Presets E (5) and F (6) run on d4r's own Vulkan engine without cooperative matrices: the input and reconstruction kernels translated from the user's DLL (engine/compile_sr_e.py, rr/ptx2rr.py), the network engine/sr/e_net.comp with packed v_pk_fma_f16 accumulation (engine/cnn_sr/mma_f16.glsl, the default head; --head-accumulation f32 keeps the f32 head). Runtime runtime_e.inc (EModel/EEngine), game adapter game_e.cpp, replay d4r-e; the shim serves them from engine\e and engine\f (D4R_ENGINE_MODEL_E_DIR / _F_DIR), LDR or HDR, any render size, not with AutoExposure. build-engine-models.sh builds both. Translator fixes that apply to every translated kernel: .relu on f16/f16x2 fma/add/mul was ignored; add.rz was always taken for the roundf idiom (lost the log1pf correction term); formatted image stores expand at the call site (SPIR-V image type fix); f16 mma.sync m16n8k8/k16, .const loads, shared 16-bit stores, aligned 32-bit arena words (D4R_WORD_ARENA), unified arena. Steam Deck gfx1033: 2.55 ms at 640x360 -> 1280x720, 6.20 ms at 1080p output; Rounded Quality sizes take mid_3x3 (reconstruction 2.44 -> 1.23 ms). Ray Reconstruction CNN presets A-C (compile_rr3.py, the packed RR flavor) stay out of this commit; engine/README.md already documents their tuning.
110 lines
6.2 KiB
C++
110 lines
6.2 KiB
C++
// Vulkan entry points for the engine. A native build links the loader. A build without a Vulkan import
|
|
// library (the MinGW NGX shim) defines D4R_ENGINE_VK_TABLE and fills this table once with loadVulkan().
|
|
#pragma once
|
|
#include <vulkan/vulkan.h>
|
|
#ifdef D4R_ENGINE_VK_TABLE
|
|
namespace d4r {
|
|
struct VkTable {
|
|
PFN_vkGetPhysicalDeviceFormatProperties GetPhysicalDeviceFormatProperties = nullptr;
|
|
PFN_vkGetPhysicalDeviceMemoryProperties GetPhysicalDeviceMemoryProperties = nullptr;
|
|
PFN_vkGetPhysicalDeviceProperties GetPhysicalDeviceProperties = nullptr;
|
|
PFN_vkAllocateDescriptorSets AllocateDescriptorSets = nullptr;
|
|
PFN_vkAllocateMemory AllocateMemory = nullptr;
|
|
PFN_vkBindBufferMemory BindBufferMemory = nullptr;
|
|
PFN_vkBindImageMemory BindImageMemory = nullptr;
|
|
PFN_vkCmdBindDescriptorSets CmdBindDescriptorSets = nullptr;
|
|
PFN_vkCmdBindPipeline CmdBindPipeline = nullptr;
|
|
PFN_vkCmdBlitImage CmdBlitImage = nullptr;
|
|
PFN_vkCmdClearColorImage CmdClearColorImage = nullptr;
|
|
PFN_vkCmdCopyBuffer CmdCopyBuffer = nullptr;
|
|
PFN_vkCmdCopyBufferToImage CmdCopyBufferToImage = nullptr;
|
|
PFN_vkCmdCopyImageToBuffer CmdCopyImageToBuffer = nullptr;
|
|
PFN_vkCmdDispatch CmdDispatch = nullptr;
|
|
PFN_vkCmdFillBuffer CmdFillBuffer = nullptr;
|
|
PFN_vkCmdPipelineBarrier CmdPipelineBarrier = nullptr;
|
|
PFN_vkCmdUpdateBuffer CmdUpdateBuffer = nullptr;
|
|
PFN_vkCmdWriteTimestamp CmdWriteTimestamp = nullptr;
|
|
PFN_vkCmdResetQueryPool CmdResetQueryPool = nullptr;
|
|
PFN_vkCreateQueryPool CreateQueryPool = nullptr;
|
|
PFN_vkDestroyQueryPool DestroyQueryPool = nullptr;
|
|
PFN_vkGetQueryPoolResults GetQueryPoolResults = nullptr;
|
|
PFN_vkCreateBuffer CreateBuffer = nullptr;
|
|
PFN_vkCreateComputePipelines CreateComputePipelines = nullptr;
|
|
PFN_vkCreateDescriptorPool CreateDescriptorPool = nullptr;
|
|
PFN_vkCreateDescriptorSetLayout CreateDescriptorSetLayout = nullptr;
|
|
PFN_vkCreateImage CreateImage = nullptr;
|
|
PFN_vkCreateImageView CreateImageView = nullptr;
|
|
PFN_vkCreatePipelineLayout CreatePipelineLayout = nullptr;
|
|
PFN_vkCreateSampler CreateSampler = nullptr;
|
|
PFN_vkCreateShaderModule CreateShaderModule = nullptr;
|
|
PFN_vkDestroyBuffer DestroyBuffer = nullptr;
|
|
PFN_vkDestroyDescriptorPool DestroyDescriptorPool = nullptr;
|
|
PFN_vkDestroyDescriptorSetLayout DestroyDescriptorSetLayout = nullptr;
|
|
PFN_vkDestroyImage DestroyImage = nullptr;
|
|
PFN_vkDestroyImageView DestroyImageView = nullptr;
|
|
PFN_vkDestroyPipeline DestroyPipeline = nullptr;
|
|
PFN_vkDestroyPipelineLayout DestroyPipelineLayout = nullptr;
|
|
PFN_vkDestroySampler DestroySampler = nullptr;
|
|
PFN_vkDestroyShaderModule DestroyShaderModule = nullptr;
|
|
PFN_vkFreeMemory FreeMemory = nullptr;
|
|
PFN_vkGetBufferMemoryRequirements GetBufferMemoryRequirements = nullptr;
|
|
PFN_vkGetBufferDeviceAddress GetBufferDeviceAddress = nullptr;
|
|
PFN_vkGetImageMemoryRequirements GetImageMemoryRequirements = nullptr;
|
|
PFN_vkMapMemory MapMemory = nullptr;
|
|
PFN_vkUnmapMemory UnmapMemory = nullptr;
|
|
PFN_vkUpdateDescriptorSets UpdateDescriptorSets = nullptr;
|
|
};
|
|
extern VkTable vkTable;
|
|
// False when an entry point is missing. Call before constructing a Model.
