From 33c72eb68f66dd3c727bb20a5248ecebc860ca31 Mon Sep 17 00:00:00 2001 From: phantoslayer21 <156617979+phantoslayer21@users.noreply.github.com> Date: Sat, 14 Nov 2026 14:43:04 -0500 Subject: [PATCH 1/2] D3D12 executor: measure a network larger than the default arena again in a 4095 MiB arena (Fixes #182) Model L at 3840x2160 native needs 2738 MiB of native D3D12 arena. The executor measured the network in the default 2560 MiB arena, ran out, and handed the context to the HIP executor, whose process keeps HIP's instance and the pooled imported arena after the context is destroyed (+1419 MiB, constant per cycle). The measure is now repeated in a 4095 MiB arena (WG_D3D12_ARENA_MB's upper bound) when the default one runs out and WG_D3D12_ARENA_MB is not set; the retry and its outcome are logged. Contexts that fit the default arena take the same path as before. Record: clean/l/records/issue182_create_destroy_record.json (5 create/destroy cycles each, Model L and Model M at 4K native and 4K Quality: executor dx12 in every cycle, +2 MiB after every destroy; control with the retry off: executor hip, +1419 MiB). Signed-off-by: phantoslayer21 <156617979+phantoslayer21@users.noreply.github.com> --- clean/FORMATS.md | 11 + .../issue182_create_destroy_record.json | 208 ++++++++++++++++++ clean/runtime/interop/executor_d3d12.cpp | 42 +++- 3 files changed, 257 insertions(+), 4 deletions(-) create mode 100644 clean/l/records/issue182_create_destroy_record.json diff --git a/clean/FORMATS.md b/clean/FORMATS.md index adc064e3..1f37fb82 100644 --- a/clean/FORMATS.md +++ b/clean/FORMATS.md @@ -467,6 +467,17 @@ see "Context teardown and re-creation"). Other keys go to the network runtime's `k_input=16|f32` (model K's input pass, below); the create flag `WG_CREATE_HDR` reaches it as `WgRtConfig.hdr`; timing log parts then named exposure, input, network, output). +The D3D12 executor makes the network's allocations twice: once to measure the arena they need, in the default arena +(`WG_D3D12_ARENA_MB`, 2560 MiB), then in an arena of exactly that size (executor_d3d12.cpp `prepare_device`). A network +that does not fit the default arena is measured again in a 4095 MiB arena, the largest (logged `the network does not fit +the default arena (...); measuring again in a 4095 MiB arena`, then `measured in the 4095 MiB arena: the network needs N +MiB; the D3D12 executor runs it in an arena of that size` or `measuring again in a 4095 MiB arena failed (...)`); not +when `WG_D3D12_ARENA_MB` is set. Model L at 3840x2160 native needs 2738 MiB and runs on the D3D12 executor this way +(clean/l/records/issue182_create_destroy_record.json; issue #182). If the second measure fails too, the context goes to +the HIP executor (`executor dx12 (default on RDNA 4) could not take this context (...); the HIP executor runs it`), and +after it is destroyed the process keeps HIP's instance and the pooled imported arena until it ends, as "Context +teardown and re-creation" describes (the same record's control: +1419 MiB after every destroy, constant). + ### Shared resources (created at create on the game's device, imported into HIP) Two slots (used alternately by the frames whose network is enqueued). All ten buffers (twelve with `motion_hi`) live in ONE committed buffer, diff --git a/clean/l/records/issue182_create_destroy_record.json b/clean/l/records/issue182_create_destroy_record.json new