From: Jessica Paquette <jpaquette@apple.com>
Date: Tue, 3 Sep 2019 17:21:12 +0000 (+0000)
Subject: [AArch64][GlobalISel] Don't import i64imm_32bit pattern at -O0
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=3487d71788c15668bd4cc9f9c56c286c6b6eabb3;p=llvm

[AArch64][GlobalISel] Don't import i64imm_32bit pattern at -O0

This pattern, when imported at -O0 adds an extra copy via the SUBREG_TO_REG.

This is because the SUBREG_TO_REG is not eliminated. At all other opt levels,
it is eliminated.

This is a 1% geomean code size savings at -O0 on CTMark.

Differential Revision: https://reviews.llvm.org/D67027

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370789 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Target/AArch64/AArch64InstrInfo.td b/lib/Target/AArch64/AArch64InstrInfo.td
index 5128fc6bd1d..7123ba043c3 100644
--- a/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/lib/Target/AArch64/AArch64InstrInfo.td
@@ -437,6 +437,13 @@ let RecomputePerFunction = 1 in {
 
   def UseBTI : Predicate<[{ MF->getFunction().hasFnAttribute("branch-target-enforcement") }]>;
   def NotUseBTI : Predicate<[{ !MF->getFunction().hasFnAttribute("branch-target-enforcement") }]>;
+
+  // Toggles patterns which aren't beneficial in GlobalISel when we aren't
+  // optimizing. This allows us to selectively use patterns without impacting
+  // SelectionDAG's behaviour.
+  // FIXME: One day there will probably be a nicer way to check for this, but
+  // today is not that day.
+  def OptimizedGISelOrOtherSelector : Predicate<"!MF->getFunction().hasOptNone() || MF->getProperties().hasProperty(MachineFunctionProperties::Property::FailedISel) || !MF->getProperties().hasProperty(MachineFunctionProperties::Property::Legalized)">;
 }
 
 include "AArch64InstrFormats.td"
@@ -940,8 +947,12 @@ def trunc_imm : SDNodeXForm<imm, [{
 def gi_trunc_imm : GICustomOperandRenderer<"renderTruncImm">,
   GISDNodeXFormEquiv<trunc_imm>;
 
+let Predicates = [OptimizedGISelOrOtherSelector] in {
+// The SUBREG_TO_REG isn't eliminated at -O0, which can result in pointless
+// copies.
 def : Pat<(i64 i64imm_32bit:$src),
           (SUBREG_TO_REG (i64 0), (MOVi32imm (trunc_imm imm:$src)), sub_32)>;
+}
 
 // Materialize FP constants via MOVi32imm/MOVi64imm (MachO large code model).
 def bitcast_fpimm_to_i32 : SDNodeXForm<fpimm, [{
diff --git a/test/CodeGen/AArch64/GlobalISel/select-constant.mir b/test/CodeGen/AArch64/GlobalISel/select-constant.mir
index 2b9d51924d3..822ba251bc5 100644
--- a/test/CodeGen/AArch64/GlobalISel/select-constant.mir
+++ b/test/CodeGen/AArch64/GlobalISel/select-constant.mir
@@ -13,6 +13,9 @@
   define i64 @fconst_s64() { ret i64 1234567890123 }
   define float @fconst_s32_0() { ret float 0.0 }
   define double @fconst_s64_0() { ret double 0.0 }
+
+  define void @optnone_i64() optnone noinline { ret void }
+  define void @opt_i64() { ret void }
 ...
 
 ---
@@ -140,3 +143,32 @@ body:             |
     %0(s64) = G_FCONSTANT double 0.0
     $x0 = COPY %0(s64)
 ...
+---
+name:            optnone_i64
+legalized:       true
+regBankSelected: true
+body: |
+  bb.0:
+    ; CHECK-LABEL: name: optnone_i64
+    ; CHECK: [[MOVi64imm:%[0-9]+]]:gpr64 = MOVi64imm 42
+    ; CHECK: $x0 = COPY [[MOVi64imm]]
+    ; CHECK: RET_ReallyLR implicit $x0
+    %0:gpr(s64) = G_CONSTANT i64 42
+    $x0 = COPY %0(s64)
+    RET_ReallyLR implicit $x0
+...
+---
+name:            opt_i64
+legalized:       true
+regBankSelected: true
+body: |
+  bb.0:
+    ; CHECK-LABEL: name: opt_i64
+    ; CHECK: [[MOVi32imm:%[0-9]+]]:gpr32 = MOVi32imm 42
+    ; CHECK: [[SUBREG_TO_REG:%[0-9]+]]:gpr64all = SUBREG_TO_REG 0, [[MOVi32imm]], %subreg.sub_32
+    ; CHECK: $x0 = COPY [[SUBREG_TO_REG]]
+    ; CHECK: RET_ReallyLR implicit $x0
+    %0:gpr(s64) = G_CONSTANT i64 42
+    $x0 = COPY %0(s64)
+    RET_ReallyLR implicit $x0
+...