summaryrefslogtreecommitdiffstats
path: root/tools/gfx/render-graphics-common.cpp
diff options
context:
space:
mode:
authorTim Foley <tfoleyNV@users.noreply.github.com>2021-03-12 11:58:14 -0800
committerGitHub <noreply@github.com>2021-03-12 11:58:14 -0800
commitd6a37a0f151e390808f196998c48a341bc4c7b60 (patch)
treec1c6e3af434cb3627af67ecc8706124e4b8c7fb1 /tools/gfx/render-graphics-common.cpp
parent9ffe2f3ef245034a2dae42017a9059dfe4d02647 (diff)
Add a CPU renderer implementation (#1750)
* Add a CPU renderer implementation This change adds a CPU back-end to `gfx` and ensures that most of our existing CPU tests pass when using it. Detailed notes: * Most of the CPU renderer implementation is copy-pasted from the CUDA case, so they share a lot of similar logic * The main addition to the CPU renderer is a semi-complete implementation of host-memory textures. The logic here handles all the main shapes (Buffer, 1D, 2D, 3D, Cube) and all the currently-supported `Format`s that are sample-able as-is (no D24S8). The implementation is not intended to be fast, and it currently only does nearest-neighbor sampling, but otherwise it tries to avoid cutting too many corners and should be ar reasonable starting point for a more complete (but not performance-oriented) implementation. * Refactored the CPU prelude `IRWTexture` interface to inherit from `ITexture`, since in most cases a single type will end up implementing both. It might be worth it to collapse it all down to a single interface later. * Changed the CPU prelude `ITexture`/`IRWTexture` interface so that it takes both a pointer *and* a size for output arguments. This change seems necessary to allow a shader variable declared as a `Texture2D<float>` to fetch a single `float` when the underlying texture might be using RGBA32F. * Added to the `IComponentType` public API so that we can query a "host callable" for an entry point and not just a binary. * Turned off the `-shaderobj` flag on two tests that weren't yet compatible with shader objects but still had the flag left in on the path (since previously the CPU path always used the non-`gfx` non-shader-object logic anyway) * Disabled one test (`dynamic-dispatch-11`) that relied on the `ConstantBuffer<IInterface>` idiom that we know we are planning to chagne soon anyway. * Made a few changes to the CUDA path to bring it into line with what I added for the CPU path. These were mostly bug fixes around indexing logic for sub-objects and resources. * fixup
Diffstat (limited to 'tools/gfx/render-graphics-common.cpp')
-rw-r--r--tools/gfx/render-graphics-common.cpp31
1 files changed, 4 insertions, 27 deletions
diff --git a/tools/gfx/render-graphics-common.cpp b/tools/gfx/render-graphics-common.cpp
index 10713e92b..5ae148ea0 100644
--- a/tools/gfx/render-graphics-common.cpp
+++ b/tools/gfx/render-graphics-common.cpp
@@ -109,29 +109,6 @@ public:
}
}
- slang::TypeLayoutReflection* unwrapParameterGroups(slang::TypeLayoutReflection* typeLayout)
- {
- for (;;)
- {
- if (!typeLayout->getType())
- {
- if (auto elementTypeLayout = typeLayout->getElementTypeLayout())
- typeLayout = elementTypeLayout;
- }
-
- switch (typeLayout->getKind())
- {
- default:
- return typeLayout;
-
- case slang::TypeReflection::Kind::ConstantBuffer:
- case slang::TypeReflection::Kind::ParameterBlock:
- typeLayout = typeLayout->getElementTypeLayout();
- continue;
- }
- }
- }
-
void _addDescriptorSets(
slang::TypeLayoutReflection* typeLayout,
slang::VariableLayoutReflection* varLayout = nullptr)
@@ -178,7 +155,7 @@ public:
Result setElementTypeLayout(slang::TypeLayoutReflection* typeLayout)
{
- typeLayout = unwrapParameterGroups(typeLayout);
+ typeLayout = _unwrapParameterGroups(typeLayout);
m_elementTypeLayout = typeLayout;
@@ -414,8 +391,8 @@ public:
struct Builder : Super::Builder
{
- Builder(IDevice* renderer)
- : Super::Builder(static_cast<RendererBase*>(renderer))
+ Builder(IDevice* device)
+ : Super::Builder(static_cast<RendererBase*>(device))
{}
Result build(EntryPointLayout** outLayout)
@@ -1249,7 +1226,7 @@ protected:
return SLANG_OK;
// Once we have computed how large the buffer should be, we can allocate
- // it using the existing public `IRenderer` API.
+ // it using the existing public `IDevice` API.
//
IDevice* device = getRenderer();
IBufferResource::Desc bufferDesc;