NVAPI improvements (#1512)

* First pass at incorporating nvapi into test harness.

* D3d12 Atomic Float Add via NVAPI working

* Dx12 atomic float appears to work.

* Atomic float add on Dx12.

* Added atomic64 feature addition to vk.
Fix correct output for atomic-float-byte-address.slang

* Disable atomic float failing tests.

* Upgraded VK headers.

* Detect atomic float availability on VK.

* Try to get test working for in64 atomic.

* Made HLSL prelude controlled via the render-test requirements.

* Added -enable-nvapi to premake.

* Fix D3D12Renderer when NVAPI is not available.

* Small improvements to VKRenderer.

* Improve atomic documentation in target-compatibility.md.

* Fixed NVAPI working on D3D12.

* Test for specific NVAPI features.

* Remove requiredFeatures from Renderer::Desc as was ignored. Tried to document more around nvapiExtnSlot.

* Readded requiredFeatures to Renderer::Desc

* Improve comments in the tests.

1 files changed, 32 insertions, 16 deletions

diff --git a/tools/gfx/d3d11/render-d3d11.cpp b/tools/gfx/d3d11/render-d3d11.cpp
index 8eafd24b4..30c982ab3 100644
--- a/tools/gfx/d3d11/render-d3d11.cpp
+++ b/tools/gfx/d3d11/render-d3d11.cpp
@@ -514,6 +514,19 @@ D3D11Renderer::ScopeNVAPI::~ScopeNVAPI()
 
 // !!!!!!!!!!!!!!!!!!!!!!!!!!!! Renderer interface !!!!!!!!!!!!!!!!!!!!!!!!!!
 
+static bool _isSupportedNVAPIOp(IUnknown* dev, uint32_t op)
+{
+#ifdef GFX_NVAPI
+    {
+        bool isSupported;
+        NvAPI_Status status = NvAPI_D3D11_IsNvShaderExtnOpCodeSupported(dev, NvU32(op), &isSupported);
+        return status == NVAPI_OK && isSupported;
+    }
+#else
+    return false;
+#endif
+}
+
 SlangResult D3D11Renderer::initialize(const Desc& desc, void* inWindowHandle)
 {
     auto windowHandle = (HWND)inWindowHandle;
@@ -647,29 +660,32 @@ SlangResult D3D11Renderer::initialize(const Desc& desc, void* inWindowHandle)
     }
 
     // NVAPI
+    if (desc.nvapiExtnSlot >= 0)
     {
-        const char* features[] = { "nvapi", "atomic-float", "atomic-int64" };
-        bool needsNvapi = false;
-        for (Index i = 0; i < SLANG_COUNT_OF(features); ++i)
+        if (SLANG_FAILED(NVAPIUtil::initialize()))
         {
-            if (desc.requiredFeatures.indexOf(features[i]) >= 0)
-            {
-                needsNvapi = true;
-                break;
-            }
+            return SLANG_E_NOT_AVAILABLE;
         }
 
-        if (needsNvapi && SLANG_SUCCEEDED(NVAPIUtil::initialize()))
+#ifdef GFX_NVAPI
+        if (NvAPI_D3D11_SetNvShaderExtnSlot(m_device, NvU32(desc.nvapiExtnSlot)) != NVAPI_OK)
         {
-            // TODO(JS): We should test for specific features here.
-            for (Index i = 0; i < SLANG_COUNT_OF(features); ++i)
-            {
-                m_features.add(features[i]);
-            }
-            m_nvapi = true;
+            return SLANG_E_NOT_AVAILABLE;
         }
-    }
 
+        if (_isSupportedNVAPIOp(m_device, NV_EXTN_OP_UINT64_ATOMIC ))
+        {
+            m_features.add("atomic-int64");
+        }
+        if (_isSupportedNVAPIOp(m_device, NV_EXTN_OP_FP32_ATOMIC))
+        {
+            m_features.add("atomic-float");
+        }
+
+        m_nvapi = true;
+#endif
+    }
+    
     // TODO: Add support for debugging to help detect leaks:
     //
     //      ComPtr<ID3D11Debug> gDebug;