[llvm] r284983 - [PPC] Better codegen for AND, ANY_EXT, SRL sequence

[Ehsan Amiri via llvm-commits]

Author: amehsan
Date: Mon Oct 24 10:46:58 2016
New Revision: 284983

URL: http://llvm.org/viewvc/llvm-project?rev=284983&view=rev
Log:
[PPC] Better codegen for AND, ANY_EXT, SRL sequence

https://reviews.llvm.org/D24924

This improves the code generated for a sequence of AND, ANY_EXT, SRL instructions. This is a targetted fix for this special pattern. The pattern is generated by target independet dag combiner and so a more general fix may not be necessary. If we come across other similar cases, some ideas for handling it are discussed on the code review.

Added:
    llvm/trunk/test/CodeGen/PowerPC/anyext_srl.ll
Modified:
    llvm/trunk/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
    llvm/trunk/lib/Target/PowerPC/README.txt

Modified: llvm/trunk/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/PowerPC/PPCISelDAGToDAG.cpp?rev=284983&r1=284982&r2=284983&view=diff
==============================================================================
--- llvm/trunk/lib/Target/PowerPC/PPCISelDAGToDAG.cpp (original)
+++ llvm/trunk/lib/Target/PowerPC/PPCISelDAGToDAG.cpp Mon Oct 24 10:46:58 2016
@@ -2657,6 +2657,23 @@ void PPCDAGToDAGISel::Select(SDNode *N)
       MB = 64 - countTrailingOnes(Imm64);
       SH = 0;
 
+      if (Val.getOpcode() == ISD::ANY_EXTEND) {
+        auto Op0 = Val.getOperand(0);
+        if ( Op0.getOpcode() == ISD::SRL &&
+           isInt32Immediate(Op0.getOperand(1).getNode(), Imm) && Imm <= MB) {
+
+           auto ResultType = Val.getNode()->getValueType(0);
+           auto ImDef = CurDAG->getMachineNode(PPC::IMPLICIT_DEF, dl,
+                                               ResultType);
+           SDValue IDVal (ImDef, 0);
+
+           Val = SDValue(CurDAG->getMachineNode(PPC::INSERT_SUBREG, dl,
+                         ResultType, IDVal, Op0.getOperand(0),
+                         getI32Imm(1, dl)), 0);
+           SH = 64 - Imm;
+        }
+      }
+
       // If the operand is a logical right shift, we can fold it into this
       // instruction: rldicl(rldicl(x, 64-n, n), 0, mb) -> rldicl(x, 64-n, mb)
       // for n <= mb. The right shift is really a left rotate followed by a

Modified: llvm/trunk/lib/Target/PowerPC/README.txt
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/PowerPC/README.txt?rev=284983&r1=284982&r2=284983&view=diff
==============================================================================
--- llvm/trunk/lib/Target/PowerPC/README.txt (original)
+++ llvm/trunk/lib/Target/PowerPC/README.txt Mon Oct 24 10:46:58 2016
@@ -658,3 +658,9 @@ Instruction fusion was introduced in ISA
 ISA 2.07.  LLVM needs to add infrastructure to recognize fusion opportunities
 and force instruction pairs to be scheduled together.
 
+-----------------------------------------------------------------------------
+
+More general handling of any_extend and zero_extend:
+
+See https://reviews.llvm.org/D24924#555306
+

Added: llvm/trunk/test/CodeGen/PowerPC/anyext_srl.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/PowerPC/anyext_srl.ll?rev=284983&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/PowerPC/anyext_srl.ll (added)
+++ llvm/trunk/test/CodeGen/PowerPC/anyext_srl.ll Mon Oct 24 10:46:58 2016
@@ -0,0 +1,29 @@
+; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
+; RUN:     -mcpu=pwr8 < %s | FileCheck %s
+
+%class.PB2 = type { [1 x i32], %class.PB1* }
+%class.PB1 = type { [1 x i32], i64, i64, i32 }
+
+; Function Attrs: norecurse nounwind readonly
+define zeroext i1 @foo(%class.PB2* %s_a, %class.PB2* %s_b) local_unnamed_addr {
+entry:
+  %arrayidx.i6 = bitcast %class.PB2* %s_a to i32*
+  %0 = load i32, i32* %arrayidx.i6, align 8, !tbaa !1
+  %and.i = and i32 %0, 8
+  %cmp.i = icmp ne i32 %and.i, 0
+  %arrayidx.i37 = bitcast %class.PB2* %s_b to i32*
+  %1 = load i32, i32* %arrayidx.i37, align 8, !tbaa !1
+  %and.i4 = and i32 %1, 8
+  %cmp.i5 = icmp ne i32 %and.i4, 0
+  %cmp = xor i1 %cmp.i, %cmp.i5
+  ret i1 %cmp
+; CHECK-LABEL: @foo
+; CHECK: rldicl  {{[0-9]+}}, {{[0-9]+}}, 61, 63
+
+}
+
+!1 = !{!2, !2, i64 0}
+!2 = !{!"int", !3, i64 0}
+!3 = !{!"omnipotent char", !4, i64 0}
+!4 = !{!"Simple C++ TBAA"}
+