diff --git a/nx2navi.ini.example b/nx2navi.ini.example index 2f107f78..ac545fef 100644 --- a/nx2navi.ini.example +++ b/nx2navi.ini.example @@ -854,6 +854,12 @@ # last one it finished. Unset: on AMD GPUs (VK_AMD_buffer_marker). 1: also on NVIDIA GPUs # (VK_NV_device_diagnostic_checkpoints), which NVIDIA says costs a little. 0: off. # pass_crumbs = 1 +# Pipelines built without the video driver's shader optimiser: the same picture, slower shaders in those pipelines. +# mesh: only the pipelines with task and mesh shaders (terrain, foliage). 1: all. 0: none. +# Unset (default): mesh on AMD's Windows driver for the RX 5000 and RX 6000 series and older, where the device is lost +# ("driver timeout") in render passes that start with such a pipeline; 0 on every other driver. On those cards 0 gives +# the optimised pipelines back. +# vk_noopt = mesh # GPU draw marks, for a GPU crash (device lost) that comes back in the same place on an AMD GPU: inside each render pass # a mark is written wherever the shaders change, and after the crash the log names the shaders of the draws the GPU had # not finished, not only the pass. It costs a little frame rate, so it is off unless a crash is being tracked down. diff --git a/runtime/cfg.c b/runtime/cfg.c index c50354f3..aeba5924 100644 --- a/runtime/cfg.c +++ b/runtime/cfg.c @@ -344,7 +344,7 @@ static const CfgMeta metas[] = { {"VK_RECONVERGE", "1", "0|1", RESTART}, // vk_pipeline.c spirv_reconverge {"VK_NAN_PRESERVE", "", "0|1", RESTART}, // vk_pipeline.c spirv_nan_preserve; unset: every driver but NVIDIA's {"VK_NAN_BITS", "", "0|1", RESTART}, // vk_pipeline.c spirv_nan_bits; unset: AMD's driver for RDNA 1 and 2 - {"VK_NOOPT", "0", "0|1|mesh", RESTART}, // vk_pipeline.c noopt_flag_for + {"VK_NOOPT", "", "0|1|mesh", RESTART}, // vk_pipeline.c noopt_flag_for; unset: mesh on AMD's driver for RDNA 1 and 2 // diagnostics {"TRACE", "", NULL, RESTART}, {"FLIGHT", "0", "0|1", RESTART}, {"FLIGHT_SPIKE_MS", "100", "0..60000", RESTART}, {"WB_FENCE_LIMIT", "65536", "0..1073741824", RESTART}, {"WB_MERGE", "1", "0|1", RESTART}, {"WB_EXACT", "1", "0|1", RESTART}, {"MEM_CENSUS", "0", "0|1", RESTART}, {"WB_NO_REUP", "1", "0|1", RESTART}, {"WB_PROBE", "0", "0|1", RESTART}, {"WB_SPLIT", "1", "0|1|2|3", RESTART}, {"WB_LAZY", WB_LAZY_DEFAULT, "0|1", RESTART}, {"HEAP_LAZY", "0", "0|1", RESTART}, {"WB_LAZY_TOUCH", "0", "0..16", RESTART}, {"WB_LAZY_CHUNK", "0", "0|1", RESTART}, {"FLUSH_UPLOAD", "0", "0|1", RESTART}, {"GPA_TWIN_MAX_KB", "0", "0..1048576", RESTART}, diff --git a/runtime/vk_pipeline.c b/runtime/vk_pipeline.c index 36040e6e..185969f5 100644 --- a/runtime/vk_pipeline.c +++ b/runtime/vk_pipeline.c @@ -3171,14 +3171,27 @@ static int is_src1(unsigned f) { return f >= NVN_BLEND_FUNC_SRC1_COLOR && f <= N // which NX2navi never sets (0 of 876 pipelines in the field and fight saves). // NX2NAVI_VK_NOOPT=1: pipelines built without the driver's optimiser, for a driver whose shader compiler crashes on // one (the test switch for such a report); slower shaders, the same picture. mesh: only pipelines with task and mesh -// stages, the foliage's, whose optimiser is the suspect in device losses some minutes into a forest on AMD GPUs. +// stages, the terrain's and the foliage's. 0: none. +// Unset: mesh on AMD's Windows driver for RDNA 1 and 2 (vk_caps.amd_sc), 0 elsewhere. That driver loses the device +// ("No fault detected", a timeout) minutes into play on RX 6600 to RX 6950 XT cards in every version from 0.6.0 to +// 0.9.2, with the pipeline library on or off and the lazy write-back on or off. Where the reports' pass marks name a +// pass the GPU was in, twelve logs of five reporters, it is a pass whose first draw is a mesh pipeline (mesh shader +// ba4302f1 with fragment shader f64a96dd in nine, the one-draw pass of 1bbdb17e with 6cc3a476 in three); the five +// logs of 0.9.1 and 0.9.2 stop between the compute dispatch before such a pass and the pass. No reporter ran with +// the optimiser off, so that it is the cause is not shown: it is the one suspect the marks leave, it costs shader +// speed in those pipelines and not the picture, and NX2NAVI_VK_NOOPT=0 gives the optimised ones back. The flag is +// part of what the driver's cache keys a pipeline by, so those pipelines are built once more after the change. static VkPipelineCreateFlags noopt_flag_for(int mesh) { static int on = -1; if (on < 0) { - const char *v = cfg_value("NX2NAVI_VK_NOOPT"); - on = !strcmp(v, "mesh") ? 2 : strcmp(v, "0") != 0; - if (on) rt_log("vk_pipeline: %s built without the driver's optimiser (NX2NAVI_VK_NOOPT)", - on == 2 ? "pipelines with task and mesh stages" : "pipelines"); + const char *v = cfg_get("NX2NAVI_VK_NOOPT"); + int by_driver = !v || !*v; + on = by_driver ? (vk_caps.amd_sc ? 2 : 0) : !strcmp(v, "mesh") ? 2 : strcmp(v, "0") != 0; + if (on) rt_log("vk_pipeline: %s built without the driver's optimiser (%s)", + on == 2 ? "pipelines with task and mesh stages" : "pipelines", + by_driver ? "the default on AMD's driver for RDNA 1 and 2, where the device is lost in passes " + "that start with such a pipeline; NX2NAVI_VK_NOOPT=0 builds them optimised" + : "NX2NAVI_VK_NOOPT"); } return on == 1 || (on == 2 && mesh) ? VK_PIPELINE_CREATE_DISABLE_OPTIMIZATION_BIT : 0; }