> On Oct 3, 2017, at 13:58, Dave Airlie <airl...@gmail.com> wrote:
>
> From: Dave Airlie <airl...@redhat.com>
>
> So it appears the Vulkan SPIR-V fma opcode can be equivalent to a
> mad operation, and the fma hw opcode on AMD hw is issued like a double
> opcode so is slower. Also the radeonsi stack does this.
>
> This appears to improve performance on a number of games from Feral,
> and thanks to Feral for noticing the problem.
>
> Signed-off-by: Dave Airlie <airl...@redhat.com>
> ---
> src/amd/vulkan/radv_shader.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/src/amd/vulkan/radv_shader.c b/src/amd/vulkan/radv_shader.c
> index ca0ad2d..a37345b 100644
> --- a/src/amd/vulkan/radv_shader.c
> +++ b/src/amd/vulkan/radv_shader.c
> @@ -64,6 +64,7 @@ static const struct nir_shader_compiler_options nir_options
> = {
> .lower_unpack_unorm_4x8 = true,
> .lower_extract_byte = true,
> .lower_extract_word = true,
> + .lower_ffma = true,
> .max_unroll_iterations = 32
> };
>
> --
> 2.9.5
>
> _______________________________________________
> mesa-dev mailing list
> mesa-dev@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/mesa-dev
If it doesn’t matter this should emit llvm.fmuladd. The backend decides what’s
best to do based on the specific target whether it’s an FMA or MAD.
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
