mirror of
https://github.com/tangerineturtle1/NX2navi.git
synced 2026-11-15 19:19:58 -04:00
a8c6e992ee
A mesh draw becomes its record (the workgroup count, copied on the GPU for an indirect draw), the task dispatch, a scan that lists the mesh workgroups the tasks started, the mesh dispatch, and an instanced indirect draw with a generated vertex stage and the program's fragment stage. The compute modules bind the resources of the task and mesh stages, and their pipelines are made on a thread of their own while the program's draws are skipped. The indirect mesh ring and the texture pool marks are released at a probe's shutdown. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
170 lines
15 KiB
C
170 lines
15 KiB
C
// The recorder thread (vk_rec.c): the Vulkan calls the replay makes into its command buffer are made by a thread of
|
|
// their own. vk_sync.c brackets each part of a submission with rec_begin (after vkBeginCommandBuffer) and rec_end
|
|
// (before vkEndCommandBuffer). In between, every vkCmd* on that command buffer copies its arguments into a packet of a
|
|
// ring, in call order, and the recorder makes the real call in that order; calls into any other command buffer (uploads,
|
|
// the window, probes) are made at once. A call the ring has no packet for (a structure with a pNext chain) waits for
|
|
// the recorder to empty the ring and is then made at once on the calling thread. rec_end returns once the recorder made
|
|
// every call. vk_sync.c ends a part through rec_end_cb: the recorder makes the last calls into a part it recorded,
|
|
// vkEndCommandBuffer included; submitting and the command pool stay on the submitting thread.
|
|
//
|
|
// Every vkCmd* the runtime calls through vk.h goes through the rc_* wrappers below (the macros at the end); the
|
|
// extension commands called through function pointers have rec_* wrappers of their own. NX2NAVI_VK_RECORDER=0 makes every
|
|
// call at once (the same calls in the same order), =ab switches it with the A/B blocks (rt_ab), per submission part.
|
|
//
|
|
// A recorder thread makes the Vulkan calls: the driver's work behind the commands depends on nothing the replay decides next.
|
|
#pragma once
|
|
|
|
void rec_begin(VkCommandBuffer cb, uint64_t fence); // the submitting thread, sub_lock held; fence: the part's value
|
|
void rec_end(void); // waits for the recorder; no-op when rec_begin did not start it
|
|
// The end of part cb: the breadcrumb crumb (0: none, vk_crumbs.c), then vkEndCommandBuffer, both made by the recorder
|
|
// when it records cb, and the wait for it (1); otherwise rec_end and the breadcrumb, and the caller ends cb (0).
|
|
int rec_end_cb(VkCommandBuffer cb, int crumb, uint64_t n);
|
|
void rec_drain(void); // waits until the recorder made every call queued so far
|
|
void rec_wait_totals(uint64_t *full_ns, uint64_t *drain_ns); // producer time spent on a full ring and in drains
|
|
void rec_stats_log(void); // NX2NAVI_TRACE=perf: packets, bytes, drains and waits since the last call
|
|
// NX2NAVI_REC_CHECK=1 (debug, recorder on): vk_memory.c reports each object it defers (destroy 0, stamped tl) or destroys
|
|
// (destroy 1) with the value the GPU reached (gpu); a packet of the part being recorded that still names it is logged
|
|
// as a hazard when the object can go before the part ran. rec_check_log: the counts by kind and packet, at exit.
|
|
enum { REC_IMAGE, REC_VIEW, REC_BUFFER, REC_KINDS };
|
|
void rec_check_handle(int kind, uint64_t handle, int destroy, uint64_t tl, uint64_t gpu);
|
|
void rec_check_log(void);
|
|
|
|
// Extension commands called through device function pointers.
