build dnn with Vulkan support, need installing Vulkan SDK and setting environment variable "VULKAN_SDK" and add "-DWITH_VULKAN=ON" to cmake command. You can download Vulkan SDK from: https://vulkan.lunarg.com/sdk/home#linux For how to install, see https://vulkan.lunarg.com/doc/sdk/latest/linux/getting_started.html https://vulkan.lunarg.com/doc/sdk/latest/windows/getting_started.html https://vulkan.lunarg.com/doc/sdk/latest/mac/getting_started.html respectively for linux, windows and mac. To run the vulkan backend, also need installing mesa driver. On Ubuntu, use this command 'sudo apt-get install mesa-vulkan-drivers' To test, use command '$BUILD_DIR/bin/opencv_test_dnn --gtest_filter=*VkCom*' Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com> * dnn/Vulkan: dynamically load Vulkan runtime No compile-time dependency on Vulkan library. If Vulkan runtime is unavailable, fallback to CPU path. Use environment "OPENCL_VULKAN_RUNTIME" to specify path to your own vulkan runtime library. Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com> * dnn/Vulkan: Add a python script to compile GLSL shaders to SPIR-V shaders The SPIR-V shaders are in format of text-based 32-bit hexadecimal numbers, and inserted into .cpp files as unsigned int32 array. * dnn/Vulkan: Put Vulkan headers into 3rdparty directory and some other fixes Vulkan header files are copied from https://github.com/KhronosGroup/Vulkan-Docs/tree/master/include/vulkan to 3rdparty/include Fix the Copyright declaration issue. Refine OpenCVDetectVulkan.cmake * dnn/Vulkan: Add vulkan backend tests into existing ones. Also fixed some test failures. - Don't use bool variable as uniform for shader - Fix dispathed group number beyond max issue - Bypass "group > 1" convolution. This should be support in future. * dnn/Vulkan: Fix multiple initialization in one thread.
74 lines
2.1 KiB
Plaintext
74 lines
2.1 KiB
Plaintext
#version 450
|
|
#define LOCAL_SZ_X 256
|
|
layout(binding = 0) readonly buffer Input0{
|
|
float image_data[];
|
|
};
|
|
layout(binding = 1) readonly buffer Input1 {
|
|
float bias_data[];
|
|
};
|
|
layout(binding = 2) readonly buffer Input3{
|
|
float weight_data[];
|
|
};
|
|
layout(binding = 3) writeonly buffer Output{
|
|
float convolved_image_data[];
|
|
};
|
|
|
|
layout(push_constant) uniform pushBlock {
|
|
int in_h;
|
|
int in_w;
|
|
int out_h;
|
|
int out_w;
|
|
int stride_h;
|
|
int stride_w;
|
|
int pad_h;
|
|
int pad_w;
|
|
int filter_h;
|
|
int filter_w;
|
|
int dilation_h;
|
|
int dilation_w;
|
|
int channels;
|
|
int batch;
|
|
int has_bias;
|
|
int M;
|
|
int K;
|
|
int N;
|
|
} p;
|
|
|
|
layout(local_size_x = LOCAL_SZ_X, local_size_y = 1, local_size_z = 1) in;
|
|
void main()
|
|
{
|
|
int gx = int(gl_GlobalInvocationID.x);
|
|
int gy = int(gl_GlobalInvocationID.y);
|
|
int gz = int(gl_GlobalInvocationID.z);
|
|
if(gx < p.M && gy < p.N && gz < p.batch)
|
|
{
|
|
float sum = 0.0f;
|
|
int output_y = gx / p.out_w;
|
|
int output_x = gx % p.out_w;
|
|
int org_y = output_y * p.stride_h - p.pad_h;
|
|
int org_x = output_x * p.stride_w - p.pad_w;
|
|
int weight_off = gy * p.K;
|
|
int input_off = gz * p.in_h * p.in_w * p.channels + (org_y * p.in_w + org_x);
|
|
for(int c = 0; c < p.channels; c++)
|
|
{
|
|
for(int y = 0; y < p.filter_h; y++)
|
|
{
|
|
for(int x = 0; x < p.filter_w; x++)
|
|
{
|
|
if((org_y + y * p.dilation_h >= 0) && (org_y + y * p.dilation_h < p.in_h) && (org_x + x * p.dilation_w >= 0) && (org_x + x * p.dilation_w < p.in_w))
|
|
{
|
|
sum += image_data[input_off + x * p.dilation_w] * weight_data[weight_off + x];
|
|
}
|
|
}
|
|
input_off += p.in_w * p.dilation_h;
|
|
weight_off += p.filter_w;
|
|
}
|
|
input_off += p.in_h * p.in_w - p.in_w * p.filter_h * p.dilation_h;
|
|
}
|
|
int offset = gz * p.M * p.N + gx + gy * p.M;
|
|
if (p.has_bias == 1)
|
|
sum += bias_data[gy];
|
|
convolved_image_data[offset] = sum;
|
|
}
|
|
}
|