[Mesa-dev] [PATCH] amd/common: use llvm.amdgcn.wqm for explicit derivatives

[Bas Nieuwenhuizen]

Reviewed-by: Bas Nieuwenhuizen <bas at basnieuwenhuizen.nl>

On Thu, May 3, 2018 at 5:18 PM, Nicolai Hähnle <nhaehnle at gmail.com> wrote:
> From: Nicolai Hähnle <nicolai.haehnle at amd.com>
>
> To comply with an upcoming change in LLVM, see
> https://reviews.llvm.org/D46051
> ---
>  src/amd/common/ac_llvm_build.c | 7 +++++++
>  1 file changed, 7 insertions(+)
>
> diff --git a/src/amd/common/ac_llvm_build.c b/src/amd/common/ac_llvm_build.c
> index f21a5d2623c..c9b2e36b632 100644
> --- a/src/amd/common/ac_llvm_build.c
> +++ b/src/amd/common/ac_llvm_build.c
> @@ -1241,20 +1241,27 @@ ac_build_ddxy(struct ac_llvm_context *ctx,
>                 trbl = ac_build_intrinsic(ctx,
>                                         "llvm.amdgcn.ds.swizzle", ctx->i32,
>                                         args, 2,
>                                         AC_FUNC_ATTR_READNONE |
>                                         AC_FUNC_ATTR_CONVERGENT);
>         }
>
>         tl = LLVMBuildBitCast(ctx->builder, tl, ctx->f32, "");
>         trbl = LLVMBuildBitCast(ctx->builder, trbl, ctx->f32, "");
>         result = LLVMBuildFSub(ctx->builder, trbl, tl, "");
> +
> +       if (HAVE_LLVM >= 0x0700) {
> +               result = ac_build_intrinsic(ctx,
> +                       "llvm.amdgcn.wqm.f32", ctx->f32,
> +                       &result, 1, 0);
> +       }
> +
>         return result;
>  }
>
>  void
>  ac_build_sendmsg(struct ac_llvm_context *ctx,
>                  uint32_t msg,
>                  LLVMValueRef wave_id)
>  {
>         LLVMValueRef args[2];
>         args[0] = LLVMConstInt(ctx->i32, msg, false);
> --
> 2.14.1
>
> _______________________________________________
> mesa-dev mailing list
> mesa-dev at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/mesa-dev