[Mesa-dev] [PATCH] radv: lower ffma in nir.

[Matt Arsenault]

> On Oct 3, 2017, at 13:58, Dave Airlie <airlied at gmail.com> wrote:
> 
> From: Dave Airlie <airlied at 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 <airlied at 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 at 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.