summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorBrett Weiland <brett_weiland@gmail.com>2024-05-08 22:52:46 -0500
committerBrett Weiland <brett_weiland@gmail.com>2024-05-08 22:52:46 -0500
commit882999e591ece292d5ddbc87020ba70b3d2d1658 (patch)
treee09b8ccc68f447a096981355b4330c31b4fcb268
parentae190c620265549ac2d355a94de19c905d54c2a0 (diff)
workspace
-rw-r--r--.gdb_history14
-rwxr-xr-xbruhbin0 -> 17896 bytes
-rw-r--r--first0
-rw-r--r--include/helper_math.h1469
-rw-r--r--main.c23
-rw-r--r--main.cu6
-rw-r--r--makefile11
7 files changed, 1523 insertions, 0 deletions
diff --git a/.gdb_history b/.gdb_history
new file mode 100644
index 0000000..2f823ae
--- /dev/null
+++ b/.gdb_history
@@ -0,0 +1,14 @@
+quit
+break main.c:11
+run
+image
+print image
+print image.data
+print image.data[0]
+print image.data
+x image.data
+x *image.data
+x *=image.data
+print image
+context
+quit
diff --git a/bruh b/bruh
new file mode 100755
index 0000000..e25e187
--- /dev/null
+++ b/bruh
Binary files differ
diff --git a/first b/first
deleted file mode 100644
index e69de29..0000000
--- a/first
+++ /dev/null
diff --git a/include/helper_math.h b/include/helper_math.h
new file mode 100644
index 0000000..6d2f63a
--- /dev/null
+++ b/include/helper_math.h
@@ -0,0 +1,1469 @@
+/* Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of NVIDIA CORPORATION nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+ * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
+ * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/*
+ * This file implements common mathematical operations on vector types
+ * (float3, float4 etc.) since these are not provided as standard by CUDA.
+ *
+ * The syntax is modeled on the Cg standard library.
+ *
+ * This is part of the Helper library includes
+ *
+ * Thanks to Linh Hah for additions and fixes.
+ */
+
+#ifndef HELPER_MATH_H
+#define HELPER_MATH_H
+
+#include "cuda_runtime.h"
+
+typedef unsigned int uint;
+typedef unsigned short ushort;
+
+#ifndef EXIT_WAIVED
+#define EXIT_WAIVED 2
+#endif
+
+#ifndef __CUDACC__
+#include <math.h>
+
+////////////////////////////////////////////////////////////////////////////////
+// host implementations of CUDA functions
+////////////////////////////////////////////////////////////////////////////////
+
+inline float fminf(float a, float b)
+{
+ return a < b ? a : b;
+}
+
+inline float fmaxf(float a, float b)
+{
+ return a > b ? a : b;
+}
+
+inline int max(int a, int b)
+{
+ return a > b ? a : b;
+}
+
+inline int min(int a, int b)
+{
+ return a < b ? a : b;
+}
+
+inline float rsqrtf(float x)
+{
+ return 1.0f / sqrtf(x);
+}
+#endif
+
+////////////////////////////////////////////////////////////////////////////////
+// constructors
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float2 make_float2(float s)
+{
+ return make_float2(s, s);
+}
+inline __host__ __device__ float2 make_float2(float3 a)
+{
+ return make_float2(a.x, a.y);
+}
+inline __host__ __device__ float2 make_float2(int2 a)
+{
+ return make_float2(float(a.x), float(a.y));
+}
+inline __host__ __device__ float2 make_float2(uint2 a)
+{
+ return make_float2(float(a.x), float(a.y));
+}
+
+inline __host__ __device__ int2 make_int2(int s)
+{
+ return make_int2(s, s);
+}
+inline __host__ __device__ int2 make_int2(int3 a)
+{
+ return make_int2(a.x, a.y);
+}
+inline __host__ __device__ int2 make_int2(uint2 a)
+{
+ return make_int2(int(a.x), int(a.y));
+}
+inline __host__ __device__ int2 make_int2(float2 a)
+{
+ return make_int2(int(a.x), int(a.y));
+}
+
+inline __host__ __device__ uint2 make_uint2(uint s)
+{
+ return make_uint2(s, s);
+}
+inline __host__ __device__ uint2 make_uint2(uint3 a)
+{
+ return make_uint2(a.x, a.y);
+}
+inline __host__ __device__ uint2 make_uint2(int2 a)
+{
+ return make_uint2(uint(a.x), uint(a.y));
+}
+
+inline __host__ __device__ float3 make_float3(float s)
+{
+ return make_float3(s, s, s);
+}
+inline __host__ __device__ float3 make_float3(float2 a)
+{
+ return make_float3(a.x, a.y, 0.0f);
+}
+inline __host__ __device__ float3 make_float3(float2 a, float s)
+{
+ return make_float3(a.x, a.y, s);
+}
+inline __host__ __device__ float3 make_float3(float4 a)
+{
+ return make_float3(a.x, a.y, a.z);
+}
+inline __host__ __device__ float3 make_float3(int3 a)
+{
+ return make_float3(float(a.x), float(a.y), float(a.z));
+}
+inline __host__ __device__ float3 make_float3(uint3 a)
+{
+ return make_float3(float(a.x), float(a.y), float(a.z));
+}
+
+inline __host__ __device__ int3 make_int3(int s)
+{
+ return make_int3(s, s, s);
+}
+inline __host__ __device__ int3 make_int3(int2 a)
+{
+ return make_int3(a.x, a.y, 0);
+}
+inline __host__ __device__ int3 make_int3(int2 a, int s)
+{
+ return make_int3(a.x, a.y, s);
+}
+inline __host__ __device__ int3 make_int3(uint3 a)
+{
+ return make_int3(int(a.x), int(a.y), int(a.z));
