Mesa (master): radeonsi/gfx9: fix vertex idx in ES with multiple waves per threadgroup

[Nicolai Hähnle]

Module: Mesa
Branch: master
Commit: 873789002f5d1c7c6c39231a8c8d541f4f61e65c
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=873789002f5d1c7c6c39231a8c8d541f4f61e65c

Author: Nicolai Hähnle <nicolai.haehnle at amd.com>
Date:   Fri Jul 14 13:31:49 2017 +0200

radeonsi/gfx9: fix vertex idx in ES with multiple waves per threadgroup

Cc: mesa-stable at lists.freedesktop.org
Reviewed: Marek Olšák <marek.olsak at amd.com>

---

 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 a5baf71b0d..a153cb7784 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -2879,7 +2879,12 @@ static void si_llvm_emit_es_epilogue(struct lp_build_tgsi_context *bld_base)
 
 	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), "");
 	}