tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-05 14:43:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: subgroup size test

Browse Source
This commit is contained in:
Daniele
2025-02-09 23:30:13 +00:00
parent 19d3c8293b
commit 7037e94852
1 changed files with 52 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View File

@ -1423,6 +1423,49 @@ static bool ggml_vk_matmul_shmem_support(const vk_device& device, const std::vec
return supported;
}
struct GpuPipelineConfig {
// List of all aliases for a given GPU.
// For example, this can include names like "NAVI10", "RX 5700", etc.
std::vector<std::string> device_names;
// Mapping of pipeline names to their specific subgroup sizes.
// Example: {"soft_max_f32", 64}.
std::unordered_map<std::string, uint32_t> pipelines;
// Default subgroup size for this GPU.
// Defaults to 0 if not explicitly provided.
uint32_t default_subgroup_size = 0;
};
// Define configurations for different GPUs.
static std::vector<GpuPipelineConfig> gpu_pipeline_configs = {
{
{"NAVI10", "NAVI14", "RX 5700", "RX 5600", "RX 5500"},
{
{"soft_max_f32", 64}, {"soft_max_f32_wg512", 64},
{"soft_max_f32_f16", 64}, {"soft_max_f32_f16_wg512", 64},
{"im2col_f32", 64}, {"im2col_f32_f16", 64},
},
32
},
};
static uint32_t get_subgroup_size(const std::string &pipeline_name, const std::string &device_name) {
for (const auto &config : gpu_pipeline_configs) {
for (const auto &alias : config.device_names) {
if (device_name.find(alias) != std::string::npos) {
auto pipIt = config.pipelines.find(pipeline_name);
if (pipIt != config.pipelines.end() && pipIt->second != 0) {
return pipIt->second;
}
return config.default_subgroup_size;
}
}
}
// If no matching configuration is found, return 0.
return 0;
}
static void ggml_vk_load_shaders(vk_device& device) {
VK_LOG_DEBUG("ggml_vk_load_shaders(" << device->name << ")");
@ -1543,11 +1586,17 @@ static void ggml_vk_load_shaders(vk_device& device) {
device->pipeline_matmul_id_f32 = std::make_shared<vk_matmul_pipeline_struct>();
}
vk::PhysicalDeviceProperties2 props2;
device->physical_device.getProperties2(&props2);
std::string device_name = props2.properties.deviceName.data();
std::vector<std::future<void>> compiles;
auto const &ggml_vk_create_pipeline = [&](vk_device& device, vk_pipeline& pipeline, const std::string &name, size_t spv_size, const void* spv_data, const std::string &entrypoint,
uint32_t parameter_count, uint32_t push_constant_size, std::array<uint32_t, 3> wg_denoms, const std::vector<uint32_t>& specialization_constants,
uint32_t align, bool disable_robustness = false, bool require_full_subgroups = false, uint32_t required_subgroup_size = 0) {
required_subgroup_size = get_subgroup_size(name, device_name);
if (!pipeline) {
pipeline = std::make_shared<vk_pipeline_struct>();
pipeline->name = name;
@ -2699,7 +2748,9 @@ static void ggml_vk_print_gpu_info(size_t idx) {
subgroup_props.pNext = &driver_props;
physical_device.getProperties2(&props2);
const size_t subgroup_size = subgroup_props.subgroupSize;
uint32_t default_subgroup_size = get_subgroup_size("", props2.properties.deviceName.data());
const size_t subgroup_size = (default_subgroup_size != 0) ? default_subgroup_size : subgroup_props.subgroupSize;
const bool uma = props2.properties.deviceType == vk::PhysicalDeviceType::eIntegratedGpu;
bool fp16_storage = false;