Mesa (master): i965/fs: Less broken handling of force_writemask_all in lower_load_payload().

[Francisco Jerez]

Module: Mesa
Branch: master
Commit: 8e47f51a5a7aba2bb56e7185988072431444d811
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=8e47f51a5a7aba2bb56e7185988072431444d811

Author: Francisco Jerez <currojerez at riseup.net>
Date:   Sat Jan 17 14:12:34 2015 +0200

i965/fs: Less broken handling of force_writemask_all in lower_load_payload().

It's perfectly fine to read the second half of a register written with
force_writemask_all from a first half MOV instruction or vice versa, and
lower_load_payload shouldn't mark the whole MOV as belonging to the second
half in that case.  Replicate the same metadata to both halves of the
destination when writemasking is disabled.

Reviewed-by: Jason Ekstrand <jason.ekstrand at intel.com>

---

 src/mesa/drivers/dri/i965/brw_fs.cpp |   20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index 9e1676e..62a5639 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -3135,9 +3135,11 @@ fs_visitor::lower_load_payload()
       }
 
       if (inst->dst.file == MRF || inst->dst.file == GRF) {
-         bool force_sechalf = inst->force_sechalf;
+         bool force_sechalf = inst->force_sechalf &&
+                              !inst->force_writemask_all;
          bool toggle_sechalf = inst->dst.width == 16 &&
-                               type_sz(inst->dst.type) == 4;
+                               type_sz(inst->dst.type) == 4 &&
+                               !inst->force_writemask_all;
          for (int i = 0; i < inst->regs_written; ++i) {
             metadata[dst_reg + i].written = true;
             metadata[dst_reg + i].force_sechalf = force_sechalf;
@@ -3180,11 +3182,15 @@ fs_visitor::lower_load_payload()
                   mov->force_writemask_all = metadata[src_reg].force_writemask_all;
                   metadata[dst_reg] = metadata[src_reg];
                   if (dst.width * type_sz(dst.type) > 32) {
-                     assert((!metadata[src_reg].written ||
-                             !metadata[src_reg].force_sechalf) &&
-                            (!metadata[src_reg + 1].written ||
-                             metadata[src_reg + 1].force_sechalf));
-                     metadata[dst_reg + 1] = metadata[src_reg + 1];
+                     if (metadata[src_reg].force_writemask_all) {
+                        metadata[dst_reg + 1] = metadata[src_reg];
+                     } else {
+                        assert((!metadata[src_reg].written ||
+                                !metadata[src_reg].force_sechalf) &&
+                               (!metadata[src_reg + 1].written ||
+                                metadata[src_reg + 1].force_sechalf));
+                        metadata[dst_reg + 1] = metadata[src_reg + 1];
+                     }
                   }
                } else {
                   metadata[dst_reg].force_writemask_all = false;