Mirror of github.com/cira0100/Eglantine-public nx2, a fork of Djihads80/Eglantine. https://git.cirakg.xyz/eglantine-cirakg/atom?h=nx2 2026-11-02T16:24:19+00:00 2026-11-02T16:24:19+00:00 Takoroka 137927095+Takoroka@users.noreply.github.com 2026-11-02T16:24:19+00:00 urn:sha1:8f1435f8db104351fa3388551eee9d12d2043b40 The trees fix (#52) drains the split and flushes for every command list on a GPU-written page: in a Mario Kart World race ~13,500 lists and ~400 GPU round trips a second, during which the back has nothing to do. The replay ran at ~40 fps instead of ~45. The front now marks the pages those lists are on. The buffer cache notes writes to them; after a compute dispatch or DMA copy that writes one it copies the page into host memory and submits. The front waits for the back only up to the last compute or copy work it sent (not everything queued), then reads the copy once the GPU is done with it. Pages the GPU wrote once, long before, and the CPU now writes lists to have no copy: their first list drains and flushes the whole page, which is then read from guest memory until GPU work writes it again. CPU writes and inline uploads reach guest memory, so they keep such a page synced but make a copy stale. A page a draw writes always drains. Mario Kart World time-trial replay, Radeon 780M: ~40 -> ~45 fps, trees drawn, no list drains left. 2026-10-30T15:00:28+00:00 Djihads 76681596+Djihads80@users.noreply.github.com 2026-10-30T15:00:28+00:00 urn:sha1:9e2d8d27a8f8065a74fd3d4eb51efc426bd742f7 nx2: Fix the current crash when switching from fast to accurate and vice versa 2026-10-30T13:57:05+00:00 kraibse 33869366+kraibse@users.noreply.github.com 2026-10-30T13:57:05+00:00 urn:sha1:dfb3241838c17bd0e6c392cc29f24d085185dd73 The split starts only with unsafe command reads, decided once at start-up. Switching to accurate afterwards made the front thread flush caches the back thread owns, which raced on Scheduler::chunk and crashed. MaybeStart now re-checks the settings between commands: it drains and stops the split when they no longer allow it and starts it again when they do. DmaPusher keeps unsafe reads while the split is active to cover the gap until then. 2026-10-30T12:58:10+00:00 givethesourceplox 272928635+givethesourceplox@users.noreply.github.com 2026-10-30T12:58:10+00:00 urn:sha1:9ad01b60c8cefe0bb2d91eabf67cf54a1eeeb92c Pause() fell back to a sched_yield system call on arm64; use the yield instruction like the x86 PAUSE. Mark the Windows-only back thread id unused for clang. Assisted-by: Claude (Anthropic) 2026-10-30T04:54:38+00:00 Takoroka 137927095+Takoroka@users.noreply.github.com 2026-10-30T04:54:19+00:00 urn:sha1:092c16d6f39b395e7b3e105a42963733bf9de045 GpuSplit is a static instance and outlives the emulation session. Stop() joined the back thread but kept the ring positions and engine pointers, so the next session's back thread started reading at 0 of a new, empty ring while `published` still held the old session's position: each empty entry reads as a wrap, the back thread skipped ahead a ring at a time and never landed on the old position. The front then spun in Drain(), the next game's first GPU work never ran, and it waited on its first syncpoint forever (Mario Kart World loaded after another Switch 2 game: syncpoint 2 stuck at 0, waiting for 2). The back thread also held the previous session's freed engines. Stop() now drops the ring and resets the positions, the engines and the front macro mode, so MaybeStart() begins a clean ring. 2026-10-30T00:49:48+00:00 Takoroka 137927095+Takoroka@users.noreply.github.com 2026-10-29T15:55:07+00:00 urn:sha1:15e953cafd5cb348833cb373d7ddd996b81307f7 Clean A/B in title 1 (3 rounds each): 1.46x the draws a second of one thread, frames 17% shorter, no crashes, front register copies equal to the back's in 57,089 checks. EDEN_NX2_SPLIT=0 runs everything on one thread, =1 keeps macros on the back. The front's per-write paths no longer check guarded statics (GpuSplit::Get, Nx2Profile::Enabled, the skip-same switches) and the ring's method writes are inline. Notes row 145. 2026-10-30T00:49:48+00:00 Takoroka 137927095+Takoroka@users.noreply.github.com 2026-10-29T15:16:43+00:00 urn:sha1:7a251d3a92f870649dab6068007ca3a1c910bbb5 The GPU thread (front) takes the CPU's commands, parses command lists and runs the puller; engine method calls and everything behind them (registers, draws, dispatches, the rasterizer and its caches) run in order on a second thread (back), fed through a single-producer single-consumer ring (gpu_split.h). Work the front did on back-owned state (end of command list flushes, channel binds, semaphore releases, syncpoint increments, flush/invalidate requests, presentation) is deferred into the same ring; the front waits for the back only where it needs a result from that state: semaphore acquires and MME DMA reads. EDEN_NX2_SPLIT=1 runs macros on the back. EDEN_NX2_SPLIT=2 runs the 3D and compute macros on the front against copies of the registers they read (Maxwell3D/KeplerCompute Front*), drops state writes that keep a register's value there, and sends the rest. EDEN_NX2_SPLIT_VERIFY=1 compares the copies with the back's registers every 4096 macro calls (0 differences in 40,193 checks in title 1); EDEN_NX2_SPLIT_CHECK=1 logs the stack of any other thread using the Vulkan scheduler while the back runs. Switch 2 titles, Vulkan, non-accurate GPU only. Title 1, 3D attract loop: ~44,000 draws a second on one thread, ~47,400 with EDEN_NX2_SPLIT=1, 50,000-66,500 with EDEN_NX2_SPLIT=2.