file mode 100644 index 00000000..15398721 --- /dev/null +++ b/clean/l/records/issue182_create_destroy_record.json @@ -0,0 +1,208 @@ +{ + "what": "Issue #182: process GPU memory after an upscaler is created and destroyed (5 cycles, no resize), Model L and Model M at 3840x2160 output, native and Quality, with the D3D12 executor's arena re-measure", + "harness": "clean/fsr/tests/test_dll_d3d12.cpp resize_real (WG_TEST_RESIZE_STEPS=0, WG_TEST_RESIZE_CYCLES=5, settle 800 ms): DXGI QueryVideoMemoryInfo, local segment, this process only; the runtime-reported figure is the front end's FFX_API_QUERY_DESC_TYPE_UPSCALE_GPU_MEMORY_USAGE", + "setup": { + "gpu": "AMD Radeon RX 9070 XT (gfx1201), 16191 MiB dedicated", + "base": "main 6622148", + "runtime": "this branch, clean/runner/build.py --model-l --no-model-k, D3D12 kernels build_dx12.py --model-l (68 kernels)", + "front_end": "clean/fsr with WG_MODEL_L=ON, WG_MODEL_K=OFF (test_dll_d3d12 and its front-end copy)", + "runtime_dll_sha256": "276f805d776532f6b0fec5c3d819fb291b22d5fd4a9288aa972d280557b25292", + "front_end_dll_sha256": "b89ceea05b3dd1de875f366266a0bf88bddc7bf3d307bc24f7b06b252529eb55", + "models": "synthetic files from the repository's generators (Model M: synthetic_model.synthetic_tensors(3) with its Swin weights scaled so every stage takes the clamp-free kernels, as a real model's do; Model L: l_frame_check's synthetic model, seed 89); memory depends on the network's shapes, not on the values", + "gpu_runs": "one at a time, each through tools/gpu_slot.py --cap-s 170" + }, + "runs": [ + { + "run": "l4k-native", + "model": "L", + "output": "3840x2160", + "mode": "native (render 3840x2160)", + "what": "fix", + "cycles": 5, + "process_local_mib_before_any_context": 204, + "process_growth_mib_per_cycle_peak": [ + 2742, + 2742, + 2742, + 2742, + 2742 + ], + "runtime_reported_mib": [ + 2739 + ], + "growth_mib_after_each_destroy": [ + 2, + 2, + 2, + 2, + 2 + ], + "executor_per_cycle": [ + "dx12", + "dx12", + "dx12", + "dx12", + "dx12" + ], + "remeasured_in_4095_mib_arena": 5, + "d3d12_arena_need_mib": [ + 2738 + ], + "hip_fallback_lines": 0, + "pooled_arena_kept_lines": 0, + "test_passed": true + }, + { + "run": "l4k-q", + "model": "L", + "output": "3840x2160", + "mode": "Quality (render 2560x1440)", + "what": "fix", + "cycles": 5, + "process_local_mib_before_any_context": 135, + "process_growth_mib_per_cycle_peak": [ + 1444, + 1444, + 1444, + 1444, + 1444 + ], + "runtime_reported_mib": [ + 1441 + ], + "growth_mib_after_each_destroy": [ + 2, + 2, + 2, + 2, + 2 + ], + "executor_per_cycle": [ + "dx12", + "dx12", + "dx12", + "dx12", + "dx12" + ], + "remeasured_in_4095_mib_arena": 0, + "d3d12_arena_need_mib": [], + "hip_fallback_lines": 0, + "pooled_arena_kept_lines": 0, + "test_passed": true + }, + { + "run": "m4k-native", + "model": "M", + "output": "3840x2160", + "mode": "native (render 3840x2160)", + "what": "fix", + "cycles": 5, + "process_local_mib_before_any_context": 204, + "process_growth_mib_per_cycle_peak": [ + 1593, + 1593, + 1593, + 1593, + 1593 + ], + "runtime_reported_mib": [ + 1590 + ], + "growth_mib_after_each_destroy": [ + 2, + 2, + 2, + 2, + 2 + ], + "executor_per_cycle": [ + "dx12", + "dx12", + "dx12", + "dx12", + "dx12" + ], + "remeasured_in_4095_mib_arena": 0, + "d3d12_arena_need_mib": [], + "hip_fallback_lines": 0, + "pooled_arena_kept_lines": 0, + "test_passed": true + }, + { + "run": "m4k-q", + "model": "M", + "output": "3840x2160", + "mode": "Quality (render 2560x1440)", + "what": "fix", + "cycles": 5, + "process_local_mib_before_any_context": 135, + "process_growth_mib_per_cycle_peak": [ + 936, + 936, + 936, + 936, + 936 + ], + "runtime_reported_mib": [ + 933 + ], + "growth_mib_after_each_destroy": [ + 2, + 2, + 2, + 2, + 2 + ], + "executor_per_cycle": [ + "dx12", + "dx12", + "dx12", + "dx12", + "dx12" + ], + "remeasured_in_4095_mib_arena": 0, + "d3d12_arena_need_mib": [], + "hip_fallback_lines": 0, + "pooled_arena_kept_lines": 0, + "test_passed": true + }, + { + "run": "l4k-native-arena2560", + "model": "L", + "output": "3840x2160", + "mode": "native (render 3840x2160)", + "what": "control: same build, WG_D3D12_ARENA_MB=2560 (no re-measure: the behaviour before this change)", + "cycles": 5, + "process_local_mib_before_any_context": 204, + "process_growth_mib_per_cycle_peak": [ + 4230, + 4230, + 4230, + 4230, + 4230 + ], + "runtime_reported_mib": [ + 3433 + ], + "growth_mib_after_each_destroy": [ + 1419, + 1419, + 1419, + 1419, + 1419 + ], + "executor_per_cycle": [ + "hip", + "hip", + "hip", + "hip", + "hip" + ], + "remeasured_in_4095_mib_arena": 0, + "d3d12_arena_need_mib": [], + "hip_fallback_lines": 5, + "pooled_arena_kept_lines": 5, + "test_passed": true + } + ] +} diff --git a/clean/runtime/interop/executor_d3d12.cpp b/clean/runtime/interop/executor_d3d12.cpp index 4d29adf5..fdc90515 100644 --- a/clean/runtime/interop/executor_d3d12.cpp +++ b/clean/runtime/interop/executor_d3d12.cpp @@ -23,6 +23,7 @@ // into an RG32F texture of ours, which the network then reads as its render-size motion texture. #include #include +#include #include #include #include @@ -39,6 +40,10 @@ namespace wgi { namespace { +// The largest native D3D12 arena (WG_D3D12_ARENA_MB's upper bound, 4095 MiB): the arena that measures a network +// larger than the default one. +constexpr uint64_t kMeasureMaxBytes = uint64_t(4095) << 20; + template void release_ref(T*& p) { if (p) p->Release(); @@ -94,15 +99,44 @@ class D3d12Executor : public Executor { const std::string build = cfg_.build_dir ? cfg_.build_dir : "."; // Pass 1 measures the arena the network needs (the default arena is large); pass 2 makes the same allocations in // an arena of exactly that size. The allocation sequence of runtime_create is deterministic. + // A network larger than the default arena (Model L at 4K native: about 3.4 GiB) is measured again in the largest + // arena (kMeasureMaxBytes, WG_D3D12_ARENA_MB's upper bound) unless WG_D3D12_ARENA_MB is set. Without this the + // context went to the HIP executor, whose process keeps HIP's instance and the pooled imported arena after the + // context is destroyed (clean/FORMATS.md "Context teardown and re-creation"; issue #182). uint64_t need = 0; { + const char* arena_env = std::getenv("WG_D3D12_ARENA_MB"); + const bool may_grow = !arena_env || !