[Mesa-dev] [PATCH] radeonsi/gfx9: compile shaders with +xnack

[Marek Olšák]

From: Marek Olšák <marek.olsak at amd.com>

so that LLVM doesn't allocate SGPRs where XNACK is.

Cc: 17.1 <mesa-stable at lists.freedesktop.org>
---
 src/gallium/drivers/radeonsi/si_pipe.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/src/gallium/drivers/radeonsi/si_pipe.c b/src/gallium/drivers/radeonsi/si_pipe.c
index eaa3348..6f82e29 100644
--- a/src/gallium/drivers/radeonsi/si_pipe.c
+++ b/src/gallium/drivers/radeonsi/si_pipe.c
@@ -26,23 +26,20 @@
 #include "si_shader_internal.h"
 #include "sid.h"
 
 #include "radeon/radeon_uvd.h"
 #include "util/u_memory.h"
 #include "util/u_suballoc.h"
 #include "util/u_tests.h"
 #include "vl/vl_decoder.h"
 #include "../ddebug/dd_util.h"
 
-#define SI_LLVM_DEFAULT_FEATURES \
-	"+DumpCode,+vgpr-spilling,-fp32-denormals,-xnack"
-
 /*
  * pipe_context
  */
 static void si_destroy_context(struct pipe_context *context)
 {
 	struct si_context *sctx = (struct si_context *)context;
 	int i;
 
 	/* Unreference the framebuffer normally to disable related logic
 	 * properly.
@@ -120,26 +117,30 @@ static void si_emit_string_marker(struct pipe_context *ctx,
 {
 	struct si_context *sctx = (struct si_context *)ctx;
 
 	dd_parse_apitrace_marker(string, len, &sctx->apitrace_call_number);
 }
 
 static LLVMTargetMachineRef
 si_create_llvm_target_machine(struct si_screen *sscreen)
 {
 	const char *triple = "amdgcn--";
+	char features[256];
+
+	snprintf(features, sizeof(features),
+		 "+DumpCode,+vgpr-spilling,-fp32-denormals,+fp64-denormals%s%s",
+		 sscreen->b.chip_class >= GFX9 ? ",+xnack" : ",-xnack",
+		 sscreen->b.debug_flags & DBG_SI_SCHED ? ",+si-scheduler" : "");
 
 	return LLVMCreateTargetMachine(si_llvm_get_amdgpu_target(triple), triple,
 				       r600_get_llvm_processor_name(sscreen->b.family),
-				       sscreen->b.debug_flags & DBG_SI_SCHED ?
-					       SI_LLVM_DEFAULT_FEATURES ",+si-scheduler" :
-					       SI_LLVM_DEFAULT_FEATURES,
+				       features,
 				       LLVMCodeGenLevelDefault,
 				       LLVMRelocDefault,
 				       LLVMCodeModelDefault);
 }
 
 static struct pipe_context *si_create_context(struct pipe_screen *screen,
                                               unsigned flags)
 {
 	struct si_context *sctx = CALLOC_STRUCT(si_context);
 	struct si_screen* sscreen = (struct si_screen *)screen;
-- 
2.7.4