[Mesa-dev] [PATCH v2 1/5] r600: double multiply can handle only one multiply at a time

[Nicolai Hähnle]

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

It seems clear that trying to multiply two pairs of doubles would result
in the temporary register getting overwritten by the second pair. So
make the code more explicit.
---
 src/gallium/drivers/r600/r600_shader.c | 36 ++++++++++++++++++----------------
 1 file changed, 19 insertions(+), 17 deletions(-)

diff --git a/src/gallium/drivers/r600/r600_shader.c b/src/gallium/drivers/r600/r600_shader.c
index ebe2744..7d1452a 100644
--- a/src/gallium/drivers/r600/r600_shader.c
+++ b/src/gallium/drivers/r600/r600_shader.c
@@ -4319,39 +4319,41 @@ static int cayman_mul_int_instr(struct r600_shader_ctx *ctx)
 
 
 static int cayman_mul_double_instr(struct r600_shader_ctx *ctx)
 {
 	struct tgsi_full_instruction *inst = &ctx->parse.FullToken.FullInstruction;
 	int i, j, k, r;
 	struct r600_bytecode_alu alu;
 	int lasti = tgsi_last_instruction(inst->Dst[0].Register.WriteMask);
 	int t1 = ctx->temp_reg;
 
-	for (k = 0; k < 2; k++) {
-		if (!(inst->Dst[0].Register.WriteMask & (0x3 << (k * 2))))
-			continue;
+	/* t1 would get overwritten below if we actually tried to
+	 * multiply two pairs of doubles at a time. */
+	assert(inst->Dst[0].Register.WriteMask == TGSI_WRITEMASK_XY ||
+	       inst->Dst[0].Register.WriteMask == TGSI_WRITEMASK_ZW);
 
-		for (i = 0; i < 4; i++) {
-			memset(&alu, 0, sizeof(struct r600_bytecode_alu));
-			alu.op = ctx->inst_info->op;
-			for (j = 0; j < inst->Instruction.NumSrcRegs; j++) {
-				r600_bytecode_src(&alu.src[j], &ctx->src[j], k * 2 + ((i == 3) ? 0 : 1));
-			}
-			alu.dst.sel = t1;
-			alu.dst.chan = i;
-			alu.dst.write = 1;
-			if (i == 3)
-				alu.last = 1;
-			r = r600_bytecode_add_alu(ctx->bc, &alu);
-			if (r)
-				return r;
+	k = inst->Dst[0].Register.WriteMask == TGSI_WRITEMASK_XY ? 0 : 1;
+
+	for (i = 0; i < 4; i++) {
+		memset(&alu, 0, sizeof(struct r600_bytecode_alu));
+		alu.op = ctx->inst_info->op;
+		for (j = 0; j < inst->Instruction.NumSrcRegs; j++) {
+			r600_bytecode_src(&alu.src[j], &ctx->src[j], k * 2 + ((i == 3) ? 0 : 1));
 		}
+		alu.dst.sel = t1;
+		alu.dst.chan = i;
+		alu.dst.write = 1;
+		if (i == 3)
+			alu.last = 1;
+		r = r600_bytecode_add_alu(ctx->bc, &alu);
+		if (r)
+			return r;
 	}
 
 	for (i = 0; i <= lasti; i++) {
 		if (!(inst->Dst[0].Register.WriteMask & (1 << i)))
 			continue;
 		memset(&alu, 0, sizeof(struct r600_bytecode_alu));
 		alu.op = ALU_OP1_MOV;
 		alu.src[0].sel = t1;
 		alu.src[0].chan = i;
 		tgsi_dst(ctx, &inst->Dst[0], i, &alu.dst);
-- 
2.7.4