+}
+inline __host__ __device__ int3 make_int3(float3 a)
+{
+ return make_int3(int(a.x), int(a.y), int(a.z));
+}
+
+inline __host__ __device__ uint3 make_uint3(uint s)
+{
+ return make_uint3(s, s, s);
+}
+inline __host__ __device__ uint3 make_uint3(uint2 a)
+{
+ return make_uint3(a.x, a.y, 0);
+}
+inline __host__ __device__ uint3 make_uint3(uint2 a, uint s)
+{
+ return make_uint3(a.x, a.y, s);
+}
+inline __host__ __device__ uint3 make_uint3(uint4 a)
+{
+ return make_uint3(a.x, a.y, a.z);
+}
+inline __host__ __device__ uint3 make_uint3(int3 a)
+{
+ return make_uint3(uint(a.x), uint(a.y), uint(a.z));
+}
+
+inline __host__ __device__ float4 make_float4(float s)
+{
+ return make_float4(s, s, s, s);
+}
+inline __host__ __device__ float4 make_float4(float3 a)
+{
+ return make_float4(a.x, a.y, a.z, 0.0f);
+}
+inline __host__ __device__ float4 make_float4(float3 a, float w)
+{
+ return make_float4(a.x, a.y, a.z, w);
+}
+inline __host__ __device__ float4 make_float4(int4 a)
+{
+ return make_float4(float(a.x), float(a.y), float(a.z), float(a.w));
+}
+inline __host__ __device__ float4 make_float4(uint4 a)
+{
+ return make_float4(float(a.x), float(a.y), float(a.z), float(a.w));
+}
+
+inline __host__ __device__ int4 make_int4(int s)
+{
+ return make_int4(s, s, s, s);
+}
+inline __host__ __device__ int4 make_int4(int3 a)
+{
+ return make_int4(a.x, a.y, a.z, 0);
+}
+inline __host__ __device__ int4 make_int4(int3 a, int w)
+{
+ return make_int4(a.x, a.y, a.z, w);
+}
+inline __host__ __device__ int4 make_int4(uint4 a)
+{
+ return make_int4(int(a.x), int(a.y), int(a.z), int(a.w));
+}
+inline __host__ __device__ int4 make_int4(float4 a)
+{
+ return make_int4(int(a.x), int(a.y), int(a.z), int(a.w));
+}
+
+
+inline __host__ __device__ uint4 make_uint4(uint s)
+{
+ return make_uint4(s, s, s, s);
+}
+inline __host__ __device__ uint4 make_uint4(uint3 a)
+{
+ return make_uint4(a.x, a.y, a.z, 0);
+}
+inline __host__ __device__ uint4 make_uint4(uint3 a, uint w)
+{
+ return make_uint4(a.x, a.y, a.z, w);
+}
+inline __host__ __device__ uint4 make_uint4(int4 a)
+{
+ return make_uint4(uint(a.x), uint(a.y), uint(a.z), uint(a.w));
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// negate
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float2 operator-(float2 &a)
+{
+ return make_float2(-a.x, -a.y);
+}
+inline __host__ __device__ int2 operator-(int2 &a)
+{
+ return make_int2(-a.x, -a.y);
+}
+inline __host__ __device__ float3 operator-(float3 &a)
+{
+ return make_float3(-a.x, -a.y, -a.z);
+}
+inline __host__ __device__ int3 operator-(int3 &a)
+{
+ return make_int3(-a.x, -a.y, -a.z);
+}
+inline __host__ __device__ float4 operator-(float4 &a)
+{
+ return make_float4(-a.x, -a.y, -a.z, -a.w);
+}
+inline __host__ __device__ int4 operator-(int4 &a)
+{
+ return make_int4(-a.x, -a.y, -a.z, -a.w);
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// addition
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float2 operator+(float2 a, float2 b)
+{
+ return make_float2(a.x + b.x, a.y + b.y);
+}
+inline __host__ __device__ void operator+=(float2 &a, float2 b)
+{
+ a.x += b.x;
+ a.y += b.y;
+}
+inline __host__ __device__ float2 operator+(float2 a, float b)
+{
+ return make_float2(a.x + b, a.y + b);
+}
+inline __host__ __device__ float2 operator+(float b, float2 a)
+{
+ return make_float2(a.x + b, a.y + b);
+}
+inline __host__ __device__ void operator+=(float2 &a, float b)
+{
+ a.x += b;
+ a.y += b;
+}
+
+inline __host__ __device__ int2 operator+(int2 a, int2 b)
+{
+ return make_int2(a.x + b.x, a.y + b.y);
+}
+inline __host__ __device__ void operator+=(int2 &a, int2 b)
+{
+ a.x += b.x;
+ a.y += b.y;
+}
+inline __host__ __device__ int2 operator+(int2 a, int b)
+{
+ return make_int2(a.x + b, a.y + b);
+}
+inline __host__ __device__ int2 operator+(int b, int2 a)
+{
+ return make_int2(a.x + b, a.y + b);
+}
+inline __host__ __device__ void operator+=(int2 &a, int b)
+{
+ a.x += b;
+ a.y += b;
+}
+
+inline __host__ __device__ uint2 operator+(uint2 a, uint2 b)
+{
+ return make_uint2(a.x + b.x, a.y + b.y);
+}
+inline __host__ __device__ void operator+=(uint2 &a, uint2 b)
+{
+ a.x += b.x;
+ a.y += b.y;
+}
+inline __host__ __device__ uint2 operator+(uint2 a, uint b)
+{
+ return make_uint2(a.x + b, a.y + b);
+}
+inline __host__ __device__ uint2 operator+(uint b, uint2 a)
+{
+ return make_uint2(a.x + b, a.y + b);
+}
+inline __host__ __device__ void operator+=(uint2 &a, uint b)
+{
+ a.x += b;
+ a.y += b;
+}
+
+
+inline __host__ __device__ float3 operator+(float3 a, float3 b)
+{
+ return make_float3(a.x + b.x, a.y + b.y, a.z + b.z);
+}
+inline __host__ __device__ void operator+=(float3 &a, float3 b)
+{
+ a.x += b.x;
+ a.y += b.y;
+ a.z += b.z;
+}
+inline __host__ __device__ float3 operator+(float3 a, float b)
+{
+ return make_float3(a.x + b, a.y + b, a.z + b);
