[Mesa-dev] [PATCH 26/36] i965/fs: Handle nir shared variable store intrinsic function

[Jordan Justen]

Signed-off-by: Jordan Justen <jordan.l.justen at intel.com>
---

Notes:
    I have ported this commit to shared variable stores:
    
    commit 0cb7d7b4b7c32246d4c4225a1d17d7ff79a7526d
    Author: Kristian Høgsberg Kristensen <krh at bitplanet.net>
    Date:   Wed Oct 21 23:43:34 2015 -0700
    
        i965/fs: Optimize ssbo stores
    
    It is not included because it regresses
    ES31-CTS.compute_shader.shared-max.

 src/mesa/drivers/dri/i965/brw_fs_nir.cpp | 54 ++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
index e9336fd..c8c6370 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
@@ -2330,6 +2330,60 @@ fs_visitor::nir_emit_intrinsic(const fs_builder &bld, nir_intrinsic_instr *instr
       break;
    }
 
+   case nir_intrinsic_store_shared_indirect:
+      has_indirect = true;
+      /* fallthrough */
+   case nir_intrinsic_store_shared: {
+      assert(devinfo->gen >= 7);
+
+      /* Block index */
+      fs_reg surf_index;
+      unsigned index = BRW_SLM_SURFACE_INDEX;
+      surf_index = fs_reg(index);
+
+      /* Offset */
+      fs_reg offset_reg = vgrf(glsl_type::uint_type);
+      unsigned const_offset_bytes = 0;
+      if (has_indirect) {
+         bld.MOV(offset_reg, get_nir_src(instr->src[1]));
+      } else {
+         const_offset_bytes = instr->const_index[0];
+         bld.MOV(offset_reg, fs_reg(const_offset_bytes));
+      }
+
+      /* Value */
+      fs_reg val_reg = get_nir_src(instr->src[0]);
+
+      /* Writemask */
+      unsigned writemask = instr->const_index[1];
+
+      /* Write each component present in the writemask */
+      unsigned skipped_channels = 0;
+      for (int i = 0; i < instr->num_components; i++) {
+         int component_mask = 1 << i;
+         if (writemask & component_mask) {
+            if (skipped_channels) {
+               if (!has_indirect) {
+                  const_offset_bytes += 4 * skipped_channels;
+                  bld.MOV(offset_reg, fs_reg(const_offset_bytes));
+               } else {
+                  bld.ADD(offset_reg, offset_reg,
+                           brw_imm_ud(4 * skipped_channels));
+               }
+               skipped_channels = 0;
+            }
+
+            emit_untyped_write(bld, surf_index, offset_reg,
+                               offset(val_reg, bld, i),
+                               1 /* dims */, 1 /* size */,
+                               BRW_PREDICATE_NONE);
+         }
+
+         skipped_channels++;
+      }
+      break;
+   }
+
    case nir_intrinsic_load_input_indirect:
       has_indirect = true;
       /* fallthrough */
-- 
2.6.2