From 47392bc72b826b4ad427b703391a77e697735a65 Mon Sep 17 00:00:00 2001
From: jsmall-nvidia <jsmall@nvidia.com>
Date: Tue, 21 Jan 2020 09:38:10 -0500
Subject: CUDA support improvements (#1168)

* Add test result for compile-to-cuda

* Add RAII for some CUDA types to simplify usage.

* First pass handling of some instrinsics on CUDA (for example transcendentals)

* CUDA working with built in intrinsics.

* Add missing CUDA prelude intrinsics.

* CUDA matches CPU output on simple-cross-compile.slang

* First pass at hlsl-scalar-float-intrinsic.slang test.

* Fix smoothstep impl on CUDA and CPU.

* Fixed step intrinsic on CUDA/CPU.

* Added operator[] to Matrix for C++, to allow row access.
Needs a fix for CUDA.

* Fixed warning on clang build.
---
 prelude/slang-cpp-types.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'prelude/slang-cpp-types.h')

diff --git a/prelude/slang-cpp-types.h b/prelude/slang-cpp-types.h
index 67db607f6..a7ecf5991 100644
--- a/prelude/slang-cpp-types.h
+++ b/prelude/slang-cpp-types.h
@@ -82,6 +82,9 @@ typedef Vector<uint32_t, 4> uint4;
 template <typename T, int ROWS, int COLS>
 struct Matrix
 {
+    Vector<T, COLS>& operator[](int i) { SLANG_PRELUDE_ASSERT(i >= 0 && i < ROWS); return rows[i]; }
+    const Vector<T, COLS>& operator[](int i) const { SLANG_PRELUDE_ASSERT(i >= 0 && i < ROWS); return rows[i]; }
+    
     Vector<T, COLS> rows[ROWS];
 };
 
-- 
cgit v1.2.3