[Mesa-dev] [PATCH] radv: Implement buffer stores with less than 4 components.

[Samuel Pitoiset]

Reviewed-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>

On 12/24/18 3:43 PM, Bas Nieuwenhuizen wrote:
> We started using it in the btoi paths for r32g32b32, and the LLVM IR
> checker will complain about it because we end up with intrinsics with
> the wrong type extension in the name.
>
> Fixes: 593996bc02 ("radv: implement buffer to image operations for R32G32B32")
> ---
>   src/amd/common/ac_nir_to_llvm.c | 19 ++++++++++++++-----
>   1 file changed, 14 insertions(+), 5 deletions(-)
>
> diff --git a/src/amd/common/ac_nir_to_llvm.c b/src/amd/common/ac_nir_to_llvm.c
> index 6d97212b805..0fa38b83a57 100644
> --- a/src/amd/common/ac_nir_to_llvm.c
> +++ b/src/amd/common/ac_nir_to_llvm.c
> @@ -2392,24 +2392,33 @@ static void visit_image_store(struct ac_nir_context *ctx,
>   		glc = ctx->ac.i1true;
>   
>   	if (dim == GLSL_SAMPLER_DIM_BUF) {
> +		char name[48];
> +		const char *types[] = { "f32", "v2f32", "v4f32" };
>   		LLVMValueRef rsrc = get_image_buffer_descriptor(ctx, instr, true);
> +		LLVMValueRef src = ac_to_float(&ctx->ac, get_src(ctx, instr->src[3]));
> +		unsigned src_channels = ac_get_llvm_num_components(src);
>   
> -		params[0] = ac_to_float(&ctx->ac, get_src(ctx, instr->src[3])); /* data */
> +		if (src_channels == 3)
> +			src = ac_build_expand(&ctx->ac, src, 3, 4);
> +
> +		params[0] = src; /* data */
>   		params[1] = rsrc;
>   		params[2] = LLVMBuildExtractElement(ctx->ac.builder, get_src(ctx, instr->src[1]),
>   						    ctx->ac.i32_0, ""); /* vindex */
>   		params[3] = ctx->ac.i32_0; /* voffset */
> +		snprintf(name, sizeof(name), "%s.%s",
> +		         HAVE_LLVM >= 0x800 ? "llvm.amdgcn.struct.buffer.store.format"
> +		                            : "llvm.amdgcn.buffer.store.format",
> +		         types[CLAMP(src_channels, 1, 3) - 1]);
> +
>   		if (HAVE_LLVM >= 0x800) {
>   			params[4] = ctx->ac.i32_0; /* soffset */
>   			params[5] = glc ? ctx->ac.i32_1 : ctx->ac.i32_0;
> -			ac_build_intrinsic(&ctx->ac, "llvm.amdgcn.struct.buffer.store.format.v4f32", ctx->ac.voidt,
> -			                   params, 6, 0);
>   		} else {
>   			params[4] = glc;  /* glc */
>   			params[5] = ctx->ac.i1false;  /* slc */
> -			ac_build_intrinsic(&ctx->ac, "llvm.amdgcn.buffer.store.format.v4f32", ctx->ac.voidt,
> -			                   params, 6, 0);
>   		}
> +		ac_build_intrinsic(&ctx->ac, name, ctx->ac.voidt, params, 6, 0);
>   	} else {
>   		struct ac_image_args args = {};
>   		args.opcode = ac_image_store;