[Mesa-dev] [PATCH v2 01/20] radeonsi: lower compute shader arguments

[eocallaghan at alterapraxis.com]

Patches - 2-4, 7-8, 12-14 & 17 - are all:

  Reviewed-by: Edward O'Callaghan <eocallaghan at alterapraxis.com>

The series was:

  Tested-by: Edward O'Callaghan <eocallaghan at alterapraxis.com>

On 2016-04-14 05:29, Bas Nieuwenhuizen wrote:
> Signed-off-by: Bas Nieuwenhuizen <bas at basnieuwenhuizen.nl>
> Reviewed-by: Marek Olšák <marek.olsak at amd.com>
> Reviewed-by: Nicolai Hähnle <nicolai.haehnle at amd.com>
> ---
>  src/gallium/drivers/radeonsi/si_shader.c | 41 
> ++++++++++++++++++++++++++++++++
>  src/gallium/drivers/radeonsi/si_shader.h |  7 ++++++
>  2 files changed, 48 insertions(+)
> 
> diff --git a/src/gallium/drivers/radeonsi/si_shader.c
> b/src/gallium/drivers/radeonsi/si_shader.c
> index c58467d..1ccdcac 100644
> --- a/src/gallium/drivers/radeonsi/si_shader.c
> +++ b/src/gallium/drivers/radeonsi/si_shader.c
> @@ -1282,6 +1282,36 @@ static void declare_system_value(
>  		value = get_primitive_id(&radeon_bld->soa.bld_base, 0);
>  		break;
> 
> +	case TGSI_SEMANTIC_GRID_SIZE:
> +		value = LLVMGetParam(radeon_bld->main_fn, SI_PARAM_GRID_SIZE);
> +		break;
> +
> +	case TGSI_SEMANTIC_BLOCK_SIZE:
> +	{
> +		LLVMValueRef values[3];
> +		unsigned i;
> +		unsigned *properties = ctx->shader->selector->info.properties;
> +		unsigned sizes[3] = {
> +			properties[TGSI_PROPERTY_CS_FIXED_BLOCK_WIDTH],
> +			properties[TGSI_PROPERTY_CS_FIXED_BLOCK_HEIGHT],
> +			properties[TGSI_PROPERTY_CS_FIXED_BLOCK_DEPTH]
> +		};
> +
> +		for (i = 0; i < 3; ++i)
> +			values[i] = lp_build_const_int32(gallivm, sizes[i]);
> +
> +		value = lp_build_gather_values(gallivm, values, 3);
> +		break;
> +	}
> +
> +	case TGSI_SEMANTIC_BLOCK_ID:
> +		value = LLVMGetParam(radeon_bld->main_fn, SI_PARAM_BLOCK_ID);
> +		break;
> +
> +	case TGSI_SEMANTIC_THREAD_ID:
> +		value = LLVMGetParam(radeon_bld->main_fn, SI_PARAM_THREAD_ID);
> +		break;
> +
>  	default:
>  		assert(!"unknown system value");
>  		return;
> @@ -4823,6 +4853,14 @@ static void create_function(struct
> si_shader_context *ctx)
>  		}
>  		break;
> 
> +	case TGSI_PROCESSOR_COMPUTE:
> +		params[SI_PARAM_GRID_SIZE] = v3i32;
> +		params[SI_PARAM_BLOCK_ID] = v3i32;
> +		last_sgpr = SI_PARAM_BLOCK_ID;
> +
> +		params[SI_PARAM_THREAD_ID] = v3i32;
> +		num_params = SI_PARAM_THREAD_ID + 1;
> +		break;
>  	default:
>  		assert(0 && "unimplemented shader");
>  		return;
> @@ -5600,6 +5638,7 @@ void si_dump_shader_key(unsigned shader, union
> si_shader_key *key, FILE *f)
>  		break;
> 
>  	case PIPE_SHADER_GEOMETRY:
> +	case PIPE_SHADER_COMPUTE:
>  		break;
> 
>  	case PIPE_SHADER_FRAGMENT:
> @@ -5784,6 +5823,8 @@ int si_compile_tgsi_shader(struct si_screen 
> *sscreen,
>  		else
>  			bld_base->emit_epilogue = si_llvm_return_fs_outputs;
>  		break;
> +	case TGSI_PROCESSOR_COMPUTE:
> +		break;
>  	default:
>  		assert(!"Unsupported shader type");
>  		return -1;
> diff --git a/src/gallium/drivers/radeonsi/si_shader.h
> b/src/gallium/drivers/radeonsi/si_shader.h
> index 013c8a2..5043d43 100644
> --- a/src/gallium/drivers/radeonsi/si_shader.h
> +++ b/src/gallium/drivers/radeonsi/si_shader.h
> @@ -91,6 +91,7 @@ struct radeon_shader_reloc;
>  #define SI_SGPR_TCS_OUT_LAYOUT	11 /* TCS & TES only */
>  #define SI_SGPR_TCS_IN_LAYOUT	12 /* TCS only */
>  #define SI_SGPR_ALPHA_REF	10 /* PS only */
> +#define SI_SGPR_GRID_SIZE	10 /* CS only */
> 
>  #define SI_VS_NUM_USER_SGPR	15 /* API VS */
>  #define SI_ES_NUM_USER_SGPR	14 /* API VS */
> @@ -100,6 +101,7 @@ struct radeon_shader_reloc;
>  #define SI_GS_NUM_USER_SGPR	10
>  #define SI_GSCOPY_NUM_USER_SGPR	4
>  #define SI_PS_NUM_USER_SGPR	11
> +#define SI_CS_NUM_USER_SGPR	13
> 
>  /* LLVM function parameter indices */
>  #define SI_PARAM_RW_BUFFERS	0
> @@ -173,6 +175,11 @@ struct radeon_shader_reloc;
>  #define SI_PARAM_SAMPLE_COVERAGE	21
>  #define SI_PARAM_POS_FIXED_PT		22
> 
> +/* CS only parameters */
> +#define SI_PARAM_GRID_SIZE		5
> +#define SI_PARAM_BLOCK_ID		6
> +#define SI_PARAM_THREAD_ID		7
> +
>  #define SI_NUM_PARAMS (SI_PARAM_POS_FIXED_PT + 9) /* +8 for 
> COLOR[0..1] */
> 
>  struct si_shader;