[Mesa-dev] [PATCH 25/45] i965/fs: Support push constants of 16-bit types

[Alejandro Piñeiro]

From: Jose Maria Casanova Crespo <jmcasanova at igalia.com>

We enable the use of 16-bit values in push constants
modifying the assign_constant_locations function to work
with 16-bit types.

The API to access buffers in Vulkan use multiples of 4-byte for
offsets and sizes. Current accountability of uniforms based on 4-byte
slots will work for 16-bit values if they are allowed to use 32-bit
slots. For that, we replace the division by 4 by a DIV_ROUND_UP, so
2-byte elements will use 1 slot instead of 0.

We aligns the 16-bit locations after assigning the 32-bit
ones.
---
 src/intel/compiler/brw_fs.cpp | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/src/intel/compiler/brw_fs.cpp b/src/intel/compiler/brw_fs.cpp
index 08c1a8d..3bead1f 100644
--- a/src/intel/compiler/brw_fs.cpp
+++ b/src/intel/compiler/brw_fs.cpp
@@ -1879,8 +1879,9 @@ set_push_pull_constant_loc(unsigned uniform, int *chunk_start,
    if (!contiguous) {
       /* If bitsize doesn't match the target one, skip it */
       if (*max_chunk_bitsize != target_bitsize) {
-         /* FIXME: right now we only support 32 and 64-bit accesses */
-         assert(*max_chunk_bitsize == 4 || *max_chunk_bitsize == 8);
+         assert(*max_chunk_bitsize == 4 ||
+                *max_chunk_bitsize == 8 ||
+                *max_chunk_bitsize == 2);
          *max_chunk_bitsize = 0;
          *chunk_start = -1;
          return;
@@ -1957,8 +1958,9 @@ fs_visitor::assign_constant_locations()
          int constant_nr = inst->src[i].nr + inst->src[i].offset / 4;
 
          if (inst->opcode == SHADER_OPCODE_MOV_INDIRECT && i == 0) {
-            assert(inst->src[2].ud % 4 == 0);
-            unsigned last = constant_nr + (inst->src[2].ud / 4) - 1;
+            assert(type_sz(inst->src[i].type) == 2 ?
+                   (inst->src[2].ud % 2 == 0) : (inst->src[2].ud % 4 == 0));
+            unsigned last = constant_nr + DIV_ROUND_UP(inst->src[2].ud, 4) - 1;
             assert(last < uniforms);
 
             for (unsigned j = constant_nr; j < last; j++) {
@@ -1970,8 +1972,8 @@ fs_visitor::assign_constant_locations()
             bitsize_access[last] = MAX2(bitsize_access[last], type_sz(inst->src[i].type));
          } else {
             if (constant_nr >= 0 && constant_nr < (int) uniforms) {
-               int regs_read = inst->components_read(i) *
-                  type_sz(inst->src[i].type) / 4;
+               int regs_read = DIV_ROUND_UP(inst->components_read(i) *
+                                            type_sz(inst->src[i].type), 4);
                for (int j = 0; j < regs_read; j++) {
                   is_live[constant_nr + j] = true;
                   bitsize_access[constant_nr + j] =
@@ -2032,7 +2034,7 @@ fs_visitor::assign_constant_locations()
 
    }
 
-   /* Then push the rest of uniforms */
+   /* Then push the 32-bit uniforms */
    const unsigned uniform_32_bit_size = type_sz(BRW_REGISTER_TYPE_F);
    for (unsigned u = 0; u < uniforms; u++) {
       if (!is_live[u])
@@ -2051,6 +2053,20 @@ fs_visitor::assign_constant_locations()
                                  stage_prog_data);
    }
 
+   const unsigned uniform_16_bit_size = type_sz(BRW_REGISTER_TYPE_HF);
+   for (unsigned u = 0; u < uniforms; u++) {
+      if (!is_live[u])
+         continue;
+
+      set_push_pull_constant_loc(u, &chunk_start, &max_chunk_bitsize,
+                                 contiguous[u], bitsize_access[u],
+                                 uniform_16_bit_size,
+                                 push_constant_loc, pull_constant_loc,
+                                 &num_push_constants, &num_pull_constants,
+                                 max_push_components, max_chunk_size,
+                                 stage_prog_data);
+   }
+
    /* Add the CS local thread ID uniform at the end of the push constants */
    if (thread_local_id_index >= 0)
       push_constant_loc[thread_local_id_index] = num_push_constants++;
-- 
2.9.3