[Mesa-dev] [PATCH] R600: Use CONSTANT_BUFFER_0 address space for Implicit Parameters

Tom Stellard tom at stellard.net
Tue Mar 19 18:40:22 PDT 2013


On Sat, Mar 16, 2013 at 05:45:31PM +0100, Vincent Lejeune wrote:
> It allows the backend to generate reads to constant cache which
> are faster that VTX_READ.

Hi Vincent,

Is there a corresponding Mesa change that goes with this patch?

-Tom

> ---
>  lib/Target/R600/R600ISelLowering.cpp | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/lib/Target/R600/R600ISelLowering.cpp b/lib/Target/R600/R600ISelLowering.cpp
> index a0e27ea..caa1899 100644
> --- a/lib/Target/R600/R600ISelLowering.cpp
> +++ b/lib/Target/R600/R600ISelLowering.cpp
> @@ -522,7 +522,7 @@ SDValue R600TargetLowering::LowerImplicitParameter(SelectionDAG &DAG, EVT VT,
>                                                     unsigned DwordOffset) const {
>    unsigned ByteOffset = DwordOffset * 4;
>    PointerType * PtrType = PointerType::get(VT.getTypeForEVT(*DAG.getContext()),
> -                                      AMDGPUAS::PARAM_I_ADDRESS);
> +                                      AMDGPUAS::CONSTANT_BUFFER_0);
>  
>    // We shouldn't be using an offset wider than 16-bits for implicit parameters.
>    assert(isInt<16>(ByteOffset));
> -- 
> 1.8.1.4
> 
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits


More information about the mesa-dev mailing list