[Mesa-dev] [PATCH 2/2] r600: Fix SSG when not all components are written

[Gert Wollny]

Make sure only those components are written to that are specified in the
write mask.

Fixes:
  dEQP-GLES2.functional.shaders.operator.common_functions.sign.lowp_float_vertex
  dEQP-GLES2.functional.shaders.operator.common_functions.sign.lowp_float_fragment
  dEQP-GLES2.functional.shaders.operator.common_functions.sign.mediump_float_vertex
  dEQP-GLES2.functional.shaders.operator.common_functions.sign.mediump_float_fragment
  dEQP-GLES2.functional.shaders.operator.common_functions.sign.highp_float_vertex
  dEQP-GLES2.functional.shaders.operator.common_functions.sign.highp_float_fragment
  dEQP-GLES2.functional.shaders.operator.common_functions.sign.lowp_vec3_vertex
  dEQP-GLES2.functional.shaders.operator.common_functions.sign.lowp_vec3_fragment
  dEQP-GLES2.functional.shaders.operator.common_functions.sign.mediump_vec3_vertex
  dEQP-GLES2.functional.shaders.operator.common_functions.sign.mediump_vec3_fragment
  dEQP-GLES2.functional.shaders.operator.common_functions.sign.highp_vec3_vertex
  dEQP-GLES2.functional.shaders.operator.common_functions.sign.highp_vec3_fragment
Signed-off-by: Gert Wollny <gw.fossdev at gmail.com>
---
 src/gallium/drivers/r600/r600_shader.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/src/gallium/drivers/r600/r600_shader.c b/src/gallium/drivers/r600/r600_shader.c
index e29cca6b98..ae91f84766 100644
--- a/src/gallium/drivers/r600/r600_shader.c
+++ b/src/gallium/drivers/r600/r600_shader.c
@@ -6678,11 +6678,15 @@ static int tgsi_issg(struct r600_shader_ctx *ctx)
 static int tgsi_ssg(struct r600_shader_ctx *ctx)
 {
 	struct tgsi_full_instruction *inst = &ctx->parse.FullToken.FullInstruction;
+	unsigned write_mask = inst->Dst[0].Register.WriteMask;
+	int last_inst = tgsi_last_instruction(write_mask);
 	struct r600_bytecode_alu alu;
 	int i, r;
 
 	/* tmp = (src > 0 ? 1 : src) */
-	for (i = 0; i < 4; i++) {
+	for (i = 0; i <= last_inst; i++) {
+		if (!(write_mask & (1 << i)))
+			continue; 
 		memset(&alu, 0, sizeof(struct r600_bytecode_alu));
 		alu.op = ALU_OP3_CNDGT;
 		alu.is_op3 = 1;
@@ -6694,7 +6698,7 @@ static int tgsi_ssg(struct r600_shader_ctx *ctx)
 		alu.src[1].sel = V_SQ_ALU_SRC_1;
 		r600_bytecode_src(&alu.src[2], &ctx->src[0], i);
 
-		if (i == 3)
+		if (i == last_inst)
 			alu.last = 1;
 		r = r600_bytecode_add_alu(ctx->bc, &alu);
 		if (r)
@@ -6702,7 +6706,9 @@ static int tgsi_ssg(struct r600_shader_ctx *ctx)
 	}
 
 	/* dst = (-tmp > 0 ? -1 : tmp) */
-	for (i = 0; i < 4; i++) {
+	for (i = 0; i <= last_inst; i++) {
+		if (!(write_mask & (1 << i)))
+			continue;
 		memset(&alu, 0, sizeof(struct r600_bytecode_alu));
 		alu.op = ALU_OP3_CNDGT;
 		alu.is_op3 = 1;
@@ -6718,7 +6724,7 @@ static int tgsi_ssg(struct r600_shader_ctx *ctx)
 		alu.src[2].sel = ctx->temp_reg;
 		alu.src[2].chan = i;
 
-		if (i == 3)
+		if (i == last_inst)
 			alu.last = 1;
 		r = r600_bytecode_add_alu(ctx->bc, &alu);
 		if (r)
-- 
2.16.1