[Mesa-dev] [PATCH 4/6] tgsi/scan: take advantage of already swizzled usage mask in scan_src_operand

[Marek Olšák]

From: Marek Olšák <marek.olsak at amd.com>

It has always been a usage mask *after* swizzling.
---
 src/gallium/auxiliary/tgsi/tgsi_scan.c | 47 ++++++++++++----------------------
 1 file changed, 17 insertions(+), 30 deletions(-)

diff --git a/src/gallium/auxiliary/tgsi/tgsi_scan.c b/src/gallium/auxiliary/tgsi/tgsi_scan.c
index 6f87f8d..ee9a261 100644
--- a/src/gallium/auxiliary/tgsi/tgsi_scan.c
+++ b/src/gallium/auxiliary/tgsi/tgsi_scan.c
@@ -100,98 +100,85 @@ computes_derivative(unsigned opcode)
           opcode == TGSI_OPCODE_SAMPLE_B ||
           opcode == TGSI_OPCODE_SAMPLE_C;
 }
 
 
 static void
 scan_src_operand(struct tgsi_shader_info *info,
                  const struct tgsi_full_instruction *fullinst,
                  const struct tgsi_full_src_register *src,
                  unsigned src_index,
-                 unsigned usage_mask,
+                 unsigned usage_mask_after_swizzle,
                  bool is_interp_instruction,
                  bool *is_mem_inst)
 {
    int ind = src->Register.Index;
 
    if (info->processor == PIPE_SHADER_COMPUTE &&
        src->Register.File == TGSI_FILE_SYSTEM_VALUE) {
-      unsigned swizzle[4], i, name;
+      unsigned name, mask;
 
       name = info->system_value_semantic_name[src->Register.Index];
-      swizzle[0] = src->Register.SwizzleX;
-      swizzle[1] = src->Register.SwizzleY;
-      swizzle[2] = src->Register.SwizzleZ;
-      swizzle[3] = src->Register.SwizzleW;
 
       switch (name) {
       case TGSI_SEMANTIC_THREAD_ID:
       case TGSI_SEMANTIC_BLOCK_ID:
-         for (i = 0; i < 4; i++) {
-            if (swizzle[i] <= TGSI_SWIZZLE_Z) {
-               if (name == TGSI_SEMANTIC_THREAD_ID)
-                  info->uses_thread_id[swizzle[i]] = true;
-               else
-                  info->uses_block_id[swizzle[i]] = true;
-            }
+         mask = usage_mask_after_swizzle & TGSI_WRITEMASK_XYZ;
+         while (mask) {
+            unsigned i = u_bit_scan(&mask);
+
+            if (name == TGSI_SEMANTIC_THREAD_ID)
+               info->uses_thread_id[i] = true;
+            else
+               info->uses_block_id[i] = true;
          }
          break;
       case TGSI_SEMANTIC_BLOCK_SIZE:
          /* The block size is translated to IMM with a fixed block size. */
          if (info->properties[TGSI_PROPERTY_CS_FIXED_BLOCK_WIDTH] == 0)
             info->uses_block_size = true;
          break;
       case TGSI_SEMANTIC_GRID_SIZE:
          info->uses_grid_size = true;
          break;
       }
    }
 
    /* Mark which inputs are effectively used */
    if (src->Register.File == TGSI_FILE_INPUT) {
       if (src->Register.Indirect) {
          for (ind = 0; ind < info->num_inputs; ++ind) {
-            info->input_usage_mask[ind] |= usage_mask;
+            info->input_usage_mask[ind] |= usage_mask_after_swizzle;
          }
       } else {
          assert(ind >= 0);
          assert(ind < PIPE_MAX_SHADER_INPUTS);
-         info->input_usage_mask[ind] |= usage_mask;
+         info->input_usage_mask[ind] |= usage_mask_after_swizzle;
       }
 
       if (info->processor == PIPE_SHADER_FRAGMENT) {
          unsigned name, index, input;
 
          if (src->Register.Indirect && src->Indirect.ArrayID)
             input = info->input_array_first[src->Indirect.ArrayID];
          else
             input = src->Register.Index;
 
          name = info->input_semantic_name[input];
          index = info->input_semantic_index[input];
 
          if (name == TGSI_SEMANTIC_POSITION &&
-             (src->Register.SwizzleX == TGSI_SWIZZLE_Z ||
-              src->Register.SwizzleY == TGSI_SWIZZLE_Z ||
-              src->Register.SwizzleZ == TGSI_SWIZZLE_Z ||
-              src->Register.SwizzleW == TGSI_SWIZZLE_Z))
-            info->reads_z = TRUE;
-
-         if (name == TGSI_SEMANTIC_COLOR) {
-            unsigned mask =
-               (1 << src->Register.SwizzleX) |
-               (1 << src->Register.SwizzleY) |
-               (1 << src->Register.SwizzleZ) |
-               (1 << src->Register.SwizzleW);
-
-            info->colors_read |= mask << (index * 4);
-         }
+             usage_mask_after_swizzle & TGSI_WRITEMASK_Z)
+            info->reads_z = true;
+
+         if (name == TGSI_SEMANTIC_COLOR)
+            info->colors_read |= usage_mask_after_swizzle << (index * 4);
 
          /* Process only interpolated varyings. Don't include POSITION.
           * Don't include integer varyings, because they are not
           * interpolated. Don't process inputs interpolated by INTERP
           * opcodes. Those are tracked separately.
           */
          if ((!is_interp_instruction || src_index != 0) &&
              (name == TGSI_SEMANTIC_GENERIC ||
               name == TGSI_SEMANTIC_TEXCOORD ||
               name == TGSI_SEMANTIC_COLOR ||
-- 
2.7.4