woutermans 4064117244 zluda: skip compiling modules whose kernels are all native (0014) ...

DLSS loads every module of a model at feature creation and ZLUDA compiled
each one, even when the bridge had already linked a native kernel for every
visible entry and the compiled code never ran. On RDNA2 the transformer
layers emulate MMA and each took minutes in LLVM's register allocator, so
install.sh's K test frame looked hung for about half an hour on a Steam Deck.

Such a module (no globals, 64-bit) now loads the first native code object as
a stand-in and keeps its PTX; it is compiled only if a function without a
native replacement is requested. The K frame takes ~40 s on the Deck.

2026-10-18 23:03:58 +02:00

..

git-hooks

Add redistribution guard

2026-10-10 20:54:31 +02:00

build_bench_dlss_kernel.sh

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

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

build_d3d12_dlss_harness.sh

Add experimental preset L and fix DLSS resource lifetimes and waits

2026-10-02 00:30:46 -04:00

build_d3d12_hip_interop_probe.sh

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

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

build_d4r_motion_kernels.sh

release: prepare 0.1.5 with RDNA2 kernels and in-game DLSS/FSR switching

2026-10-17 16:05:09 -04:00

build_d4r_nvapi_identity.sh

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

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

build_d4r_nvngx_shim.sh

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

2026-10-18 20:39:26 +02:00

build_fsr_rr_probe.sh

rr: add FSR Ray Regeneration, exact RDNA3 inference and motion experiments

2026-10-16 04:55:25 -04:00

build_hip_vk_interop_probe.sh

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

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

build_hip_vk_texture_stale_repro.sh

Document the linear-texture input investigation

2026-10-07 11:00:26 +02:00

build_k_ldr_output.sh

shim: adaptive marker polling, opt-in GPU-side input wait/completion and RGBA8 output

2026-10-13 22:30:41 -04:00

build_microcuda.sh

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

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

build_ngx_cuda_probe.sh

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

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

build_ngx_d3d12_probe.sh

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

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

build_ngx_load_probe.sh

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

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

build_ngx_vulkan_probe.sh

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

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

build_release_glibc241.sh

zluda: skip compiling modules whose kernels are all native (0014)

2026-10-18 23:03:58 +02:00

build_replay_dlss_fp8_ops.sh

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

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

build_replay_dlss_histogram.sh

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

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

build_replay_dlss_kernel.sh

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

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

build_replay_dlss_layer.sh

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

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

build_replay_dlss_surface_half_store.sh

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

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

build_replay_dlss_surface_store.sh

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

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

build_replay_dlss_texture_sample.sh

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

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

build_rr_backend_check.sh

rr: add FSR Ray Regeneration, exact RDNA3 inference and motion experiments

2026-10-16 04:55:25 -04:00

build_vkd3d_proton_d4r.sh

rr: add FSR Ray Regeneration, exact RDNA3 inference and motion experiments

2026-10-16 04:55:25 -04:00

build_vulkan_dlss_harness.sh

Add experimental native Vulkan DLSS frontend

2026-10-09 02:57:23 -04:00

build_vulkan_staging.sh

rr: add FSR Ray Regeneration, exact RDNA3 inference and motion experiments

2026-10-16 04:55:25 -04:00

build_wine_nvcuda_bridge.sh

Add experimental preset L and fix DLSS resource lifetimes and waits

2026-10-02 00:30:46 -04:00

build_zluda_ptx_helpers.sh

Add DLSS accuracy mode and GLIBC 2.41 release builds

2026-10-01 01:35:39 -04:00

check_environment.sh

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

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

check_glibc_compat.sh

Fix DLSS artifacts and improve synchronization diagnostics

2026-09-30 23:17:25 -04:00

check_redistributable.py

release: install.sh downloads DLSS RR 310.9.1 and builds the engine's models

2026-10-14 20:10:17 +02:00

configure_optiscaler.py

Fix OptiScaler NGX routing and align marker polling defaults

2026-10-02 16:32:49 -04:00

d4r_config.py

release: prepare 0.1.5 with RDNA2 kernels and in-game DLSS/FSR switching

2026-10-17 16:05:09 -04:00

d4r_play.sh

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

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

d4r_proton_env.sh

Add RDNA4 (gfx12) support and a 0.1.2 optimization round

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

fetch_rocm_runtime.sh

Bundle the ROCm 7.2.4 runtime in the release zip

2026-09-27 18:59:07 -04:00

install_d4r_runtime.sh

Add CUDA NGX Ray Reconstruction support

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

package_release.sh

release: prepare 0.1.5 with RDNA2 kernels and in-game DLSS/FSR switching

2026-10-17 16:05:09 -04:00

private_d3d12_core.py

ASI add-on for existing OptiScaler installs

2026-10-12 17:36:01 -04:00

run_bench_dlss_kernel.sh

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

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

run_d3d12_dlss_harness_optiscaler_proton.sh

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

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

run_d3d12_dlss_harness_proton.sh

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

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

run_d3d12_dlss_harness.sh

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

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

run_d3d12_hip_interop_probe.sh

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

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

run_fsr_rr_probe_proton.sh

rr: add FSR Ray Regeneration, exact RDNA3 inference and motion experiments

2026-10-16 04:55:25 -04:00

run_game_d4r_optiscaler_proton.sh

Engine: native presets K and M in the D3D12 shim, wider game coverage

2026-10-10 20:54:01 +02:00

run_hip_vk_interop_probe.sh

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

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

run_ngx_cuda_probe.sh

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

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

run_ngx_d3d12_probe.sh

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

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

run_ngx_load_probe.sh

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

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

run_ngx_vulkan_probe.sh

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

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

run_replay_dlss_fp8_ops.sh

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

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

run_replay_dlss_histogram.sh

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

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

run_replay_dlss_kernel.sh

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

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

run_replay_dlss_surface_half_store.sh

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

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

run_replay_dlss_surface_store.sh

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

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

run_replay_dlss_texture_sample.sh

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

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

run_rr_backend_check_proton.sh

rr: add FSR Ray Regeneration, exact RDNA3 inference and motion experiments

2026-10-16 04:55:25 -04:00

run_rr_engine_compare.sh

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

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

run_rr_guide_compare.sh

Keep RR guides and separate alpha in VRAM

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

run_vulkan_dlss_harness_proton.sh

Add experimental native Vulkan DLSS frontend

2026-10-09 02:57:23 -04:00

stage_engine_kit.sh

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

2026-10-18 20:39:26 +02:00

summarize_d4r_profile.py

rr: add FSR Ray Regeneration, exact RDNA3 inference and motion experiments

2026-10-16 04:55:25 -04:00