woutermans 5f520a186d engine/rr: build the Ray Reconstruction models from nvngx_dlssd.dll alone, without a capture ...

Models built from nvngx_dlssd.dll 310.9.1 are byte-identical to the capture-built ones (every file, plus
d4r-rr's outputs on capF, capF4K, capF900, capFXparticles and capDT). 310.9.1 contains 310.7's D/E kernels
and weights.

2026-10-14 20:09:08 +02:00

..

compare_launch_dump.py

kernels: compare two per-launch dumps byte for byte

2026-10-12 12:47:53 +02:00

dump_runner.cpp

Add MicroCUDA backend, adaptive output wait, wider native K coverage (improve perf)

2026-10-07 15:54:38 -04:00

extract_dlss_ptx.py

engine/rr: build the Ray Reconstruction models from nvngx_dlssd.dll alone, without a capture

2026-10-14 20:09:08 +02:00

kernel_manifest.py

kernels: build the denoiser's output kernel natively, authorized separately

2026-10-12 12:47:53 +02:00

kprof.py

d4r: official NVIDIA DLSS on AMD GPUs under Linux and Proton

2026-09-27 15:26:56 -04:00

model_enc3.py

Add RDNA4 (gfx12) support and a 0.1.2 optimization round

2026-09-29 20:36:10 -04:00

psnr.py

d4r: official NVIDIA DLSS on AMD GPUs under Linux and Proton

2026-09-27 15:26:56 -04:00

ptxload.c

d4r: official NVIDIA DLSS on AMD GPUs under Linux and Proton

2026-09-27 15:26:56 -04:00

ptxsim.py

engine/rr: native Ray Reconstruction stages with capture/replay and shim integration

2026-10-12 12:47:53 +02:00

pwin_check.py

Add RDNA4 (gfx12) support and a 0.1.2 optimization round

2026-09-29 20:36:10 -04:00

pwin_model.py

d4r: official NVIDIA DLSS on AMD GPUs under Linux and Proton

2026-09-27 15:26:56 -04:00

rr_swin_native_test.cpp

engine/rr: native preset F (DLSS 4.5 Ray Reconstruction) and the reference's fused roundings

2026-10-13 13:59:17 +02:00

rrsim.py

engine/rr: native Ray Reconstruction stages with capture/replay and shim integration

2026-10-12 12:47:53 +02:00

rrswin_enc0_engine_test.cpp

engine/rr: native Ray Reconstruction stages with capture/replay and shim integration

2026-10-12 12:47:53 +02:00

rrswin_engine_k16_test.cpp

kernels/rr: staged-image Swin layer engine prototypes

2026-10-12 12:47:53 +02:00

rrswin_fp8_unpaired_test.cpp

kernels/rr: staged-image Swin layer engine prototypes

2026-10-12 12:47:53 +02:00

rrswin_operand_fit.cpp

kernels/rr: staged-image Swin layer engine prototypes

2026-10-12 12:47:53 +02:00

rrswin_operand_probe.cpp

kernels/rr: staged-image Swin layer engine prototypes

2026-10-12 12:47:53 +02:00

rrswin_phase8_fit.py

kernels/rr: staged-image Swin layer engine prototypes

2026-10-12 12:47:53 +02:00

rrswin_phase8_model.py

kernels/rr: staged-image Swin layer engine prototypes

2026-10-12 12:47:53 +02:00

rrswin_pilot_enc0_p8.cpp

kernels/rr: staged-image Swin layer engine prototypes

2026-10-12 12:47:53 +02:00

swin_check.py

Clamp the patch merge to ±2π in the native Swin encoders

2026-10-08 02:21:41 +02:00

swin_mma.py

kernels/rr: staged-image Swin layer engine prototypes

2026-10-12 12:47:53 +02:00

swin_model.py

d4r: official NVIDIA DLSS on AMD GPUs under Linux and Proton

2026-09-27 15:26:56 -04:00

swin_stages.py

kernels/rr: staged-image Swin layer engine prototypes

2026-10-12 12:47:53 +02:00

tail_check.hip

Add RDNA4 (gfx12) support and a 0.1.2 optimization round

2026-09-29 20:36:10 -04:00