D3D12 atrocious performance

Mike Farrell · 2015-08-15T06:30:28

I'm getting about 10 FPS with only about 20 draw calls of very small meshes. Clearly I'm doing something very very wrong. Is there an issue with populating a single command list to draw 20 items? I figured even if that isn't optimal, it shouldn't be THIS terrible. At this point my iPad running OpenGL ES is outperforming my d3d12 engine by a massive margin. The following code runs before most of my draw calls to set up necessary state: Sorry for the messed up tab spacings void CoreStateMachine::prepareToDraw() { auto cl = continueRenderingCommands(); cl->SetGraphicsRootSignature(rootSignature.Get()); //prepare any buffers required by current shader program auto prog = currentProgram; if(prog) { if(!prog->globalCBuffer) { prog->globalCBuffer = make_shared<BufferArray>(); prog->globalCBufferDirty = true; } else { //this should be cleaned up at some point preserveResourceUntilRenderComplete(prog->globalCBuffer->uploadBuffers[0]); preserveResourceUntilRenderComplete(prog->globalCBuffer->buffers[0]); prog->globalCBuffer = make_shared<BufferArray>(); prog->globalCBufferDirty = true; } if(prog->globalCBufferDirty) { prog->globalCBuffer->provideData(0, prog->globalCBufferSize, prog->globalCBufferData, BufferArray::UT_DYNAMIC); prog->globalCBufferDirty = false; } cl->SetGraphicsRootConstantBufferView(2, prog->globalCBuffer->buffers[0]->GetGPUVirtualAddress()); } auto currentVA = VertexArray::current(); assert(currentVA != nullptr); currentVA->prepareForDraw(); device->CopyDescriptorsSimple(textureTableSize, cbSrvHeaps[descriptorHeapIndex]->hCPU(textureTableIndex), cpuCbSrvHeap->hCPU(0), D3D12_DESCRIPTOR_HEAP_TYPE_CBV_SRV_UAV); device->CopyDescriptorsSimple(textureTableSize, samplerHeaps[descriptorHeapIndex]->hCPU(textureTableIndex), cpuSamplerHeap->hCPU(0), D3D12_DESCRIPTOR_HEAP_TYPE_SAMPLER); if(descriptorHeapsChanged) { ID3D12DescriptorHeap *descHeaps[] = { cbSrvHeaps[descriptorHeapIndex]->get(), samplerHeaps[descriptorHeapIndex]->get() }; cl->SetDescriptorHeaps(ARRAYSIZE(descHeaps), descHeaps); descriptorHeapsChanged = false; } //might be smarter to set this up earlier if I can.. not sure what the tradeoff is here if(pipelineState) { preserveResourceUntilRenderComplete(pipelineState); pipelineState = nullptr; } ThrowIfFailed(device->CreateGraphicsPipelineState(&psoDesc, IID_PPV_ARGS(&pipelineState))); cl->SetPipelineState(pipelineState.Get()); if(descriptorTablesChanged) { cl->SetGraphicsRootDescriptorTable(0, cbSrvHeaps[descriptorHeapIndex]->hGPU(textureTableIndex)); cl->SetGraphicsRootDescriptorTable(1, samplerHeaps[descriptorHeapIndex]->hGPU(textureTableIndex)); descriptorTablesChanged = false; } }

Graphics and GPU Programming Programming OpenGL

Started by mlfarrell00 August 13, 2015 09:59 PM

20 comments, last by mlfarrell00 8 years, 8 months ago

SeanMiddleditch

17,596

August 15, 2015 03:58 AM

omfg. here's another tip. DON'T test performance with debug builds. I forgot about how bad the performance of MSVC generated debug builds are. Doing a release build shot the performance of the whole system up to max FPS

So make your debug builds faster. Turn off iterator debugging (/D_HAS_ITERATOR_DEBUGGING=0), turn off Security Development Lifecycle and Buffer Checks (/GS- and /sdl-), turn on inlining of small explicitly inlined functions like the typical C++ getter method (/Ob1), and disable the debug heap (environment variable _NO_DEBUG_HEAP=1).

You can make fairly debuggable builds that rival performance of fully optimized release builds (for small to mid-size codebases).

Sean Middleditch – Game Systems Engineer – Join my team!

mlfarrell00

137

Author

August 15, 2015 06:30 AM

wow.. so get this.. I've been doing this work on a mac rebooted into windows 10 via bootcamp (not a VM, actually running in windows on mac hardware). The same exact OpenGL demo when rebooted into OSX gets 20- 23 frames per second. Confirms what everyone already knows. Apple gives zero fucks about optimizing their OpenGL drivers. I knew nvidia had an edge on apples drivers but this is ridiculous. One of the reasons I scouted ahead to learn D3D12 was to get an edge on the concepts that will likely be available when vulkan releases, but with apple touting their vender-lockin metal API, its a wonder if we'll ever see vulkan on OSX at all. Food for thought I guess. Either way, if metal becomes the ONLY way to get performant 3D on OSX, I'll be abandoning it in favor of windows in a heatbeat.

D3D12 atrocious performance

This topic is closed to new replies.

Popular Topics

Recommended Tutorials

D3D12 atrocious performance

This topic is closed to new replies.

Popular Topics

Recommended Tutorials

Reticulating splines