+}
+inline __host__ __device__ void operator+=(float3 &a, float b)
+{
+ a.x += b;
+ a.y += b;
+ a.z += b;
+}
+
+inline __host__ __device__ int3 operator+(int3 a, int3 b)
+{
+ return make_int3(a.x + b.x, a.y + b.y, a.z + b.z);
+}
+inline __host__ __device__ void operator+=(int3 &a, int3 b)
+{
+ a.x += b.x;
+ a.y += b.y;
+ a.z += b.z;
+}
+inline __host__ __device__ int3 operator+(int3 a, int b)
+{
+ return make_int3(a.x + b, a.y + b, a.z + b);
+}
+inline __host__ __device__ void operator+=(int3 &a, int b)
+{
+ a.x += b;
+ a.y += b;
+ a.z += b;
+}
+
+inline __host__ __device__ uint3 operator+(uint3 a, uint3 b)
+{
+ return make_uint3(a.x + b.x, a.y + b.y, a.z + b.z);
+}
+inline __host__ __device__ void operator+=(uint3 &a, uint3 b)
+{
+ a.x += b.x;
+ a.y += b.y;
+ a.z += b.z;
+}
+inline __host__ __device__ uint3 operator+(uint3 a, uint b)
+{
+ return make_uint3(a.x + b, a.y + b, a.z + b);
+}
+inline __host__ __device__ void operator+=(uint3 &a, uint b)
+{
+ a.x += b;
+ a.y += b;
+ a.z += b;
+}
+
+inline __host__ __device__ int3 operator+(int b, int3 a)
+{
+ return make_int3(a.x + b, a.y + b, a.z + b);
+}
+inline __host__ __device__ uint3 operator+(uint b, uint3 a)
+{
+ return make_uint3(a.x + b, a.y + b, a.z + b);
+}
+inline __host__ __device__ float3 operator+(float b, float3 a)
+{
+ return make_float3(a.x + b, a.y + b, a.z + b);
+}
+
+inline __host__ __device__ float4 operator+(float4 a, float4 b)
+{
+ return make_float4(a.x + b.x, a.y + b.y, a.z + b.z, a.w + b.w);
+}
+inline __host__ __device__ void operator+=(float4 &a, float4 b)
+{
+ a.x += b.x;
+ a.y += b.y;
+ a.z += b.z;
+ a.w += b.w;
+}
+inline __host__ __device__ float4 operator+(float4 a, float b)
+{
+ return make_float4(a.x + b, a.y + b, a.z + b, a.w + b);
+}
+inline __host__ __device__ float4 operator+(float b, float4 a)
+{
+ return make_float4(a.x + b, a.y + b, a.z + b, a.w + b);
+}
+inline __host__ __device__ void operator+=(float4 &a, float b)
+{
+ a.x += b;
+ a.y += b;
+ a.z += b;
+ a.w += b;
+}
+
+inline __host__ __device__ int4 operator+(int4 a, int4 b)
+{
+ return make_int4(a.x + b.x, a.y + b.y, a.z + b.z, a.w + b.w);
+}
+inline __host__ __device__ void operator+=(int4 &a, int4 b)
+{
+ a.x += b.x;
+ a.y += b.y;
+ a.z += b.z;
+ a.w += b.w;
+}
+inline __host__ __device__ int4 operator+(int4 a, int b)
+{
+ return make_int4(a.x + b, a.y + b, a.z + b, a.w + b);
+}
+inline __host__ __device__ int4 operator+(int b, int4 a)
+{
+ return make_int4(a.x + b, a.y + b, a.z + b, a.w + b);
+}
+inline __host__ __device__ void operator+=(int4 &a, int b)
+{
+ a.x += b;
+ a.y += b;
+ a.z += b;
+ a.w += b;
+}
+
+inline __host__ __device__ uint4 operator+(uint4 a, uint4 b)
+{
+ return make_uint4(a.x + b.x, a.y + b.y, a.z + b.z, a.w + b.w);
+}
+inline __host__ __device__ void operator+=(uint4 &a, uint4 b)
+{
+ a.x += b.x;
+ a.y += b.y;
+ a.z += b.z;
+ a.w += b.w;
+}
+inline __host__ __device__ uint4 operator+(uint4 a, uint b)
+{
+ return make_uint4(a.x + b, a.y + b, a.z + b, a.w + b);
+}
+inline __host__ __device__ uint4 operator+(uint b, uint4 a)
+{
+ return make_uint4(a.x + b, a.y + b, a.z + b, a.w + b);
+}
+inline __host__ __device__ void operator+=(uint4 &a, uint b)
+{
+ a.x += b;
+ a.y += b;
+ a.z += b;
+ a.w += b;
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// subtract
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float2 operator-(float2 a, float2 b)
+{
+ return make_float2(a.x - b.x, a.y - b.y);
+}
+inline __host__ __device__ void operator-=(float2 &a, float2 b)
+{
+ a.x -= b.x;
+ a.y -= b.y;
+}
+inline __host__ __device__ float2 operator-(float2 a, float b)
+{
+ return make_float2(a.x - b, a.y - b);
+}
+inline __host__ __device__ float2 operator-(float b, float2 a)
+{
+ return make_float2(b - a.x, b - a.y);
+}
+inline __host__ __device__ void operator-=(float2 &a, float b)
+{
+ a.x -= b;
+ a.y -= b;
+}
+
+inline __host__ __device__ int2 operator-(int2 a, int2 b)
+{
+ return make_int2(a.x - b.x, a.y - b.y);
+}
+inline __host__ __device__ void operator-=(int2 &a, int2 b)
+{
+ a.x -= b.x;
+ a.y -= b.y;
+}
+inline __host__ __device__ int2 operator-(int2 a, int b)
+{
+ return make_int2(a.x - b, a.y - b);
+}
+inline __host__ __device__ int2 operator-(int b, int2 a)
+{
+ return make_int2(b - a.x, b - a.y);
+}
+inline __host__ __device__ void operator-=(int2 &a, int b)
+{
+ a.x -= b;
+ a.y -= b;
+}
+
+inline __host__ __device__ uint2 operator-(uint2 a, uint2 b)
+{
+ return make_uint2(a.x - b.x, a.y - b.y);
+}
+inline __host__ __device__ void operator-=(uint2 &a, uint2 b)
+{
+ a.x -= b.x;
+ a.y -= b.y;
+}
+inline __host__ __device__ uint2 operator-(uint2 a, uint b)
+{
+ return make_uint2(a.x - b, a.y - b);
+}
+inline __host__ __device__ uint2 operator-(uint b, uint2 a)
+{
+ return make_uint2(b - a.x, b - a.y);
+}
+inline __host__ __device__ void operator-=(uint2 &a, uint b)
+{
+ a.x -= b;
+ a.y -= b;
+}
+
+inline __host__ __device__ float3 operator-(float3 a, float3 b)
+{
+ return make_float3(a.x - b.x, a.y - b.y, a.z - b.z);
+}
+inline __host__ __device__ void operator-=(float3 &a, float3 b)
+{
+ a.x -= b.x;
+ a.y -= b.y;
+ a.z -= b.z;
+}
+inline __host__ __device__ float3 operator-(float3 a, float b)
+{
+ return make_float3(a.x - b, a.y - b, a.z - b);
+}
+inline __host__ __device__ float3 operator-(float b, float3 a)
+{
+ return make_float3(b - a.x, b - a.y, b - a.z);
+}
+inline __host__ __device__ void operator-=(float3 &a, float b)
+{
+ a.x -= b;
+ a.y -= b;
+ a.z -= b;
+}
+
+inline __host__ __device__ int3 operator-(int3 a, int3 b)
+{
+ return make_int3(a.x - b.x, a.y - b.y, a.z - b.z);
+}
+inline __host__ __device__ void operator-=(int3 &a, int3 b)
+{
+ a.x -= b.x;
+ a.y -= b.y;
+ a.z -= b.z;
+}
+inline __host__ __device__ int3 operator-(int3 a, int b)
+{
+ return make_int3(a.x - b, a.y - b, a.z - b);
+}
+inline __host__ __device__ int3 operator-(int b, int3 a)
+{
+ return make_int3(b - a.x, b - a.y, b - a.z);
+}
+inline __host__ __device__ void operator-=(int3 &a, int b)
+{
+ a.x -= b;
+ a.y -= b;
+ a.z -= b;
+}
+
+inline __host__ __device__ uint3 operator-(uint3 a, uint3 b)
+{
+ return make_uint3(a.x - b.x, a.y - b.y, a.z - b.z);
+}
+inline __host__ __device__ void operator-=(uint3 &a, uint3 b)
+{
+ a.x -= b.x;
+ a.y -= b.y;
+ a.z -= b.z;
+}
+inline __host__ __device__ uint3 operator-(uint3 a, uint b)
+{
+ return make_uint3(a.x - b, a.y - b, a.z - b);
+}
+inline __host__ __device__ uint3 operator-(uint b, uint3 a)
+{
+ return make_uint3(b - a.x, b - a.y, b - a.z);
+}
+inline __host__ __device__ void operator-=(uint3 &a, uint b)
+{
+ a.x -= b;
+ a.y -= b;
+ a.z -= b;
+}
+
+inline __host__ __device__ float4 operator-(float4 a, float4 b)
+{
+ return make_float4(a.x - b.x, a.y - b.y, a.z - b.z, a.w - b.w);
+}
+inline __host__ __device__ void operator-=(float4 &a, float4 b)
+{
+ a.x -= b.x;
+ a.y -= b.y;
+ a.z -= b.z;
+ a.w -= b.w;
+}
+inline __host__ __device__ float4 operator-(float4 a, float b)
+{
+ return make_float4(a.x - b, a.y - b, a.z - b, a.w - b);
+}
+inline __host__ __device__ void operator-=(float4 &a, float b)
+{
+ a.x -= b;
+ a.y -= b;
+ a.z -= b;
+ a.w -= b;
+}
+
+inline __host__ __device__ int4 operator-(int4 a, int4 b)
+{
+ return make_int4(a.x - b.x, a.y - b.y, a.z - b.z, a.w - b.w);
+}
+inline __host__ __device__ void operator-=(int4 &a, int4 b)
+{
+ a.x -= b.x;
+ a.y -= b.y;
+ a.z -= b.z;
+ a.w -= b.w;
+}
+inline __host__ __device__ int4 operator-(int4 a, int b)
+{
+ return make_int4(a.x - b, a.y - b, a.z - b, a.w - b);
+}
+inline __host__ __device__ int4 operator-(int b, int4 a)
+{
+ return make_int4(b - a.x, b - a.y, b - a.z, b - a.w);
+}
+inline __host__ __device__ void operator-=(int4 &a, int b)
+{
+ a.x -= b;
+ a.y -= b;
+ a.z -= b;
+ a.w -= b;
+}
+
+inline __host__ __device__ uint4 operator-(uint4 a, uint4 b)
+{
+ return make_uint4(a.x - b.x, a.y - b.y, a.z - b.z, a.w - b.w);
+}
+inline __host__ __device__ void operator-=(uint4 &a, uint4 b)
+{
+ a.x -= b.x;
+ a.y -= b.y;
+ a.z -= b.z;
+ a.w -= b.w;
+}
+inline __host__ __device__ uint4 operator-(uint4 a, uint b)
+{
+ return make_uint4(a.x - b, a.y - b, a.z - b, a.w - b);
+}
+inline __host__ __device__ uint4 operator-(uint b, uint4 a)
+{
+ return make_uint4(b - a.x, b - a.y, b - a.z, b - a.w);
+}
+inline __host__ __device__ void operator-=(uint4 &a, uint b)
+{
+ a.x -= b;
+ a.y -= b;
+ a.z -= b;
+ a.w -= b;
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// multiply
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float2 operator*(float2 a, float2 b)
+{
+ return make_float2(a.x * b.x, a.y * b.y);
+}
+inline __host__ __device__ void operator*=(float2 &a, float2 b)
+{
+ a.x *= b.x;
+ a.y *= b.y;
+}
+inline __host__ __device__ float2 operator*(float2 a, float b)
+{
+ return make_float2(a.x * b, a.y * b);
+}
+inline __host__ __device__ float2 operator*(float b, float2 a)
+{
+ return make_float2(b * a.x, b * a.y);
+}
+inline __host__ __device__ void operator*=(float2 &a, float b)
+{
+ a.x *= b;
+ a.y *= b;
+}
+
+inline __host__ __device__ int2 operator*(int2 a, int2 b)
+{
+ return make_int2(a.x * b.x, a.y * b.y);
+}
+inline __host__ __device__ void operator*=(int2 &a, int2 b)
+{
+ a.x *= b.x;
+ a.y *= b.y;
+}
+inline __host__ __device__ int2 operator*(int2 a, int b)
+{
+ return make_int2(a.x * b, a.y * b);
+}
+inline __host__ __device__ int2 operator*(int b, int2 a)
+{
+ return make_int2(b * a.x, b * a.y);
+}
+inline __host__ __device__ void operator*=(int2 &a, int b)
+{
+ a.x *= b;
+ a.y *= b;
+}
+
+inline __host__ __device__ uint2 operator*(uint2 a, uint2 b)
+{
+ return make_uint2(a.x * b.x, a.y * b.y);
+}
+inline __host__ __device__ void operator*=(uint2 &a, uint2 b)
