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.
79 lines
2.1 KiB
Plaintext
79 lines
2.1 KiB
Plaintext
|
|
#version 450
|
|
#define LOCAL_SZ_X 256
|
|
|
|
layout(binding = 0) readonly buffer buf0{
|
|
float input_buffer[]; // outer_size * channels * channel_size
|
|
};
|
|
layout(binding = 1) buffer buf1{
|
|
float max_buffer[]; // outer_size * channel_size
|
|
};
|
|
layout(binding = 2) buffer buf2{
|
|
float sum_buffer[]; // outer_size * channel_size
|
|
};
|
|
layout(binding = 3) buffer buf3{
|
|
float output_buffer[]; // outer_size * channels * channel_size
|
|
};
|
|
layout(push_constant) uniform pushBlock {
|
|
int channel_size;
|
|
int outer_size;
|
|
int channels;
|
|
} p;
|
|
layout(local_size_x = LOCAL_SZ_X, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
void main()
|
|
{
|
|
int gid = int(gl_GlobalInvocationID.x);
|
|
if (gid >= p.outer_size) return;
|
|
|
|
int global_off = gid * p.channels * p.channel_size;
|
|
int reduced_buffer_off = gid * p.channel_size;
|
|
|
|
// find the max along channel
|
|
int index = global_off;
|
|
for (int i = 0; i < p.channel_size; ++i)
|
|
{
|
|
max_buffer[reduced_buffer_off + i] = input_buffer[index];
|
|
index++;
|
|
}
|
|
for (int c = 1; c < p.channels; ++c)
|
|
{
|
|
for (int i = 0; i < p.channel_size; ++i)
|
|
{
|
|
max_buffer[reduced_buffer_off + i] = max(max_buffer[reduced_buffer_off + i], input_buffer[index]);
|
|
index++;
|
|
}
|
|
}
|
|
|
|
// substract, exp and accumulate along channel
|
|
for (int i = 0; i < p.channel_size; ++i)
|
|
sum_buffer[reduced_buffer_off + i] = 0.f;
|
|
|
|
index = global_off;
|
|
for (int c = 0; c < p.channels; ++c)
|
|
{
|
|
for (int i = 0; i < p.channel_size; ++i)
|
|
{
|
|
float exp_val = exp(input_buffer[index] - max_buffer[reduced_buffer_off + i]);
|
|
output_buffer[index] = exp_val;
|
|
sum_buffer[reduced_buffer_off + i] += exp_val;
|
|
index++;
|
|
}
|
|
}
|
|
|
|
// divide by computed sum
|
|
index = global_off;
|
|
for (int c = 0; c < p.channels; ++c)
|
|
{
|
|
for (int i = 0; i < p.channel_size; ++i)
|
|
{
|
|
float v = output_buffer[index] / sum_buffer[reduced_buffer_off + i];
|
|
#ifdef LOG_SOFTMAX
|
|
v = log(v);
|
|
#endif
|
|
output_buffer[index] = v;
|
|
index++;
|
|
}
|
|
}
|
|
}
|