[Mesa-dev] [PATCH 1/5] radeonsi/gfx9: fix vertex idx in ES with multiple waves per threadgroup

[Nicolai Hähnle]

From: Nicolai Hähnle <nicolai.haehnle at amd.com>

Cc: mesa-stable at lists.freedesktop.org
---
 src/gallium/drivers/radeonsi/si_shader.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index 4c0cda5..7a44e61 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -2890,21 +2890,26 @@ static void si_llvm_emit_es_epilogue(struct lp_build_tgsi_context *bld_base)
 	struct si_shader *es = ctx->shader;
 	struct tgsi_shader_info *info = &es->selector->info;
 	LLVMValueRef soffset = LLVMGetParam(ctx->main_fn,
 					    ctx->param_es2gs_offset);
 	LLVMValueRef lds_base = NULL;
 	unsigned chan;
 	int i;
 
 	if (ctx->screen->b.chip_class >= GFX9 && info->num_outputs) {
 		unsigned itemsize_dw = es->selector->esgs_itemsize / 4;
-		lds_base = LLVMBuildMul(gallivm->builder, ac_get_thread_id(&ctx->ac),
+		LLVMValueRef vertex_idx = ac_get_thread_id(&ctx->ac);
+		LLVMValueRef wave_idx = unpack_param(ctx, ctx->param_merged_wave_info, 24, 4);
+		vertex_idx = LLVMBuildOr(gallivm->builder, vertex_idx,
+					 LLVMBuildMul(gallivm->builder, wave_idx,
+						      LLVMConstInt(ctx->i32, 64, false), ""), "");
+		lds_base = LLVMBuildMul(gallivm->builder, vertex_idx,
 					LLVMConstInt(ctx->i32, itemsize_dw, 0), "");
 	}
 
 	for (i = 0; i < info->num_outputs; i++) {
 		LLVMValueRef *out_ptr = ctx->outputs[i];
 		int param;
 
 		if (info->output_semantic_name[i] == TGSI_SEMANTIC_VIEWPORT_INDEX ||
 		    info->output_semantic_name[i] == TGSI_SEMANTIC_LAYER)
 			continue;
-- 
2.9.3