Nobody expects the Red Teamv3

Too many changes to list, but broadly:
* Remove Intel GPU support from the compiler
* Add AMD GPU support to the compiler
* Remove Intel GPU host code
* Add AMD GPU host code
* More device instructions. From 40 to 68
* More host functions. From 48 to 184
* Add proof of concept implementation of OptiX framework
* Add minimal support of cuDNN, cuBLAS, cuSPARSE, cuFFT, NCCL, NVML
* Improve ZLUDA launcher for Windows

1 files changed, 34 insertions, 0 deletions

diff --git a/zluda/tests/kernel_texobj_2d.ptx b/zluda/tests/kernel_texobj_2d.ptx
new file mode 100644
index 0000000..6b1d7db
--- /dev/null
+++ b/zluda/tests/kernel_texobj_2d.ptx
@@ -0,0 +1,34 @@
+.version 6.5

+.target sm_30

+.address_size 64

+

+.visible .entry texobj(

+    .param .f32 input_x,

+    .param .f32 input_y,

+    .param .u64 image_param,

+    .param .u64 output

+)

+{

+    .reg .u64 	    out_addr;

+    .reg .u64 	    temp;

+    .reg .u64 	    temp2;

+    .reg .u64 	    image;

+    .reg .f32       x;

+    .reg .f32       y;

+    .reg .s32       r;

+    .reg .s32       g;

+    .reg .s32       b;

+    .reg .s32       a;

+

+    ld.param.f32    x, [input_x];

+    ld.param.f32    y, [input_y];

+    ld.param.u64    image, [image_param];

+    ld.param.u64    out_addr, [output];

+

+    tex.2d.v4.s32.f32   {r, g, b, a}, [image, {x, y}];

+    st.b32              [out_addr], a;

+    st.b32              [out_addr+4], b;

+    st.b32              [out_addr+8], g;

+    st.b32              [out_addr+12], r;

+    ret;

+}