From a6e44d12714871193ef130845b1f8727ffdbf01e Mon Sep 17 00:00:00 2001 From: Samuel Pitoiset Date: Wed, 16 May 2018 17:43:22 +0200 Subject: [PATCH] radv: do not emit unnecessary GS output stores Signed-off-by: Samuel Pitoiset Reviewed-by: Bas Nieuwenhuizen --- src/amd/vulkan/radv_nir_to_llvm.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/src/amd/vulkan/radv_nir_to_llvm.c b/src/amd/vulkan/radv_nir_to_llvm.c index b4af0f29415..05ae7096857 100644 --- a/src/amd/vulkan/radv_nir_to_llvm.c +++ b/src/amd/vulkan/radv_nir_to_llvm.c @@ -1684,6 +1684,8 @@ visit_emit_vertex(struct ac_shader_abi *abi, unsigned stream, LLVMValueRef *addr /* loop num outputs */ idx = 0; for (unsigned i = 0; i < AC_LLVM_MAX_OUTPUTS; ++i) { + unsigned output_usage_mask = + ctx->shader_info->info.gs.output_usage_mask[i]; LLVMValueRef *out_ptr = &addrs[i * 4]; int length = 4; int slot = idx; @@ -1697,8 +1699,13 @@ visit_emit_vertex(struct ac_shader_abi *abi, unsigned stream, LLVMValueRef *addr length = ctx->num_output_clips + ctx->num_output_culls; if (length > 4) slot_inc = 2; + output_usage_mask = (1 << length) - 1; } + for (unsigned j = 0; j < length; j++) { + if (!(output_usage_mask & (1 << j))) + continue; + LLVMValueRef out_val = LLVMBuildLoad(ctx->ac.builder, out_ptr[j], ""); LLVMValueRef voffset = LLVMConstInt(ctx->ac.i32, (slot * 4 + j) * ctx->gs_max_out_vertices, false); -- 2.30.2