*arena_env; std::string e; - std::unique_ptr dev = wgrt::make_d3d12_device_on(device, queue_, build, &e); - if (!dev) return *err = "D3D12 device: " + e, false; - wgrt::Runtime* rt = wgrt::runtime_create(c, std::move(dev), &e, true, true); - if (!rt) return *err = "D3D12 runtime: " + e, false; + wgrt::Runtime* rt = nullptr; + bool grown = false; + const std::string max_mib = std::to_string(kMeasureMaxBytes >> 20); + for (uint64_t arena : {uint64_t(0), kMeasureMaxBytes}) { + e.clear(); + std::unique_ptr dev = wgrt::make_d3d12_device_on(device, queue_, build, &e, arena); + if (!dev) { + if (grown && log_) + log_(true, "measuring again in a " + max_mib + " MiB arena failed (" + e + ")"); + return *err = "D3D12 device: " + e, false; + } + rt = wgrt::runtime_create(c, std::move(dev), &e, true, true); + if (rt || !may_grow || arena || e.find("native D3D12 arena exhausted") == std::string::npos) break; + grown = true; + if (log_) + log_(false, "the network does not fit the default arena (" + e + "); measuring again in a " + + max_mib + " MiB arena"); + } + if (!rt) { + if (grown && log_) + log_(true, "measuring again in a " + max_mib + " MiB arena failed (" + e + ")"); + return *err = "D3D12 runtime: " + e, false; + } need = wgrt::d3d12_ext(wgrt::runtime_device(rt))->arena_high_water(); wgrt::runtime_destroy(rt); + if (grown && log_) + log_(false, "measured in the " + max_mib + " MiB arena: the network needs " + + std::to_string((need + (1u << 20) - 1) >> 20) + " MiB; the D3D12 executor runs it in an arena " + "of that size"); } std::string e; std::unique_ptr dev = wgrt::make_d3d12_device_on(device, queue_, build, &e, need + (1u << 20)); From b5a86731cddd34a781382b4197192f5bd97a8aa7 Mon Sep 17 00:00:00 2001 From: phantoslayer21 <156617979+phantoslayer21@users.noreply.github.com> Date: Sat, 14 Nov 2026 15:24:04 -0500 Subject: [PATCH 2/2] Issue #182 record: re-run on the merged tree (main with the Model L encoder fusion); same figures Signed-off-by: phantoslayer21 <156617979+phantoslayer21@users.noreply.github.com> --- clean/l/records/issue182_create_destroy_record.json | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/clean/l/records/issue182_create_destroy_record.json b/clean/l/records/issue182_create_destroy_record.json index 15398721..87e0db54 100644 --- a/clean/l/records/issue182_create_destroy_record.json +++ b/clean/l/records/issue182_create_destroy_record.json @@ -3,10 +3,10 @@ "harness": "clean/fsr/tests/test_dll_d3d12.cpp resize_real (WG_TEST_RESIZE_STEPS=0, WG_TEST_RESIZE_CYCLES=5, settle 800 ms): DXGI QueryVideoMemoryInfo, local segment, this process only; the runtime-reported figure is the front end's FFX_API_QUERY_DESC_TYPE_UPSCALE_GPU_MEMORY_USAGE", "setup": { "gpu": "AMD Radeon RX 9070 XT (gfx1201), 16191 MiB dedicated", - "base": "main 6622148", - "runtime": "this branch, clean/runner/build.py --model-l --no-model-k, D3D12 kernels build_dx12.py --model-l (68 kernels)", + "base": "this branch merged with main (merge cabcd4c)", + "runtime": "this branch, clean/runner/build.py --model-l --no-model-k, D3D12 kernels build_dx12.py --model-l (69 kernels)", "front_end": "clean/fsr with WG_MODEL_L=ON, WG_MODEL_K=OFF (test_dll_d3d12 and its front-end copy)", - "runtime_dll_sha256": "276f805d776532f6b0fec5c3d819fb291b22d5fd4a9288aa972d280557b25292", + "runtime_dll_sha256": "9204b29fa4ba92111235a61473aa0b2f412195aa739a914c957b607c2296ddb0", "front_end_dll_sha256": "b89ceea05b3dd1de875f366266a0bf88bddc7bf3d307bc24f7b06b252529eb55", "models": "synthetic files from the repository's generators (Model M: synthetic_model.synthetic_tensors(3) with its Swin weights scaled so every stage takes the clamp-free kernels, as a real model's do; Model L: l_frame_check's synthetic model, seed 89); memory depends on the network's shapes, not on the values", "gpu_runs": "one at a time, each through tools/gpu_slot.py --cap-s 170"