[Mesa-dev] [PATCH 10.5/41] SQUASH: i965/fs: Properly set writemasks in LOAD_PAYLOAD

[Jason Ekstrand]

---
 src/mesa/drivers/dri/i965/brw_fs.cpp | 56 +++++++++++++++++++++++++++++++++++-
 1 file changed, 55 insertions(+), 1 deletion(-)

diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index 444cc32..4d97594 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -2865,10 +2865,44 @@ fs_visitor::lower_load_payload()
 {
    bool progress = false;
 
+   int vgrf_to_reg[virtual_grf_count];
+   int reg_count = 16; /* Leave room for MRF */
+   for (int i = 0; i < virtual_grf_count; ++i) {
+      vgrf_to_reg[i] = reg_count;
+      reg_count += virtual_grf_sizes[i];
+   }
+
+   struct {
+      bool written:1; /* Whether this register has ever been written */
+      bool force_writemask_all:1;
+      bool force_sechalf:1;
+   } metadata[reg_count];
+   memset(metadata, 0, sizeof(metadata));
+
    calculate_cfg();
 
    foreach_block_and_inst_safe (block, fs_inst, inst, cfg) {
+      int dst_reg;
+      if (inst->dst.file == MRF) {
+         dst_reg = inst->dst.reg;
+      } else if (inst->dst.file == GRF) {
+         dst_reg = vgrf_to_reg[inst->dst.reg];
+      }
+
+      if (inst->dst.file == MRF || inst->dst.file == GRF) {
+         bool force_sechalf = inst->force_sechalf;
+         bool toggle_sechalf = inst->dst.width == 16 &&
+                               type_sz(inst->dst.type) == 4;
+         for (int i = 0; i < inst->regs_written; ++i) {
+            metadata[dst_reg + i].written = true;
+            metadata[dst_reg + i].force_sechalf = force_sechalf;
+            metadata[dst_reg + i].force_writemask_all = inst->force_writemask_all;
+            force_sechalf = (toggle_sechalf != force_sechalf);
+         }
+      }
+
       if (inst->opcode == SHADER_OPCODE_LOAD_PAYLOAD) {
+         assert(inst->dst.file == MRF || inst->dst.file == GRF);
          fs_reg dst = inst->dst;
 
          for (int i = 0; i < inst->sources; i++) {
@@ -2879,7 +2913,27 @@ fs_visitor::lower_load_payload()
                /* Do nothing but otherwise increment as normal */
             } else {
                fs_inst *mov = MOV(dst, inst->src[i]);
-               mov->force_writemask_all = true;
+               if (inst->src[i].file == GRF) {
+                  int src_reg = vgrf_to_reg[inst->src[i].reg] +
+                                inst->src[i].reg_offset;
+                  mov->force_sechalf = metadata[src_reg].force_sechalf;
+                  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];
+                  }
+               } else {
+                  metadata[dst_reg].force_writemask_all = false;
+                  metadata[dst_reg].force_sechalf = false;
+                  if (dst.width == 16) {
+                     metadata[dst_reg + 1].force_writemask_all = false;
+                     metadata[dst_reg + 1].force_sechalf = true;
+                  }
+               }
                inst->insert_before(block, mov);
             }
 
-- 
2.1.0