|
|
void rec_push_tpl(PFN_vkCmdPushDescriptorSetWithTemplateKHR fn, VkCommandBuffer cb, VkDescriptorUpdateTemplate tpl,
|
|
VkPipelineLayout layout, uint32_t set, const void *data, uint32_t bytes); // data: bytes read by tpl
|
|
void rec_push(PFN_vkCmdPushDescriptorSetKHR fn, VkCommandBuffer cb, VkPipelineBindPoint bp, VkPipelineLayout layout,
|
|
uint32_t set, uint32_t n, const VkWriteDescriptorSet *w);
|
|
void rec_vertex_input(PFN_vkCmdSetVertexInputEXT fn, VkCommandBuffer cb, uint32_t nb,
|
|
const VkVertexInputBindingDescription2EXT *b, uint32_t na,
|
|
const VkVertexInputAttributeDescription2EXT *a);
|
|
void rec_bool(PFN_vkCmdSetDepthClampEnableEXT fn, VkCommandBuffer cb, VkBool32 v); // also alpha to coverage
|
|
void rec_polygon_mode(PFN_vkCmdSetPolygonModeEXT fn, VkCommandBuffer cb, VkPolygonMode m);
|
|
void rec_blend_enable(PFN_vkCmdSetColorBlendEnableEXT fn, VkCommandBuffer cb, uint32_t first, uint32_t n, const VkBool32 *v);
|
|
void rec_blend_equation(PFN_vkCmdSetColorBlendEquationEXT fn, VkCommandBuffer cb, uint32_t first, uint32_t n,
|
|
const VkColorBlendEquationEXT *v);
|
|
void rec_write_mask(PFN_vkCmdSetColorWriteMaskEXT fn, VkCommandBuffer cb, uint32_t first, uint32_t n,
|
|
const VkColorComponentFlags *v);
|
|
void rec_draw_mesh(PFN_vkCmdDrawMeshTasksEXT fn, VkCommandBuffer cb, uint32_t x, uint32_t y, uint32_t z);
|
|
void rec_shading_rate(PFN_vkCmdSetFragmentShadingRateKHR fn, VkCommandBuffer cb, uint32_t size); // size x size pixels per fragment
|
|
void rec_draw_mesh_ind(PFN_vkCmdDrawMeshTasksIndirectEXT fn, VkCommandBuffer cb, VkBuffer b, VkDeviceSize o, uint32_t n,
|
|
uint32_t stride);
|
|
// A pass mark (vk_crumbs.c vk_pass_mark_cmd: a buffer marker and a checkpoint), in order with the commands around it.
|
|
void rec_pass_mark(VkCommandBuffer cb, uint32_t id, int end);
|
|
|
|
#define REC_CMDS(X) \
|
|
X(BeginQuery, (VkCommandBuffer cb, VkQueryPool p, uint32_t q, VkQueryControlFlags f), (cb, p, q, f)) \
|
|
X(BeginRendering, (VkCommandBuffer cb, const VkRenderingInfo *ri), (cb, ri)) \
|
|
X(BindDescriptorSets, (VkCommandBuffer cb, VkPipelineBindPoint bp, VkPipelineLayout l, uint32_t first, uint32_t n, \
|
|
const VkDescriptorSet *s, uint32_t nd, const uint32_t *d), (cb, bp, l, first, n, s, nd, d)) \
|
|
X(BindIndexBuffer, (VkCommandBuffer cb, VkBuffer b, VkDeviceSize o, VkIndexType t), (cb, b, o, t)) \
|
|
X(BindPipeline, (VkCommandBuffer cb, VkPipelineBindPoint bp, VkPipeline p), (cb, bp, p)) \
|
|
X(BindVertexBuffers2, (VkCommandBuffer cb, uint32_t first, uint32_t n, const VkBuffer *b, const VkDeviceSize *o, \
|
|
const VkDeviceSize *sz, const VkDeviceSize *st), (cb, first, n, b, o, sz, st)) \
|
|
X(BlitImage, (VkCommandBuffer cb, VkImage s, VkImageLayout sl, VkImage d, VkImageLayout dl, uint32_t n, \
|
|
const VkImageBlit *r, VkFilter f), (cb, s, sl, d, dl, n, r, f)) \
|
|
X(ClearAttachments, (VkCommandBuffer cb, uint32_t na, const VkClearAttachment *a, uint32_t nr, const VkClearRect *r), \
|
|
(cb, na, a, nr, r)) \
|
|
X(ClearColorImage, (VkCommandBuffer cb, VkImage i, VkImageLayout l, const VkClearColorValue *c, uint32_t n, \
|
|
const VkImageSubresourceRange *r), (cb, i, l, c, n, r)) \
|
|
X(ClearDepthStencilImage, (VkCommandBuffer cb, VkImage i, VkImageLayout l, const VkClearDepthStencilValue *c, \
|
|
uint32_t n, const VkImageSubresourceRange *r), (cb, i, l, c, n, r)) \
|
|
X(CopyBuffer, (VkCommandBuffer cb, VkBuffer s, VkBuffer d, uint32_t n, const VkBufferCopy *r), (cb, s, d, n, r)) \
|
|
X(CopyBufferToImage, (VkCommandBuffer cb, VkBuffer s, VkImage d, VkImageLayout dl, uint32_t n, \
|
|
const VkBufferImageCopy *r), (cb, s, d, dl, n, r)) \
|
|
X(CopyImage, (VkCommandBuffer cb, VkImage s, VkImageLayout sl, VkImage d, VkImageLayout dl, uint32_t n, \
|
|
const VkImageCopy *r), (cb, s, sl, d, dl, n, r)) \
|
|
X(CopyImageToBuffer, (VkCommandBuffer cb, VkImage s, VkImageLayout sl, VkBuffer d, uint32_t n, \
|
|
const VkBufferImageCopy *r), (cb, s, sl, d, n, r)) \
|
|
X(Dispatch, (VkCommandBuffer cb, uint32_t x, uint32_t y, uint32_t z), (cb, x, y, z)) \
|
|
X(DispatchIndirect, (VkCommandBuffer cb, VkBuffer b, VkDeviceSize o), (cb, b, o)) \
|
|
X(Draw, (VkCommandBuffer cb, uint32_t n, uint32_t i, uint32_t f, uint32_t fi), (cb, n, i, f, fi)) \
|
|
X(DrawIndexed, (VkCommandBuffer cb, uint32_t n, uint32_t i, uint32_t f, int32_t v, uint32_t fi), (cb, n, i, f, v, fi)) \
|
|
X(DrawIndexedIndirect, (VkCommandBuffer cb, VkBuffer b, VkDeviceSize o, uint32_t n, uint32_t s), (cb, b, o, n, s)) \
|
|
X(DrawIndirect, (VkCommandBuffer cb, VkBuffer b, VkDeviceSize o, uint32_t n, uint32_t s), (cb, b, o, n, s)) \
|
|
X(EndQuery, (VkCommandBuffer cb, VkQueryPool p, uint32_t q), (cb, p, q)) \
|
|
X(EndRendering, (VkCommandBuffer cb), (cb)) \
|
|
X(FillBuffer, (VkCommandBuffer cb, VkBuffer b, VkDeviceSize o, VkDeviceSize n, uint32_t v), (cb, b, o, n, v)) \
|
|
X(PipelineBarrier2, (VkCommandBuffer cb, const VkDependencyInfo *di), (cb, di)) \
|
|
X(ExecuteCommands, (VkCommandBuffer cb, uint32_t n, const VkCommandBuffer *c), (cb, n, c)) \
|
|
