engine: Super Resolution presets E and F, the DLSS 3 CNN, on RDNA2

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.
This commit is contained in:
woutermans committed 2026-10-18 20:39:26 +02:00
1 parent 0e851b7f90
commit b9254f7f96
25 files changed
+2406 -36

No files matched your search

+10
View File
@@ -24,6 +24,10 @@ struct VkTable {
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;
@@ -44,6 +48,7 @@ struct VkTable {
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;
@@ -72,6 +77,10 @@ bool loadVulkan(PFN_vkGetInstanceProcAddr instanceProc, VkInstance instance, VkD
#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
@@ -92,6 +101,7 @@ bool loadVulkan(PFN_vkGetInstanceProcAddr instanceProc, VkInstance instance, VkD
#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