i965/compiler: handle conversion to smaller type in the lowering pass for that

[mesa.git] / src / intel / compiler / brw_fs_lower_conversions.cpp

diff --git a/src/intel/compiler/brw_fs_lower_conversions.cpp b/src/intel/compiler/brw_fs_lower_conversions.cpp
index 663c9674c494dd45500dc6504ae8e53f0fa7a19e..e27e2402746e1d21a1c7470dc32e917bc209c7f8 100644 (file)
--- a/src/intel/compiler/brw_fs_lower_conversions.cpp
+++ b/src/intel/compiler/brw_fs_lower_conversions.cpp
@@ -43,6 +43,24 @@ supports_type_conversion(const fs_inst *inst) {
    }
 }
 
+/* From the SKL PRM Vol 2a, "Move":
+ *
+ *    "A mov with the same source and destination type, no source modifier,
+ *     and no saturation is a raw move. A packed byte destination region (B
+ *     or UB type with HorzStride == 1 and ExecSize > 1) can only be written
+ *     using raw move."
+ */
+static bool
+is_byte_raw_mov (const fs_inst *inst)
+{
+   return type_sz(inst->dst.type) == 1 &&
+          inst->opcode == BRW_OPCODE_MOV &&
+          inst->src[0].type == inst->dst.type &&
+          !inst->saturate &&
+          !inst->src[0].negate &&
+          !inst->src[0].abs;
+}
+
 bool
 fs_visitor::lower_conversions()
 {
@@ -54,7 +72,8 @@ fs_visitor::lower_conversions()
       bool saturate = inst->saturate;
 
       if (supports_type_conversion(inst)) {
-         if (get_exec_type_size(inst) == 8 && type_sz(inst->dst.type) < 8) {
+         if (type_sz(inst->dst.type) < get_exec_type_size(inst) &&
+             !is_byte_raw_mov(inst)) {
             /* From the Broadwell PRM, 3D Media GPGPU, "Double Precision Float to
              * Single Precision Float":
              *
@@ -64,6 +83,9 @@ fs_visitor::lower_conversions()
              * So we need to allocate a temporary that's two registers, and then do
              * a strided MOV to get the lower DWord of every Qword that has the
              * result.
+             *
+             * This restriction applies, in general, whenever we convert to
+             * a type with a smaller bit-size.
              */
             fs_reg temp = ibld.vgrf(get_exec_type(inst));
             fs_reg strided_temp = subscript(temp, dst.type, 0);