[Mesa-dev] [PATCH] i965/fs: Reimplement nir_op_uadd_carry and _usub_borrow without accumulator.

[Francisco Jerez]

This gets rid of two no16() fall-backs and should allow better
scheduling of the generated IR.  There are no uses of usubBorrow() or
uaddCarry() in shader-db so no changes are expected.  However the
"arb_gpu_shader5/execution/built-in-functions/fs-usubBorrow" and
"arb_gpu_shader5/execution/built-in-functions/fs-uaddCarry" piglit
tests go from 40 to 28 instructions.  The reason is that the plain ADD
instruction can easily be CSE'ed with the original addition, and the
negation can easily be propagated into the source modifier of another
instruction, so effectively both operations can be performed with just
one instruction.

No piglit regressions.
---
 src/mesa/drivers/dri/i965/brw_fs_nir.cpp | 33 +++++++++++++-------------------
 1 file changed, 13 insertions(+), 20 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
index 6d9e9d3..3b6aa0a 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
@@ -829,29 +829,22 @@ fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr)
       bld.emit(SHADER_OPCODE_INT_QUOTIENT, result, op[0], op[1]);
       break;
 
-   case nir_op_uadd_carry: {
-      if (devinfo->gen >= 7)
-         no16("SIMD16 explicit accumulator operands unsupported\n");
-
-      struct brw_reg acc = retype(brw_acc_reg(dispatch_width),
-                                  BRW_REGISTER_TYPE_UD);
-
-      bld.ADDC(bld.null_reg_ud(), op[0], op[1]);
-      bld.MOV(result, fs_reg(acc));
+   case nir_op_uadd_carry:
+      /* Use signed operands for the ADD to be easily CSE'ed with the original
+       * addition (e.g. in case we're implementing the uaddCarry() GLSL
+       * built-in).
+       */
+      bld.ADD(result, retype(op[0], BRW_REGISTER_TYPE_D),
+              retype(op[1], BRW_REGISTER_TYPE_D));
+      bld.CMP(result, retype(result, BRW_REGISTER_TYPE_UD), op[0],
+              BRW_CONDITIONAL_L);
+      bld.MOV(result, negate(result));
       break;
-   }
 
-   case nir_op_usub_borrow: {
-      if (devinfo->gen >= 7)
-         no16("SIMD16 explicit accumulator operands unsupported\n");
-
-      struct brw_reg acc = retype(brw_acc_reg(dispatch_width),
-                                  BRW_REGISTER_TYPE_UD);
-
-      bld.SUBB(bld.null_reg_ud(), op[0], op[1]);
-      bld.MOV(result, fs_reg(acc));
+   case nir_op_usub_borrow:
+      bld.CMP(result, op[0], op[1], BRW_CONDITIONAL_L);
+      bld.MOV(result, negate(result));
       break;
-   }
 
    case nir_op_umod:
       bld.emit(SHADER_OPCODE_INT_REMAINDER, result, op[0], op[1]);
-- 
2.4.3