+{
+ a.x *= b.x;
+ a.y *= b.y;
+}
+inline __host__ __device__ uint2 operator*(uint2 a, uint b)
+{
+ return make_uint2(a.x * b, a.y * b);
+}
+inline __host__ __device__ uint2 operator*(uint b, uint2 a)
+{
+ return make_uint2(b * a.x, b * a.y);
+}
+inline __host__ __device__ void operator*=(uint2 &a, uint b)
+{
+ a.x *= b;
+ a.y *= b;
+}
+
+inline __host__ __device__ float3 operator*(float3 a, float3 b)
+{
+ return make_float3(a.x * b.x, a.y * b.y, a.z * b.z);
+}
+inline __host__ __device__ void operator*=(float3 &a, float3 b)
+{
+ a.x *= b.x;
+ a.y *= b.y;
+ a.z *= b.z;
+}
+inline __host__ __device__ float3 operator*(float3 a, float b)
+{
+ return make_float3(a.x * b, a.y * b, a.z * b);
+}
+inline __host__ __device__ float3 operator*(float b, float3 a)
+{
+ return make_float3(b * a.x, b * a.y, b * a.z);
+}
+inline __host__ __device__ void operator*=(float3 &a, float b)
+{
+ a.x *= b;
+ a.y *= b;
+ a.z *= b;
+}
+
+inline __host__ __device__ int3 operator*(int3 a, int3 b)
+{
+ return make_int3(a.x * b.x, a.y * b.y, a.z * b.z);
+}
+inline __host__ __device__ void operator*=(int3 &a, int3 b)
+{
+ a.x *= b.x;
+ a.y *= b.y;
+ a.z *= b.z;
+}
+inline __host__ __device__ int3 operator*(int3 a, int b)
+{
+ return make_int3(a.x * b, a.y * b, a.z * b);
+}
+inline __host__ __device__ int3 operator*(int b, int3 a)
+{
+ return make_int3(b * a.x, b * a.y, b * a.z);
+}
+inline __host__ __device__ void operator*=(int3 &a, int b)
+{
+ a.x *= b;
+ a.y *= b;
+ a.z *= b;
+}
+
+inline __host__ __device__ uint3 operator*(uint3 a, uint3 b)
+{
+ return make_uint3(a.x * b.x, a.y * b.y, a.z * b.z);
+}
+inline __host__ __device__ void operator*=(uint3 &a, uint3 b)
+{
+ a.x *= b.x;
+ a.y *= b.y;
+ a.z *= b.z;
+}
+inline __host__ __device__ uint3 operator*(uint3 a, uint b)
+{
+ return make_uint3(a.x * b, a.y * b, a.z * b);
+}
+inline __host__ __device__ uint3 operator*(uint b, uint3 a)
+{
+ return make_uint3(b * a.x, b * a.y, b * a.z);
+}
+inline __host__ __device__ void operator*=(uint3 &a, uint b)
+{
+ a.x *= b;
+ a.y *= b;
+ a.z *= b;
+}
+
+inline __host__ __device__ float4 operator*(float4 a, float4 b)
+{
+ return make_float4(a.x * b.x, a.y * b.y, a.z * b.z, a.w * b.w);
+}
+inline __host__ __device__ void operator*=(float4 &a, float4 b)
+{
+ a.x *= b.x;
+ a.y *= b.y;
+ a.z *= b.z;
+ a.w *= b.w;
+}
+inline __host__ __device__ float4 operator*(float4 a, float b)
+{
+ return make_float4(a.x * b, a.y * b, a.z * b, a.w * b);
+}
+inline __host__ __device__ float4 operator*(float b, float4 a)
+{
+ return make_float4(b * a.x, b * a.y, b * a.z, b * a.w);
+}
+inline __host__ __device__ void operator*=(float4 &a, float b)
+{
+ a.x *= b;
+ a.y *= b;
+ a.z *= b;
+ a.w *= b;
+}
+
+inline __host__ __device__ int4 operator*(int4 a, int4 b)
+{
+ return make_int4(a.x * b.x, a.y * b.y, a.z * b.z, a.w * b.w);
+}
+inline __host__ __device__ void operator*=(int4 &a, int4 b)
+{
+ a.x *= b.x;
+ a.y *= b.y;
+ a.z *= b.z;
+ a.w *= b.w;
+}
+inline __host__ __device__ int4 operator*(int4 a, int b)
+{
+ return make_int4(a.x * b, a.y * b, a.z * b, a.w * b);
+}
+inline __host__ __device__ int4 operator*(int b, int4 a)
+{
+ return make_int4(b * a.x, b * a.y, b * a.z, b * a.w);
+}
+inline __host__ __device__ void operator*=(int4 &a, int b)
+{
+ a.x *= b;
+ a.y *= b;
+ a.z *= b;
+ a.w *= b;
+}
+
+inline __host__ __device__ uint4 operator*(uint4 a, uint4 b)
+{
+ return make_uint4(a.x * b.x, a.y * b.y, a.z * b.z, a.w * b.w);
+}
+inline __host__ __device__ void operator*=(uint4 &a, uint4 b)
+{
+ a.x *= b.x;
+ a.y *= b.y;
+ a.z *= b.z;
+ a.w *= b.w;
+}
+inline __host__ __device__ uint4 operator*(uint4 a, uint b)
+{
+ return make_uint4(a.x * b, a.y * b, a.z * b, a.w * b);
+}
+inline __host__ __device__ uint4 operator*(uint b, uint4 a)
+{
+ return make_uint4(b * a.x, b * a.y, b * a.z, b * a.w);
+}
+inline __host__ __device__ void operator*=(uint4 &a, uint b)
+{
+ a.x *= b;
+ a.y *= b;
+ a.z *= b;
+ a.w *= b;
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// divide
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float2 operator/(float2 a, float2 b)
+{
+ return make_float2(a.x / b.x, a.y / b.y);
+}
+inline __host__ __device__ void operator/=(float2 &a, float2 b)
+{
+ a.x /= b.x;
+ a.y /= b.y;
+}
+inline __host__ __device__ float2 operator/(float2 a, float b)
+{
+ return make_float2(a.x / b, a.y / b);
+}
+inline __host__ __device__ void operator/=(float2 &a, float b)
+{
+ a.x /= b;
+ a.y /= b;
+}
+inline __host__ __device__ float2 operator/(float b, float2 a)
+{
+ return make_float2(b / a.x, b / a.y);
+}
+
+inline __host__ __device__ float3 operator/(float3 a, float3 b)
+{
+ return make_float3(a.x / b.x, a.y / b.y, a.z / b.z);
+}
+inline __host__ __device__ void operator/=(float3 &a, float3 b)
+{
+ a.x /= b.x;
+ a.y /= b.y;
+ a.z /= b.z;
+}
+inline __host__ __device__ float3 operator/(float3 a, float b)
+{
+ return make_float3(a.x / b, a.y / b, a.z / b);
+}
+inline __host__ __device__ void operator/=(float3 &a, float b)
+{
+ a.x /= b;
+ a.y /= b;
+ a.z /= b;
+}
+inline __host__ __device__ float3 operator/(float b, float3 a)
+{
+ return make_float3(b / a.x, b / a.y, b / a.z);
+}
+
+inline __host__ __device__ float4 operator/(float4 a, float4 b)
+{
+ return make_float4(a.x / b.x, a.y / b.y, a.z / b.z, a.w / b.w);
+}
+inline __host__ __device__ void operator/=(float4 &a, float4 b)
+{
+ a.x /= b.x;
+ a.y /= b.y;
+ a.z /= b.z;
+ a.w /= b.w;
+}
+inline __host__ __device__ float4 operator/(float4 a, float b)
+{
+ return make_float4(a.x / b, a.y / b, a.z / b, a.w / b);
+}
+inline __host__ __device__ void operator/=(float4 &a, float b)
+{
+ a.x /= b;
+ a.y /= b;
+ a.z /= b;
+ a.w /= b;
+}
+inline __host__ __device__ float4 operator/(float b, float4 a)
+{
+ return make_float4(b / a.x, b / a.y, b / a.z, b / a.w);
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// min
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float2 fminf(float2 a, float2 b)
+{
+ return make_float2(fminf(a.x,b.x), fminf(a.y,b.y));
+}
+inline __host__ __device__ float3 fminf(float3 a, float3 b)
+{
+ return make_float3(fminf(a.x,b.x), fminf(a.y,b.y), fminf(a.z,b.z));
+}
+inline __host__ __device__ float4 fminf(float4 a, float4 b)
+{
+ return make_float4(fminf(a.x,b.x), fminf(a.y,b.y), fminf(a.z,b.z), fminf(a.w,b.w));
+}
+
+inline __host__ __device__ int2 min(int2 a, int2 b)
+{
+ return make_int2(min(a.x,b.x), min(a.y,b.y));
+}
+inline __host__ __device__ int3 min(int3 a, int3 b)
+{
+ return make_int3(min(a.x,b.x), min(a.y,b.y), min(a.z,b.z));
+}
+inline __host__ __device__ int4 min(int4 a, int4 b)
+{
+ return make_int4(min(a.x,b.x), min(a.y,b.y), min(a.z,b.z), min(a.w,b.w));
+}
+
+inline __host__ __device__ uint2 min(uint2 a, uint2 b)
+{
+ return make_uint2(min(a.x,b.x), min(a.y,b.y));
+}
+inline __host__ __device__ uint3 min(uint3 a, uint3 b)
+{
+ return make_uint3(min(a.x,b.x), min(a.y,b.y), min(a.z,b.z));
+}
+inline __host__ __device__ uint4 min(uint4 a, uint4 b)
+{
+ return make_uint4(min(a.x,b.x), min(a.y,b.y), min(a.z,b.z), min(a.w,b.w));
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// max
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float2 fmaxf(float2 a, float2 b)
+{
+ return make_float2(fmaxf(a.x,b.x), fmaxf(a.y,b.y));
+}
+inline __host__ __device__ float3 fmaxf(float3 a, float3 b)
+{
+ return make_float3(fmaxf(a.x,b.x), fmaxf(a.y,b.y), fmaxf(a.z,b.z));
+}
+inline __host__ __device__ float4 fmaxf(float4 a, float4 b)
+{
+ return make_float4(fmaxf(a.x,b.x), fmaxf(a.y,b.y), fmaxf(a.z,b.z), fmaxf(a.w,b.w));
+}
+
+inline __host__ __device__ int2 max(int2 a, int2 b)
+{
+ return make_int2(max(a.x,b.x), max(a.y,b.y));
+}
+inline __host__ __device__ int3 max(int3 a, int3 b)
+{
+ return make_int3(max(a.x,b.x), max(a.y,b.y), max(a.z,b.z));
+}
+inline __host__ __device__ int4 max(int4 a, int4 b)
+{
+ return make_int4(max(a.x,b.x), max(a.y,b.y), max(a.z,b.z), max(a.w,b.w));
+}
+
+inline __host__ __device__ uint2 max(uint2 a, uint2 b)
+{
+ return make_uint2(max(a.x,b.x), max(a.y,b.y));
+}
+inline __host__ __device__ uint3 max(uint3 a, uint3 b)
+{
+ return make_uint3(max(a.x,b.x), max(a.y,b.y), max(a.z,b.z));
+}
+inline __host__ __device__ uint4 max(uint4 a, uint4 b)
+{
+ return make_uint4(max(a.x,b.x), max(a.y,b.y), max(a.z,b.z), max(a.w,b.w));
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// lerp
+// - linear interpolation between a and b, based on value t in [0, 1] range
+////////////////////////////////////////////////////////////////////////////////
+
+inline __device__ __host__ float lerp(float a, float b, float t)
+{
+ return a + t*(b-a);
+}
+inline __device__ __host__ float2 lerp(float2 a, float2 b, float t)
+{
+ return a + t*(b-a);
+}
+inline __device__ __host__ float3 lerp(float3 a, float3 b, float t)
+{
+ return a + t*(b-a);
+}
+inline __device__ __host__ float4 lerp(float4 a, float4 b, float t)
+{
+ return a + t*(b-a);
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// clamp
+// - clamp the value v to be in the range [a, b]
+////////////////////////////////////////////////////////////////////////////////
+
+inline __device__ __host__ float clamp(float f, float a, float b)
+{
+ return fmaxf(a, fminf(f, b));
+}
+inline __device__ __host__ int clamp(int f, int a, int b)
+{
+ return max(a, min(f, b));
+}
+inline __device__ __host__ uint clamp(uint f, uint a, uint b)
+{
+ return max(a, min(f, b));
+}
+
+inline __device__ __host__ float2 clamp(float2 v, float a, float b)
+{
+ return make_float2(clamp(v.x, a, b), clamp(v.y, a, b));
+}
+inline __device__ __host__ float2 clamp(float2 v, float2 a, float2 b)
+{
+ return make_float2(clamp(v.x, a.x, b.x), clamp(v.y, a.y, b.y));
