diff --git a/runtime/host.h b/runtime/host.h index 693c127c..f0bac455 100644 --- a/runtime/host.h +++ b/runtime/host.h @@ -51,9 +51,9 @@ void perf_count(int kind); // NX2NAVI_TRACE=perf: work on any thread that a frame can wait for besides the render thread's waits above, summed per // frame and per 60-frame window (perf.c perf_mark_add): RomFS reads, host zstd decodes, pipeline creates (vk_pipeline.c // pipe_create_in), guest memory maps (heap size, MapPhysicalMemory), NVN memory pool initialize and finalize -// (vk_memory.c vk_pool_init, vk_pool_fini), and device memory VMA allocates (blocks and dedicated memory: count and -// bytes, no time). perf_mark_begin returns 0 while the trace is off, so a normal run pays one branch per site. -enum { PERF_M_FILE, PERF_M_ZSTD, PERF_M_PIPE, PERF_M_GMEM, PERF_M_POOL, PERF_M_DEVMEM, PERF_M_N }; +// (vk_memory.c vk_pool_init, vk_pool_fini), device memory VMA allocates (blocks and dedicated memory: count and +// bytes, no time), and DLSS and DLSS frame generation feature creates (vk_dlaa.c). perf_mark_begin returns 0 while the trace is off, so a normal run pays one branch per site. +enum { PERF_M_FILE, PERF_M_ZSTD, PERF_M_PIPE, PERF_M_GMEM, PERF_M_POOL, PERF_M_DEVMEM, PERF_M_NGX, PERF_M_N }; uint64_t perf_mark_begin(void); void perf_mark_end(int kind, uint64_t t0, uint64_t bytes); // nothing when t0 is 0 void perf_mark_add(int kind, uint64_t ns, uint64_t bytes); // nothing while the trace is off diff --git a/runtime/perf.c b/runtime/perf.c index 23e59b0f..f5c24e28 100644 --- a/runtime/perf.c +++ b/runtime/perf.c @@ -121,7 +121,8 @@ void perf_count(int kind) { // ---- NX2NAVI_TRACE=perf work marks (host.h PERF_M_*): any thread adds; the present takes the frame's sums (mark_frame), // names them on a slow frame's line and adds them to the 60-frame window's line. static const char *const mark_name[PERF_M_N] = {"file reads", "zstd decodes", "pipeline creates", "guest memory maps", - "pool init/finalize", "device memory allocations"}; + "pool init/finalize", "device memory allocations", + "DLSS feature creates"}; static volatile int64_t mk_ns[PERF_M_N], mk_n[PERF_M_N], mk_bytes[PERF_M_N], mk_max[PERF_M_N]; // since the last present typedef struct { uint64_t ns[PERF_M_N], n[PERF_M_N], bytes[PERF_M_N], max[PERF_M_N]; } MarkSums; static MarkSums mk_win; // the 60-frame window's, present thread only diff --git a/runtime/vk_dlaa.c b/runtime/vk_dlaa.c index 62840fa8..eed9b6b8 100644 --- a/runtime/vk_dlaa.c +++ b/runtime/vk_dlaa.c @@ -1643,6 +1643,8 @@ static void evaluate(VkExec *ex, const VkExecTarget *dst) { goto evaluated; } if (!e->feat) { + // NX2NAVI_TRACE=perf: the release of the kept features (a device idle wait) and the create, as one mark + uint64_t t0 = perf_mark_begin(); if (idle_free() != 2) release_kept(e, feat_released); feat_released = 0; p_setu(p, "CreationNodeMask", 1); @@ -1667,6 +1669,7 @@ static void evaluate(VkExec *ex, const VkExecTarget *dst) { p_setu(p, "DLSS.Hint.Render.Preset.Performance", (unsigned)pm); p_setu(p, "DLSS.Hint.Render.Preset.UltraPerformance", (unsigned)pl); NgxResult r = N.create(cb, NGX_FEATURE_SUPERSAMPLING, p, &e->feat); + perf_mark_end(PERF_M_NGX, t0, 0); if (!NGX_OK(r) || !e->feat) return dl_fail("DLSS feature creation", r); D.reset = 1; int q = perf_quality(w, ow), pr = q == 0 ? pm : q == 3 ? pl : pk; @@ -2162,7 +2165,9 @@ int vk_ngxfg_evaluate(VkCommandBuffer cb, const VkNgxImage *bb, const VkNgxImage p_setu(p, "Width", bb->w); p_setu(p, "Height", bb->h); p_setu(p, "DLSSG.BackbufferFormat", (unsigned)bb->fmt); + uint64_t t0 = perf_mark_begin(); NgxResult r = N.create(cb, NGX_FEATURE_FRAME_GENERATION, p, &FG.feat); + perf_mark_end(PERF_M_NGX, t0, 0); if (!NGX_OK(r) || !FG.feat) { FG.failed = 1, FG.feat = NULL; rt_log("ngxfg: DLSS Frame Generation feature creation failed (%08x): frame generation off", (unsigned)r);