i965/vec4: Skip swizzle to subnr in 3src instructions with DF operands

We make scalar sources in 3src instructions use subnr instead of
swizzles because they don't really use swizzles.

With doubles it is more complicated because we use vstride=0 in
more scenarios in which they don't produce scalar regions. Also
RepCtrl=1 is not allowed with 64-bit operands, so we should avoid
this.

v2: Fix typo (Matt)

Reviewed-by: Matt Turner <mattst88@gmail.com>

diff --git a/src/mesa/drivers/dri/i965/brw_vec4.cpp b/src/mesa/drivers/dri/i965/brw_vec4.cpp
index 1d65b9905d0f087f5a6b68f78c8f478210484ce6..040ef0107e755e7415d282945d6fb74aad9884e4 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_vec4.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4.cpp
@@ -1962,9 +1962,12 @@ vec4_visitor::convert_to_hw_regs()
       if (inst->is_3src(devinfo)) {
          /* 3-src instructions with scalar sources support arbitrary subnr,
           * but don't actually use swizzles.  Convert swizzle into subnr.
+          * Skip this for double-precision instructions: RepCtrl=1 is not
+          * allowed for them and needs special handling.
           */
          for (int i = 0; i < 3; i++) {
-            if (inst->src[i].vstride == BRW_VERTICAL_STRIDE_0) {
+            if (inst->src[i].vstride == BRW_VERTICAL_STRIDE_0 &&
+                type_sz(inst->src[i].type) < 8) {
                assert(brw_is_single_value_swizzle(inst->src[i].swizzle));
                inst->src[i].subnr += 4 * BRW_GET_SWZ(inst->src[i].swizzle, 0);
             }