i965/vec4: select predicate based on writemask for sel emissions

Equivalent to commit 8ac3b525c but with sel operations. In this case
we select the PredCtrl based on the writemask.

This patch helps on cases like this:
 1: cmp.l.f0.0 vgrf40.0.x:F, vgrf0.zzzz:F, vgrf7.xxxx:F
 2: cmp.nz.f0.0 null:D, vgrf40.xxxx:D, 0D
 3: (+f0.0) sel vgrf41.0.x:UD, vgrf6.xxxx:UD, vgrf5.xxxx:UD

In this case, cmod propagation can't optimize instruction #2, because
instructions #1 and #2 have different writemasks, and we can't update
directly instruction #2 writemask because our code thinks that sel at
instruction #3 reads all four channels of the flag, when it actually
only reads .x.

So, with this patch, the previous case becames this:
 1: cmp.l.f0.0 vgrf40.0.x:F, vgrf0.zzzz:F, vgrf7.xxxx:F
 2: cmp.nz.f0.0 null:D, vgrf40.xxxx:D, 0D
 3: (+f0.0.x) sel vgrf41.0.x:UD, vgrf6.xxxx:UD, vgrf5.xxxx:UD

Now only the x channel of the flag is used, allowing dead code
eliminate to update the writemask at the second instruction:
 1: cmp.l.f0.0 vgrf40.0.x:F, vgrf0.zzzz:F, vgrf7.xxxx:F
 2: cmp.nz.f0.0 null.x:D, vgrf40.xxxx:D, 0D
 3: (+f0.0.x) sel vgrf41.0.x:UD, vgrf6.xxxx:UD, vgrf5.xxxx:UD

So now cmod propagation can simplify out #2:
 1: cmp.l.f0.0 vgrf40.0.x:F, attr18.wwww:F, vgrf7.xxxx:F
 2: (+f0.0.x) sel vgrf41.0.x:UD, vgrf6.xxxx:UD, vgrf5.xxxx:UD

Shader-db numbers:
total instructions in shared programs: 6235835 -> 6228008 (-0.13%)
instructions in affected programs:     219850 -> 212023 (-3.56%)
total loops in shared programs:        1979 -> 1979 (0.00%)
helped:                                1192
HURT:                                  0

diff --git a/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp b/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp
index 8ca8ddb98fb2eaf3ab35b17e136f79e8f376c31b..b848810ebc7c6e37a16b9c6eb6510c12918552b9 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp
@@ -1407,7 +1407,23 @@ vec4_visitor::nir_emit_alu(nir_alu_instr *instr)
    case nir_op_bcsel:
       emit(CMP(dst_null_d(), op[0], src_reg(0), BRW_CONDITIONAL_NZ));
       inst = emit(BRW_OPCODE_SEL, dst, op[1], op[2]);
-      inst->predicate = BRW_PREDICATE_NORMAL;
+      switch (dst.writemask) {
+      case WRITEMASK_X:
+         inst->predicate = BRW_PREDICATE_ALIGN16_REPLICATE_X;
+         break;
+      case WRITEMASK_Y:
+         inst->predicate = BRW_PREDICATE_ALIGN16_REPLICATE_Y;
+         break;
+      case WRITEMASK_Z:
+         inst->predicate = BRW_PREDICATE_ALIGN16_REPLICATE_Z;
+         break;
+      case WRITEMASK_W:
+         inst->predicate = BRW_PREDICATE_ALIGN16_REPLICATE_W;
+         break;
+      default:
+         inst->predicate = BRW_PREDICATE_NORMAL;
+         break;
+      }
       break;
 
    case nir_op_fdot_replicated2: