graphics: hoist loop-invariant checks out of draw/attrib hot paths (#807)

* graphics: hoist loop-invariant checks out of draw/attrib hot paths

DrawIndirectMulti recomputed the index_type_and_size switch on every
sub-draw of a multi-draw-indirect call, and ShaderApplyAttribSemantics
re-checked the debug-dump config flag on every vertex attribute. Both
values are invariant across their respective loops, so compute them
once before iterating instead.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

* graphics: cache vertex buffer descriptor size in AcquireVertexBuffers

VertexBufferDescriptorSize was computed twice per vertex-buffer slot
on every draw call: once while collecting guest ranges, and again
while rebuilding slot bindings. Both calls use identical inputs, so
cache the first pass's result and reuse it in the second.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>

src/graphics/guest_gpu/graphicsRun.cpp

@@ -976,6 +976,16 @@ void CommandProcessor::DrawIndirectMulti(uint32_t data_offset, uint32_t max_coun
 	const auto args_size = indexed ? sizeof(DrawIndexedIndirectArgs) : sizeof(DrawIndirectArgs);
 	EXIT_NOT_IMPLEMENTED(stride_in_bytes < args_size);
 
+	uint64_t index_size = 0;
+	if (indexed) {
+		switch (m_index_type_and_size) {
+			case 0: index_size = 2; break;
+			case 1: index_size = 4; break;
+			case 2: index_size = 1; break;
+			default: EXIT("unknown index_type_and_size: %u\n", m_index_type_and_size);
+		}
+	}
+
 	for (uint32_t i = 0; i < draw_count; i++) {
 		const auto args_addr = m_draw_indirect_args_base_addr + data_offset +
 		                       static_cast<uint64_t>(i) * stride_in_bytes;
@@ -993,14 +1003,6 @@ void CommandProcessor::DrawIndirectMulti(uint32_t data_offset, uint32_t max_coun
 
 		auto* args = reinterpret_cast<const DrawIndexedIndirectArgs*>(args_addr);
 
-		uint64_t index_size = 0;
-		switch (m_index_type_and_size) {
-			case 0: index_size = 2; break;
-			case 1: index_size = 4; break;
-			case 2: index_size = 1; break;
-			default: EXIT("unknown index_type_and_size: %u\n", m_index_type_and_size);
-		}
-
 		auto* index_addr = reinterpret_cast<const void*>(
 		    m_index_base_addr + static_cast<uint64_t>(args->start_index_location) * index_size);
 

src/graphics/host_gpu/renderer/renderDraw.cpp

@@ -686,11 +686,13 @@ static PreparedVertexBuffers AcquireVertexBuffers(CommandBuffer&               b
 	        vs_input_info.buffers_num > ShaderVertexInputInfo::RES_MAX);
 
 	// Collect the non-empty guest vertex ranges.
+	std::array<uint64_t, ShaderVertexInputInfo::RES_MAX>          sizes {};
 	std::array<VertexBufferRange, ShaderVertexInputInfo::RES_MAX> ranges {};
 	uint32_t                                                      range_count = 0;
 	for (int i = 0; i < vs_input_info.buffers_num; i++) {
 		const auto& vertex = vs_input_info.buffers[i];
 		const auto  size   = VertexBufferDescriptorSize(vertex, vs_input_info);
+		sizes[i]           = size;
 		if (size == 0) {
 			continue;
 		}
@@ -739,7 +741,7 @@ static PreparedVertexBuffers AcquireVertexBuffers(CommandBuffer&               b
 	vk::Buffer null_buffer = nullptr;
 	for (int i = 0; i < vs_input_info.buffers_num; i++) {
 		const auto& vertex = vs_input_info.buffers[i];
-		const auto  size   = VertexBufferDescriptorSize(vertex, vs_input_info);
+		const auto  size   = sizes[i];
 		if (size == 0) {
 			if (null_buffer == nullptr) {
 				null_buffer = cache.GetBuffer(NULL_BUFFER_ID).Handle();

src/graphics/shader/shader.cpp

@@ -388,6 +388,8 @@ static void ShaderApplyAttribSemantics(ShaderVertexInputInfo& info,
 
 	EXIT_IF(attrib == nullptr || buffer == nullptr);
 
+	const bool debug_dump = Config::GraphicsDebugDumpEnabled();
+
 	for (uint32_t i = 0; i < num_input_semantics; i++) {
 		const auto& in = input_semantics[i];
 
@@ -396,7 +398,7 @@ static void ShaderApplyAttribSemantics(ShaderVertexInputInfo& info,
 		uint32_t reg  = in.hardware_mapping;
 		uint32_t size = in.size_in_elements;
 
-		if (Config::GraphicsDebugDumpEnabled()) {
+		if (debug_dump) {
 			LOGF("reg = %u, size = %u, va[%u] = 0x%08" PRIx32 "\n", reg, size, i,
 			     attrib[in.semantic]);
 		}