r600: double multiply can handle only one multiply at a time

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.

Tested-by: Glenn Kennard <glenn.kennard@gmail.com>
Tested-by: James Harvey <lothmordor@gmail.com>
Cc: 17.0 <mesa-stable@lists.freedesktop.org>
(cherry picked from commit 76b02d2fe1df5351f67f53d07b37952043f0a84c)

diff --git a/src/gallium/drivers/r600/r600_shader.c b/src/gallium/drivers/r600/r600_shader.c
index ebe2744..7d1452a 100644 (file)
--- a/src/gallium/drivers/r600/r600_shader.c
+++ b/src/gallium/drivers/r600/r600_shader.c
@@ -4326,25 +4326,27 @@ static int cayman_mul_double_instr(struct r600_shader_ctx *ctx)
        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++) {