[Mesa-dev] [PATCH] radeonsi: add a debug flag for unsafe math LLVM optimizations

[Tom Stellard]

On Mon, Jun 13, 2016 at 06:27:02PM +0200, Marek Olšák wrote:
> From: Marek Olšák <marek.olsak at amd.com>
> 
> ---
>  src/gallium/drivers/radeon/r600_pipe_common.c |  1 +
>  src/gallium/drivers/radeon/r600_pipe_common.h |  1 +
>  src/gallium/drivers/radeonsi/si_shader.c      | 16 ++++++++++++++++
>  3 files changed, 18 insertions(+)
> 
> diff --git a/src/gallium/drivers/radeon/r600_pipe_common.c b/src/gallium/drivers/radeon/r600_pipe_common.c
> index fa9f70d..5d4a679 100644
> --- a/src/gallium/drivers/radeon/r600_pipe_common.c
> +++ b/src/gallium/drivers/radeon/r600_pipe_common.c
> @@ -482,6 +482,7 @@ static const struct debug_named_value common_debug_options[] = {
>  	{ "sisched", DBG_SI_SCHED, "Enable LLVM SI Machine Instruction Scheduler." },
>  	{ "mono", DBG_MONOLITHIC_SHADERS, "Use old-style monolithic shaders compiled on demand" },
>  	{ "noce", DBG_NO_CE, "Disable the constant engine"},
> +	{ "unsafemath", DBG_UNSAFE_MATH, "Enable unsafe math shader optimizations" },
>  
>  	DEBUG_NAMED_VALUE_END /* must be last */
>  };
> diff --git a/src/gallium/drivers/radeon/r600_pipe_common.h b/src/gallium/drivers/radeon/r600_pipe_common.h
> index 77dfc4f..263ef5e 100644
> --- a/src/gallium/drivers/radeon/r600_pipe_common.h
> +++ b/src/gallium/drivers/radeon/r600_pipe_common.h
> @@ -99,6 +99,7 @@
>  #define DBG_SI_SCHED		(1llu << 46)
>  #define DBG_MONOLITHIC_SHADERS	(1llu << 47)
>  #define DBG_NO_CE		(1llu << 48)
> +#define DBG_UNSAFE_MATH		(1llu << 49)
>  
>  #define R600_MAP_BUFFER_ALIGNMENT 64
>  #define R600_MAX_VIEWPORTS        16
> diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
> index 6dc4985..bba6a55 100644
> --- a/src/gallium/drivers/radeonsi/si_shader.c
> +++ b/src/gallium/drivers/radeonsi/si_shader.c
> @@ -5255,6 +5255,22 @@ static void si_create_function(struct si_shader_context *ctx,
>  		else
>  			LLVMAddAttribute(P, LLVMInRegAttribute);
>  	}
> +
> +	if (ctx->screen->b.debug_flags & DBG_UNSAFE_MATH) {
> +		/* These were copied from some LLVM test. */
> +		LLVMAddTargetDependentFunctionAttr(ctx->radeon_bld.main_fn,
> +						   "less-precise-fpmad",
> +						   "true");
> +		LLVMAddTargetDependentFunctionAttr(ctx->radeon_bld.main_fn,
> +						   "no-infs-fp-math",
> +						   "true");
> +		LLVMAddTargetDependentFunctionAttr(ctx->radeon_bld.main_fn,
> +						   "no-nans-fp-math",
> +						   "true");
> +		LLVMAddTargetDependentFunctionAttr(ctx->radeon_bld.main_fn,
> +						   "unsafe-fp-math",
> +						   "true");
> +	}

You may get better results by also adding the fast-math flags to the
individual floating-point instructions, but this would be a more
invasive change.

-Tom

>  }
>  
>  static void create_meta_data(struct si_shader_context *ctx)
> -- 
> 2.7.4
> 
> _______________________________________________
> mesa-dev mailing list
> mesa-dev at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/mesa-dev