[Mesa-dev] [PATCH 3/3] i965/fs: Optimize float conversions of byte/word extract.

[Matt Turner]

   instructions in affected programs: 31535 -> 29966 (-4.98%)
   helped: 23

   cycles in affected programs: 272648 -> 266022 (-2.43%)
   helped: 14
   HURT: 1

The patch decreases the number of instructions in the two Unigine
programs by:

 #1721: 4374 -> 4155 instructions (-5.01%)
 #1706: 3582 -> 3363 instructions (-6.11%)
---
 src/mesa/drivers/dri/i965/brw_fs.h       |  2 ++
 src/mesa/drivers/dri/i965/brw_fs_nir.cpp | 46 ++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+)

diff --git a/src/mesa/drivers/dri/i965/brw_fs.h b/src/mesa/drivers/dri/i965/brw_fs.h
index 7446ca1..21c7813 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.h
+++ b/src/mesa/drivers/dri/i965/brw_fs.h
@@ -272,6 +272,8 @@ public:
    void emit_percomp(const brw::fs_builder &bld, const fs_inst &inst,
                      unsigned wr_mask);
 
+   bool optimize_extract_to_float(nir_alu_instr *instr,
+                                  const fs_reg &result);
    bool optimize_frontfacing_ternary(nir_alu_instr *instr,
                                      const fs_reg &result);
 
diff --git a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
index db20c71..04e9b8f 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
@@ -500,6 +500,49 @@ fs_visitor::nir_emit_instr(nir_instr *instr)
    }
 }
 
+/**
+ * Recognizes a parent instruction of nir_op_extract_* and changes the type to
+ * match instr.
+ */
+bool
+fs_visitor::optimize_extract_to_float(nir_alu_instr *instr,
+                                      const fs_reg &result)
+{
+   if (!instr->src[0].src.is_ssa ||
+       !instr->src[0].src.ssa->parent_instr)
+      return false;
+
+   if (instr->src[0].src.ssa->parent_instr->type != nir_instr_type_alu)
+      return false;
+
+   nir_alu_instr *src0 =
+      nir_instr_as_alu(instr->src[0].src.ssa->parent_instr);
+
+   if (src0->op != nir_op_extract_u8 && src0->op != nir_op_extract_u16 &&
+       src0->op != nir_op_extract_i8 && src0->op != nir_op_extract_i16)
+      return false;
+
+   nir_const_value *element = nir_src_as_const_value(src0->src[1].src);
+   assert(element != NULL);
+
+   enum opcode extract_op;
+   if (src0->op == nir_op_extract_u16 || src0->op == nir_op_extract_i16) {
+      assert(element->u[0] <= 1);
+      extract_op = SHADER_OPCODE_EXTRACT_WORD;
+   } else {
+      assert(element->u[0] <= 3);
+      extract_op = SHADER_OPCODE_EXTRACT_BYTE;
+   }
+
+   fs_reg op0 = get_nir_src(src0->src[0].src);
+   op0.type = brw_type_for_nir_type(nir_op_infos[src0->op].input_types[0]);
+   op0 = offset(op0, bld, src0->src[0].swizzle[0]);
+
+   set_saturate(instr->dest.saturate,
+                bld.emit(extract_op, result, op0, brw_imm_ud(element->u[0])));
+   return true;
+}
+
 bool
 fs_visitor::optimize_frontfacing_ternary(nir_alu_instr *instr,
                                          const fs_reg &result)
@@ -671,6 +714,9 @@ fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr)
    switch (instr->op) {
    case nir_op_i2f:
    case nir_op_u2f:
+      if (optimize_extract_to_float(instr, result))
+         return;
+
       inst = bld.MOV(result, op[0]);
       inst->saturate = instr->dest.saturate;
       break;
-- 
2.4.10