aaron/ispc
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Added nvptx64 target. Things to do:

Browse Source 
1. builtins/target-nvptx64.ll to write, now it is just a copy of target-generic-1.ll
2. add __global__ & __device__ scope
2. make code work for a single cuda thread
3. use tasks to work as a block grid and programIndex as laneIdx, programCount as warpSize
4. ... and more...
This commit is contained in:
egaburov
2013-07-28 14:31:43 +02:00
parent 663ebf7857
commit 67b549a937
6 changed files with 1035 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ispc.h
View File

@@ -175,7 +175,7 @@ public:
flexible/performant of them will apear last in the enumerant. Note
also that __best_available_isa() needs to be updated if ISAs are
added or the enumerant values are reordered. */
enum ISA { NEON, SSE2, SSE4, AVX, AVX11, AVX2, GENERIC, NUM_ISAS };
enum ISA { NVPTX64, NEON, SSE2, SSE4, AVX, AVX11, AVX2, GENERIC, NUM_ISAS };
/** Initializes the given Target pointer for a target of the given
name, if the name is a known target. Returns true if the