[Libclc-dev] [PATCH 2/2] R600: improve float vload/vstore path

Matt Arsenault arsenm2 at gmail.com
Fri Jul 18 11:12:30 PDT 2014


On Jul 18, 2014, at 9:04 AM, Aaron Watry <awatry at gmail.com> wrote:

> -/*Note: R600 back-end doesn't support load <3 x ?>... so
> +/*Note: R600 back-end doesn't support store <3 x ?>... so
>  * those functions aren't actually overridden here... When the back-end supports
>  * that, then clean add here, and remove the vstore3 definitions from above.
>  */
> @@ -100,5 +106,6 @@ _CLC_DECL void __clc_vstore16_##LLVM_SCALAR_TYPE##__addr##ADDR_SPACE_ID (PRIM_TY
>   _CLC_VSTORE_ASM_DECL(int,i32,__global,1) \
>   _CLC_VSTORE_ASM_OVERLOAD_ADDR_SPACES(int,int,i32) \
>   _CLC_VSTORE_ASM_OVERLOAD_ADDR_SPACES(uint,int,i32) \
> +  _CLC_VSTORE_ASM_OVERLOAD_ADDR_SPACES(float,int,i32) \

What’s wrong with 3 x vectors? They don’t work very well and get split into multiple loads currently, but they should work correctly for now
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/libclc-dev/attachments/20140718/d41d5721/attachment-0001.html>


More information about the Libclc-dev mailing list