|
|
bool loadVulkan(PFN_vkGetInstanceProcAddr instanceProc, VkInstance instance, VkDevice device);
|
|
} // namespace d4r
|
|
#define vkGetPhysicalDeviceFormatProperties ::d4r::vkTable.GetPhysicalDeviceFormatProperties
|
|
#define vkGetPhysicalDeviceMemoryProperties ::d4r::vkTable.GetPhysicalDeviceMemoryProperties
|
|
#define vkGetPhysicalDeviceProperties ::d4r::vkTable.GetPhysicalDeviceProperties
|
|
#define vkAllocateDescriptorSets ::d4r::vkTable.AllocateDescriptorSets
|
|
#define vkAllocateMemory ::d4r::vkTable.AllocateMemory
|
|
#define vkBindBufferMemory ::d4r::vkTable.BindBufferMemory
|
|
#define vkBindImageMemory ::d4r::vkTable.BindImageMemory
|
|
#define vkCmdBindDescriptorSets ::d4r::vkTable.CmdBindDescriptorSets
|
|
#define vkCmdBindPipeline ::d4r::vkTable.CmdBindPipeline
|
|
#define vkCmdBlitImage ::d4r::vkTable.CmdBlitImage
|
|
#define vkCmdClearColorImage ::d4r::vkTable.CmdClearColorImage
|
|
#define vkCmdCopyBuffer ::d4r::vkTable.CmdCopyBuffer
|
|
#define vkCmdCopyBufferToImage ::d4r::vkTable.CmdCopyBufferToImage
|
|
#define vkCmdCopyImageToBuffer ::d4r::vkTable.CmdCopyImageToBuffer
|
|
#define vkCmdDispatch ::d4r::vkTable.CmdDispatch
|
|
#define vkCmdFillBuffer ::d4r::vkTable.CmdFillBuffer
|
|
#define vkCmdPipelineBarrier ::d4r::vkTable.CmdPipelineBarrier
|
|
#define vkCmdUpdateBuffer ::d4r::vkTable.CmdUpdateBuffer
|
|
#define vkCmdWriteTimestamp ::d4r::vkTable.CmdWriteTimestamp
|
|
#define vkCmdResetQueryPool ::d4r::vkTable.CmdResetQueryPool
|
|
#define vkCreateQueryPool ::d4r::vkTable.CreateQueryPool
|
|
#define vkDestroyQueryPool ::d4r::vkTable.DestroyQueryPool
|
|
#define vkGetQueryPoolResults ::d4r::vkTable.GetQueryPoolResults
|
|
#define vkCreateBuffer ::d4r::vkTable.CreateBuffer
|
|
#define vkCreateComputePipelines ::d4r::vkTable.CreateComputePipelines
|
|
#define vkCreateDescriptorPool ::d4r::vkTable.CreateDescriptorPool
|
|
#define vkCreateDescriptorSetLayout ::d4r::vkTable.CreateDescriptorSetLayout
|
|
#define vkCreateImage ::d4r::vkTable.CreateImage
|
|
#define vkCreateImageView ::d4r::vkTable.CreateImageView
|
|
#define vkCreatePipelineLayout ::d4r::vkTable.CreatePipelineLayout
|
|
#define vkCreateSampler ::d4r::vkTable.CreateSampler
|
|
#define vkCreateShaderModule ::d4r::vkTable.CreateShaderModule
|
|
#define vkDestroyBuffer ::d4r::vkTable.DestroyBuffer
|
|
#define vkDestroyDescriptorPool ::d4r::vkTable.DestroyDescriptorPool
|
|
#define vkDestroyDescriptorSetLayout ::d4r::vkTable.DestroyDescriptorSetLayout
|
|
#define vkDestroyImage ::d4r::vkTable.DestroyImage
|
|
#define vkDestroyImageView ::d4r::vkTable.DestroyImageView
|
|
#define vkDestroyPipeline ::d4r::vkTable.DestroyPipeline
|
|
#define vkDestroyPipelineLayout ::d4r::vkTable.DestroyPipelineLayout
|
|
#define vkDestroySampler ::d4r::vkTable.DestroySampler
|
|
#define vkDestroyShaderModule ::d4r::vkTable.DestroyShaderModule
|
|
#define vkFreeMemory ::d4r::vkTable.FreeMemory
|
|
#define vkGetBufferMemoryRequirements ::d4r::vkTable.GetBufferMemoryRequirements
|
|
#define vkGetBufferDeviceAddress ::d4r::vkTable.GetBufferDeviceAddress
|
|
#define vkGetImageMemoryRequirements ::d4r::vkTable.GetImageMemoryRequirements
|
|
#define vkMapMemory ::d4r::vkTable.MapMemory
|
|
#define vkUnmapMemory ::d4r::vkTable.UnmapMemory
|
|
#define vkUpdateDescriptorSets ::d4r::vkTable.UpdateDescriptorSets
|
|
#endif
|