+}
+inline __device__ __host__ float3 clamp(float3 v, float a, float b)
+{
+ return make_float3(clamp(v.x, a, b), clamp(v.y, a, b), clamp(v.z, a, b));
+}
+inline __device__ __host__ float3 clamp(float3 v, float3 a, float3 b)
+{
+ return make_float3(clamp(v.x, a.x, b.x), clamp(v.y, a.y, b.y), clamp(v.z, a.z, b.z));
+}
+inline __device__ __host__ float4 clamp(float4 v, float a, float b)
+{
+ return make_float4(clamp(v.x, a, b), clamp(v.y, a, b), clamp(v.z, a, b), clamp(v.w, a, b));
+}
+inline __device__ __host__ float4 clamp(float4 v, float4 a, float4 b)
+{
+ return make_float4(clamp(v.x, a.x, b.x), clamp(v.y, a.y, b.y), clamp(v.z, a.z, b.z), clamp(v.w, a.w, b.w));
+}
+
+inline __device__ __host__ int2 clamp(int2 v, int a, int b)
+{
+ return make_int2(clamp(v.x, a, b), clamp(v.y, a, b));
+}
+inline __device__ __host__ int2 clamp(int2 v, int2 a, int2 b)
+{
+ return make_int2(clamp(v.x, a.x, b.x), clamp(v.y, a.y, b.y));
+}
+inline __device__ __host__ int3 clamp(int3 v, int a, int b)
+{
+ return make_int3(clamp(v.x, a, b), clamp(v.y, a, b), clamp(v.z, a, b));
+}
+inline __device__ __host__ int3 clamp(int3 v, int3 a, int3 b)
+{
+ return make_int3(clamp(v.x, a.x, b.x), clamp(v.y, a.y, b.y), clamp(v.z, a.z, b.z));
+}
+inline __device__ __host__ int4 clamp(int4 v, int a, int b)
+{
+ return make_int4(clamp(v.x, a, b), clamp(v.y, a, b), clamp(v.z, a, b), clamp(v.w, a, b));
+}
+inline __device__ __host__ int4 clamp(int4 v, int4 a, int4 b)
+{
+ return make_int4(clamp(v.x, a.x, b.x), clamp(v.y, a.y, b.y), clamp(v.z, a.z, b.z), clamp(v.w, a.w, b.w));
+}
+
+inline __device__ __host__ uint2 clamp(uint2 v, uint a, uint b)
+{
+ return make_uint2(clamp(v.x, a, b), clamp(v.y, a, b));
+}
+inline __device__ __host__ uint2 clamp(uint2 v, uint2 a, uint2 b)
+{
+ return make_uint2(clamp(v.x, a.x, b.x), clamp(v.y, a.y, b.y));
+}
+inline __device__ __host__ uint3 clamp(uint3 v, uint a, uint b)
+{
+ return make_uint3(clamp(v.x, a, b), clamp(v.y, a, b), clamp(v.z, a, b));
+}
+inline __device__ __host__ uint3 clamp(uint3 v, uint3 a, uint3 b)
+{
+ return make_uint3(clamp(v.x, a.x, b.x), clamp(v.y, a.y, b.y), clamp(v.z, a.z, b.z));
+}
+inline __device__ __host__ uint4 clamp(uint4 v, uint a, uint b)
+{
+ return make_uint4(clamp(v.x, a, b), clamp(v.y, a, b), clamp(v.z, a, b), clamp(v.w, a, b));
+}
+inline __device__ __host__ uint4 clamp(uint4 v, uint4 a, uint4 b)
+{
+ return make_uint4(clamp(v.x, a.x, b.x), clamp(v.y, a.y, b.y), clamp(v.z, a.z, b.z), clamp(v.w, a.w, b.w));
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// dot product
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float dot(float2 a, float2 b)
+{
+ return a.x * b.x + a.y * b.y;
+}
+inline __host__ __device__ float dot(float3 a, float3 b)
+{
+ return a.x * b.x + a.y * b.y + a.z * b.z;
+}
+inline __host__ __device__ float dot(float4 a, float4 b)
+{
+ return a.x * b.x + a.y * b.y + a.z * b.z + a.w * b.w;
+}
+
+inline __host__ __device__ int dot(int2 a, int2 b)
+{
+ return a.x * b.x + a.y * b.y;
+}
+inline __host__ __device__ int dot(int3 a, int3 b)
+{
+ return a.x * b.x + a.y * b.y + a.z * b.z;
+}
+inline __host__ __device__ int dot(int4 a, int4 b)
+{
+ return a.x * b.x + a.y * b.y + a.z * b.z + a.w * b.w;
+}
+
+inline __host__ __device__ uint dot(uint2 a, uint2 b)
+{
+ return a.x * b.x + a.y * b.y;
+}
+inline __host__ __device__ uint dot(uint3 a, uint3 b)
+{
+ return a.x * b.x + a.y * b.y + a.z * b.z;
+}
+inline __host__ __device__ uint dot(uint4 a, uint4 b)
+{
+ return a.x * b.x + a.y * b.y + a.z * b.z + a.w * b.w;
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// length
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float length(float2 v)
+{
+ return sqrtf(dot(v, v));
+}
+inline __host__ __device__ float length(float3 v)
+{
+ return sqrtf(dot(v, v));
+}
+inline __host__ __device__ float length(float4 v)
+{
+ return sqrtf(dot(v, v));
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// normalize
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float2 normalize(float2 v)
+{
+ float invLen = rsqrtf(dot(v, v));
+ return v * invLen;
+}
+inline __host__ __device__ float3 normalize(float3 v)
+{
+ float invLen = rsqrtf(dot(v, v));
+ return v * invLen;
+}
+inline __host__ __device__ float4 normalize(float4 v)
+{
+ float invLen = rsqrtf(dot(v, v));
+ return v * invLen;
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// floor
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float2 floorf(float2 v)
+{
+ return make_float2(floorf(v.x), floorf(v.y));
+}
+inline __host__ __device__ float3 floorf(float3 v)
+{
+ return make_float3(floorf(v.x), floorf(v.y), floorf(v.z));
+}
+inline __host__ __device__ float4 floorf(float4 v)
+{
+ return make_float4(floorf(v.x), floorf(v.y), floorf(v.z), floorf(v.w));