X(PushConstants, (VkCommandBuffer cb, VkPipelineLayout l, VkShaderStageFlags st, uint32_t o, uint32_t n, \
|
|
const void *v), (cb, l, st, o, n, v)) \
|
|
X(ResetQueryPool, (VkCommandBuffer cb, VkQueryPool p, uint32_t f, uint32_t n), (cb, p, f, n)) \
|
|
X(ResolveImage, (VkCommandBuffer cb, VkImage s, VkImageLayout sl, VkImage d, VkImageLayout dl, uint32_t n, \
|
|
const VkImageResolve *r), (cb, s, sl, d, dl, n, r)) \
|
|
X(SetBlendConstants, (VkCommandBuffer cb, const float c[4]), (cb, c)) \
|
|
X(SetCullMode, (VkCommandBuffer cb, VkCullModeFlags m), (cb, m)) \
|
|
X(SetDepthBias, (VkCommandBuffer cb, float c, float cl, float s), (cb, c, cl, s)) \
|
|
X(SetDepthBiasEnable, (VkCommandBuffer cb, VkBool32 v), (cb, v)) \
|
|
X(SetDepthCompareOp, (VkCommandBuffer cb, VkCompareOp v), (cb, v)) \
|
|
X(SetDepthTestEnable, (VkCommandBuffer cb, VkBool32 v), (cb, v)) \
|
|
X(SetDepthWriteEnable, (VkCommandBuffer cb, VkBool32 v), (cb, v)) \
|
|
X(SetFrontFace, (VkCommandBuffer cb, VkFrontFace v), (cb, v)) \
|
|
X(SetPrimitiveRestartEnable, (VkCommandBuffer cb, VkBool32 v), (cb, v)) \
|
|
X(SetPrimitiveTopology, (VkCommandBuffer cb, VkPrimitiveTopology v), (cb, v)) \
|
|
X(SetRasterizerDiscardEnable, (VkCommandBuffer cb, VkBool32 v), (cb, v)) \
|
|
X(SetScissorWithCount, (VkCommandBuffer cb, uint32_t n, const VkRect2D *r), (cb, n, r)) \
|
|
X(SetStencilCompareMask, (VkCommandBuffer cb, VkStencilFaceFlags f, uint32_t v), (cb, f, v)) \
|
|
X(SetStencilOp, (VkCommandBuffer cb, VkStencilFaceFlags f, VkStencilOp a, VkStencilOp b, VkStencilOp c, \
|
|
VkCompareOp d), (cb, f, a, b, c, d)) \
|
|
X(SetStencilReference, (VkCommandBuffer cb, VkStencilFaceFlags f, uint32_t v), (cb, f, v)) \
|
|
X(SetStencilTestEnable, (VkCommandBuffer cb, VkBool32 v), (cb, v)) \
|
|
X(SetStencilWriteMask, (VkCommandBuffer cb, VkStencilFaceFlags f, uint32_t v), (cb, f, v)) \
|
|
X(SetViewportWithCount, (VkCommandBuffer cb, uint32_t n, const VkViewport *v), (cb, n, v)) \
|
|
X(WriteTimestamp, (VkCommandBuffer cb, VkPipelineStageFlagBits s, VkQueryPool p, uint32_t q), (cb, s, p, q)) \
|
|
X(WriteTimestamp2, (VkCommandBuffer cb, VkPipelineStageFlags2 s, VkQueryPool p, uint32_t q), (cb, s, p, q))
|
|
|
|
#define REC_DECL(name, params, args) void rc_vkCmd##name params;
|
|
REC_CMDS(REC_DECL)
|
|
#undef REC_DECL
|
|
|
|
#ifndef VK_REC_IMPL
|
|
#define vkCmdBeginQuery rc_vkCmdBeginQuery
|
|
#define vkCmdBeginRendering rc_vkCmdBeginRendering
|
|
#define vkCmdBindDescriptorSets rc_vkCmdBindDescriptorSets
|
|
#define vkCmdBindIndexBuffer rc_vkCmdBindIndexBuffer
|
|
#define vkCmdBindPipeline rc_vkCmdBindPipeline
|
|
#define vkCmdBindVertexBuffers2 rc_vkCmdBindVertexBuffers2
|
|
#define vkCmdBlitImage rc_vkCmdBlitImage
|
|
#define vkCmdExecuteCommands rc_vkCmdExecuteCommands
|
|
#define vkCmdClearAttachments rc_vkCmdClearAttachments
|
|
#define vkCmdClearColorImage rc_vkCmdClearColorImage
|
|
#define vkCmdClearDepthStencilImage rc_vkCmdClearDepthStencilImage
|
|
#define vkCmdCopyBuffer rc_vkCmdCopyBuffer
|
|
#define vkCmdCopyBufferToImage rc_vkCmdCopyBufferToImage
|
|
#define vkCmdCopyImage rc_vkCmdCopyImage
|
|
#define vkCmdCopyImageToBuffer rc_vkCmdCopyImageToBuffer
|
|
#define vkCmdDispatch rc_vkCmdDispatch
|
|
#define vkCmdDispatchIndirect rc_vkCmdDispatchIndirect
|
|
#define vkCmdDraw rc_vkCmdDraw
|
|
#define vkCmdDrawIndexed rc_vkCmdDrawIndexed
|
|
#define vkCmdDrawIndexedIndirect rc_vkCmdDrawIndexedIndirect
|
|
#define vkCmdDrawIndirect rc_vkCmdDrawIndirect
|
|
#define vkCmdEndQuery rc_vkCmdEndQuery
|
|
#define vkCmdEndRendering rc_vkCmdEndRendering
|
|
#define vkCmdFillBuffer rc_vkCmdFillBuffer
|
|
#define vkCmdPipelineBarrier2 rc_vkCmdPipelineBarrier2
|
|
#define vkCmdPushConstants rc_vkCmdPushConstants
|
|
#define vkCmdResetQueryPool rc_vkCmdResetQueryPool
|
|
#define vkCmdResolveImage rc_vkCmdResolveImage
|
|
#define vkCmdSetBlendConstants rc_vkCmdSetBlendConstants
|
|
#define vkCmdSetCullMode rc_vkCmdSetCullMode
|
|
#define vkCmdSetDepthBias rc_vkCmdSetDepthBias
|
|
#define vkCmdSetDepthBiasEnable rc_vkCmdSetDepthBiasEnable
|
|
#define vkCmdSetDepthCompareOp rc_vkCmdSetDepthCompareOp
|
|
#define vkCmdSetDepthTestEnable rc_vkCmdSetDepthTestEnable
|
|
#define vkCmdSetDepthWriteEnable rc_vkCmdSetDepthWriteEnable
|
|
#define vkCmdSetFrontFace rc_vkCmdSetFrontFace
|
|
#define vkCmdSetPrimitiveRestartEnable rc_vkCmdSetPrimitiveRestartEnable
|
|
#define vkCmdSetPrimitiveTopology rc_vkCmdSetPrimitiveTopology
|
|
#define vkCmdSetRasterizerDiscardEnable rc_vkCmdSetRasterizerDiscardEnable
|
|
#define vkCmdSetScissorWithCount rc_vkCmdSetScissorWithCount
|
|
#define vkCmdSetStencilCompareMask rc_vkCmdSetStencilCompareMask
|
|
#define vkCmdSetStencilOp rc_vkCmdSetStencilOp
|
|
#define vkCmdSetStencilReference rc_vkCmdSetStencilReference
|
|
#define vkCmdSetStencilTestEnable rc_vkCmdSetStencilTestEnable
|
|
#define vkCmdSetStencilWriteMask rc_vkCmdSetStencilWriteMask
|
|
#define vkCmdSetViewportWithCount rc_vkCmdSetViewportWithCount
|
|
#define vkCmdWriteTimestamp rc_vkCmdWriteTimestamp
|
|
#define vkCmdWriteTimestamp2 rc_vkCmdWriteTimestamp2
|
|
#endif
|