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

+5
View File
@@ -26,6 +26,10 @@ bool loadVulkan(PFN_vkGetInstanceProcAddr instanceProc, VkInstance instance, VkD
ok &= (vkTable.CmdPipelineBarrier = reinterpret_cast<PFN_vkCmdPipelineBarrier>(deviceProc(device, "vkCmdPipelineBarrier"))) != nullptr;
ok &= (vkTable.CmdUpdateBuffer = reinterpret_cast<PFN_vkCmdUpdateBuffer>(deviceProc(device, "vkCmdUpdateBuffer"))) != nullptr;
ok &= (vkTable.CmdWriteTimestamp = reinterpret_cast<PFN_vkCmdWriteTimestamp>(deviceProc(device, "vkCmdWriteTimestamp"))) != nullptr;
ok &= (vkTable.CmdResetQueryPool = reinterpret_cast<PFN_vkCmdResetQueryPool>(deviceProc(device, "vkCmdResetQueryPool"))) != nullptr;
ok &= (vkTable.CreateQueryPool = reinterpret_cast<PFN_vkCreateQueryPool>(deviceProc(device, "vkCreateQueryPool"))) != nullptr;
ok &= (vkTable.DestroyQueryPool = reinterpret_cast<PFN_vkDestroyQueryPool>(deviceProc(device, "vkDestroyQueryPool"))) != nullptr;
ok &= (vkTable.GetQueryPoolResults = reinterpret_cast<PFN_vkGetQueryPoolResults>(deviceProc(device, "vkGetQueryPoolResults"))) != nullptr;
ok &= (vkTable.CreateBuffer = reinterpret_cast<PFN_vkCreateBuffer>(deviceProc(device, "vkCreateBuffer"))) != nullptr;
ok &= (vkTable.CreateComputePipelines = reinterpret_cast<PFN_vkCreateComputePipelines>(deviceProc(device, "vkCreateComputePipelines"))) != nullptr;
ok &= (vkTable.CreateDescriptorPool = reinterpret_cast<PFN_vkCreateDescriptorPool>(deviceProc(device, "vkCreateDescriptorPool"))) != nullptr;
@@ -46,6 +50,7 @@ bool loadVulkan(PFN_vkGetInstanceProcAddr instanceProc, VkInstance instance, VkD
ok &= (vkTable.DestroyShaderModule = reinterpret_cast<PFN_vkDestroyShaderModule>(deviceProc(device, "vkDestroyShaderModule"))) != nullptr;
ok &= (vkTable.FreeMemory = reinterpret_cast<PFN_vkFreeMemory>(deviceProc(device, "vkFreeMemory"))) != nullptr;
ok &= (vkTable.GetBufferMemoryRequirements = reinterpret_cast<PFN_vkGetBufferMemoryRequirements>(deviceProc(device, "vkGetBufferMemoryRequirements"))) != nullptr;
ok &= (vkTable.GetBufferDeviceAddress = reinterpret_cast<PFN_vkGetBufferDeviceAddress>(deviceProc(device, "vkGetBufferDeviceAddress"))) != nullptr;
ok &= (vkTable.GetImageMemoryRequirements = reinterpret_cast<PFN_vkGetImageMemoryRequirements>(deviceProc(device, "vkGetImageMemoryRequirements"))) != nullptr;
ok &= (vkTable.MapMemory = reinterpret_cast<PFN_vkMapMemory>(deviceProc(device, "vkMapMemory"))) != nullptr;
ok &= (vkTable.UnmapMemory = reinterpret_cast<PFN_vkUnmapMemory>(deviceProc(device, "vkUnmapMemory"))) != nullptr;