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// frac - returns the fractional portion of a scalar or each vector component
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float fracf(float v)
+{
+ return v - floorf(v);
+}
+inline __host__ __device__ float2 fracf(float2 v)
+{
+ return make_float2(fracf(v.x), fracf(v.y));
+}
+inline __host__ __device__ float3 fracf(float3 v)
+{
+ return make_float3(fracf(v.x), fracf(v.y), fracf(v.z));
+}
+inline __host__ __device__ float4 fracf(float4 v)
+{
+ return make_float4(fracf(v.x), fracf(v.y), fracf(v.z), fracf(v.w));
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// fmod
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float2 fmodf(float2 a, float2 b)
+{
+ return make_float2(fmodf(a.x, b.x), fmodf(a.y, b.y));
+}
+inline __host__ __device__ float3 fmodf(float3 a, float3 b)
+{
+ return make_float3(fmodf(a.x, b.x), fmodf(a.y, b.y), fmodf(a.z, b.z));
+}
+inline __host__ __device__ float4 fmodf(float4 a, float4 b)
+{
+ return make_float4(fmodf(a.x, b.x), fmodf(a.y, b.y), fmodf(a.z, b.z), fmodf(a.w, b.w));
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// absolute value
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float2 fabs(float2 v)
+{
+ return make_float2(fabs(v.x), fabs(v.y));
+}
+inline __host__ __device__ float3 fabs(float3 v)
+{
+ return make_float3(fabs(v.x), fabs(v.y), fabs(v.z));
+}
+inline __host__ __device__ float4 fabs(float4 v)
+{
+ return make_float4(fabs(v.x), fabs(v.y), fabs(v.z), fabs(v.w));
+}
+
+inline __host__ __device__ int2 abs(int2 v)
+{
+ return make_int2(abs(v.x), abs(v.y));
+}
+inline __host__ __device__ int3 abs(int3 v)
+{
+ return make_int3(abs(v.x), abs(v.y), abs(v.z));
+}
+inline __host__ __device__ int4 abs(int4 v)
+{
+ return make_int4(abs(v.x), abs(v.y), abs(v.z), abs(v.w));
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// reflect
+// - returns reflection of incident ray I around surface normal N
+// - N should be normalized, reflected vector's length is equal to length of I
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float3 reflect(float3 i, float3 n)
+{
+ return i - 2.0f * n * dot(n,i);
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// cross product
+////////////////////////////////////////////////////////////////////////////////
+
+inline __host__ __device__ float3 cross(float3 a, float3 b)
+{
+ return make_float3(a.y*b.z - a.z*b.y, a.z*b.x - a.x*b.z, a.x*b.y - a.y*b.x);
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// smoothstep
+// - returns 0 if x < a
+// - returns 1 if x > b
+// - otherwise returns smooth interpolation between 0 and 1 based on x
+////////////////////////////////////////////////////////////////////////////////
+
+inline __device__ __host__ float smoothstep(float a, float b, float x)
+{
+ float y = clamp((x - a) / (b - a), 0.0f, 1.0f);
+ return (y*y*(3.0f - (2.0f*y)));
+}
+inline __device__ __host__ float2 smoothstep(float2 a, float2 b, float2 x)
+{
+ float2 y = clamp((x - a) / (b - a), 0.0f, 1.0f);
+ return (y*y*(make_float2(3.0f) - (make_float2(2.0f)*y)));
+}
+inline __device__ __host__ float3 smoothstep(float3 a, float3 b, float3 x)
+{
+ float3 y = clamp((x - a) / (b - a), 0.0f, 1.0f);
+ return (y*y*(make_float3(3.0f) - (make_float3(2.0f)*y)));
+}
+inline __device__ __host__ float4 smoothstep(float4 a, float4 b, float4 x)
+{
+ float4 y = clamp((x - a) / (b - a), 0.0f, 1.0f);
+ return (y*y*(make_float4(3.0f) - (make_float4(2.0f)*y)));
+}
+
+#endif
diff --git a/main.c b/main.c
new file mode 100644
index 0000000..b5dda5c
--- /dev/null
+++ b/main.c
@@ -0,0 +1,23 @@
+#include <stdio.h>
+#include "raylib.h"
+
+int main() {
+ const int size_x = 1920;
+ const int size_y = 1080;
+ Image image = GenImageColor(size_x, size_y, BLUE);
+
+ InitWindow(size_x, size_y, "cuda teseteroni");
+
+
+
+
+ if(!IsWindowFullscreen()) ToggleFullscreen();
+
+ while(!WindowShouldClose()) {
+ BeginDrawing();
+ DrawTexture(LoadTextureFromImage(image), 0, 0, WHITE);
+ EndDrawing();
+ }
+
+ return 0;
+}
diff --git a/main.cu b/main.cu
new file mode 100644
index 0000000..9063a8f
--- /dev/null
+++ b/main.cu
@@ -0,0 +1,6 @@
+#include "include/helper_math.h"
+__global__ void random_noise(double **image) {
+ int2 unnormalized_coordinates = make_int2(blockDim.x, blockDim.y) * make_int2(blockIdx.x, blockIdx.y) + make_int2(threadIdx.x, threadIdx.y);
+ int2 img_res = make_int2(blockDim.x, blockDim.y) * make_int2(gridDim.x, gridDim.y);//could move out of kernel for performance boost
+
+}
diff --git a/makefile b/makefile
new file mode 100644
index 0000000..c2e4c4e
--- /dev/null
+++ b/makefile
@@ -0,0 +1,11 @@
+LIBS = -lraylib -lGL -lm -lpthread -ldl -lrt -lX11
+$CC = gcc
+make:
+ $(CC) $(LIBS) main.c -o build/main.o
+ nvcc --compile main.cu -o build/kernel.o
+ gcc -o indigo_worlds main.o kernel.o
+
+clean:
+ rm -r build/*
+
+