[PowerPC] Reduce register pressure by not materializing a constant just for use as...

For this example:
float test (int *arr) {
    return arr[2];
}

We currently generate the following code:
  li r4, 8
  lxsiwax f0, r3, r4
  xscvsxdsp f1, f0

With this patch, we will now generate:
  addi r3, r3, 8
  lxsiwax f0, 0, r3
  xscvsxdsp f1, f0

Originally reported in: https://bugs.llvm.org/show_bug.cgi?id=27204
Differential Revision: https://reviews.llvm.org/D35027

llvm-svn: 307553

diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index 4d667cd..56da6db 100644 (file)
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -2239,10 +2239,15 @@ bool PPCTargetLowering::SelectAddressRegRegOnly(SDValue N, SDValue &Base,
   if (SelectAddressRegReg(N, Base, Index, DAG))
     return true;
 
-  // If the operand is an addition, always emit this as [r+r], since this is
-  // better (for code size, and execution, as the memop does the add for free)
-  // than emitting an explicit add.
-  if (N.getOpcode() == ISD::ADD) {
+  // If the address is the result of an add, we will utilize the fact that the
+  // address calculation includes an implicit add.  However, we can reduce
+  // register pressure if we do not materialize a constant just for use as the
+  // index register.  We only get rid of the add if it is not an add of a
+  // value and a 16-bit signed constant and both have a single use.
+  int16_t imm = 0;
+  if (N.getOpcode() == ISD::ADD &&
+      (!isIntS16Immediate(N.getOperand(1), imm) ||
+       !N.getOperand(1).hasOneUse() || !N.getOperand(0).hasOneUse())) {
     Base = N.getOperand(0);
     Index = N.getOperand(1);
     return true;

diff --git a/llvm/test/CodeGen/PowerPC/build-vector-tests.ll b/llvm/test/CodeGen/PowerPC/build-vector-tests.ll
index c42f677..60bec4d 100644 (file)
--- a/llvm/test/CodeGen/PowerPC/build-vector-tests.ll
+++ b/llvm/test/CodeGen/PowerPC/build-vector-tests.ll
@@ -1028,7 +1028,7 @@ entry:
 ; P9LE: vperm
 ; P9LE: blr
 ; P8BE: sldi {{r[0-9]+}}, r4, 2
-; P8BE-DAG: lxvw4x {{v[0-9]+}}, r3,
+; P8BE-DAG: lxvw4x {{v[0-9]+}}, 0, r3
 ; P8BE-DAG: lxvw4x
 ; P8BE: vperm
 ; P8BE: blr
@@ -2187,7 +2187,7 @@ entry:
 ; P9LE: vperm
 ; P9LE: blr
 ; P8BE-DAG: sldi {{r[0-9]+}}, r4, 2
-; P8BE-DAG: lxvw4x {{v[0-9]+}}, r3
+; P8BE-DAG: lxvw4x {{v[0-9]+}}, 0, r3
 ; P8BE-DAG: lxvw4x
 ; P8BE: vperm
 ; P8BE: blr

diff --git a/llvm/test/CodeGen/PowerPC/ppc64le-smallarg.ll b/llvm/test/CodeGen/PowerPC/ppc64le-smallarg.ll
index 0e871c3..3a42540 100644 (file)
--- a/llvm/test/CodeGen/PowerPC/ppc64le-smallarg.ll
+++ b/llvm/test/CodeGen/PowerPC/ppc64le-smallarg.ll
@@ -53,8 +53,8 @@ entry:
   ret void
 }
 ; CHECK: @caller2
-; CHECK: li [[TOCOFF:[0-9]+]], 136
-; CHECK: stxsspx {{[0-9]+}}, 1, [[TOCOFF]]
+; CHECK: addi [[TOCOFF:[0-9]+]], {{[0-9]+}}, 136
+; CHECK: stxsspx {{[0-9]+}}, 0, [[TOCOFF]]
 ; CHECK: bl test2
 
 declare float @test2(float, float, float, float, float, float, float, float, float, float, float, float, float, float)

diff --git a/llvm/test/CodeGen/PowerPC/select-addrRegRegOnly.ll b/llvm/test/CodeGen/PowerPC/select-addrRegRegOnly.ll
new file mode 100644 (file)
index 0000000..f880d1f
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/select-addrRegRegOnly.ll
@@ -0,0 +1,37 @@
+; RUN: llc -mcpu=pwr8 -mtriple=powerpc64le-unknown-unknown -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -mcpu=pwr8 -mtriple=powerpc64-unknown-unknown -verify-machineinstrs < %s | FileCheck %s
+
+; Function Attrs: norecurse nounwind readonly
+define float @testSingleAccess(i32* nocapture readonly %arr) local_unnamed_addr #0 {
+; CHECK-LABEL: testSingleAccess:
+; CHECK:       # BB#0: # %entry
+; CHECK-NEXT:    addi 3, 3, 8
+; CHECK-NEXT:    lxsiwax 0, 0, 3
+; CHECK-NEXT:    xscvsxdsp 1, 0
+; CHECK-NEXT:    blr
+entry:
+  %arrayidx = getelementptr inbounds i32, i32* %arr, i64 2
+  %0 = load i32, i32* %arrayidx, align 4
+  %conv = sitofp i32 %0 to float
+  ret float %conv
+}
+
+; Function Attrs: norecurse nounwind readonly
+define float @testMultipleAccess(i32* nocapture readonly %arr) local_unnamed_addr #0 {
+; CHECK-LABEL: testMultipleAccess:
+; CHECK:       # BB#0: # %entry
+; CHECK-NEXT:    lwz 4, 8(3)
+; CHECK-NEXT:    lwz 12, 12(3)
+; CHECK-NEXT:    add 3, 12, 4
+; CHECK-NEXT:    mtvsrwa 0, 3
+; CHECK-NEXT:    xscvsxdsp 1, 0
+; CHECK-NEXT:    blr
+entry:
+  %arrayidx = getelementptr inbounds i32, i32* %arr, i64 2
+  %0 = load i32, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32, i32* %arr, i64 3
+  %1 = load i32, i32* %arrayidx1, align 4
+  %add = add nsw i32 %1, %0
+  %conv = sitofp i32 %add to float
+  ret float %conv
+}

diff --git a/llvm/test/CodeGen/PowerPC/vsx-partword-int-loads-and-stores.ll b/llvm/test/CodeGen/PowerPC/vsx-partword-int-loads-and-stores.ll
index 67146e4..5346d8a 100644 (file)
--- a/llvm/test/CodeGen/PowerPC/vsx-partword-int-loads-and-stores.ll
+++ b/llvm/test/CodeGen/PowerPC/vsx-partword-int-loads-and-stores.ll
@@ -321,8 +321,8 @@ entry:
 ; CHECK: lxsibzx 34, 0, 3
 ; CHECK-NEXT: vspltb 2, 2, 7
 ; CHECK-BE-LABEL: vecucus
-; CHECK-BE: li [[OFFSET:[0-9]+]], 1
-; CHECK-BE-NEXT: lxsibzx 34, 3, [[OFFSET]]
+; CHECK-BE: addi [[OFFSET:[0-9]+]], [[OFFSET]], 1
+; CHECK-BE-NEXT: lxsibzx 34, 0, [[OFFSET]]
 ; CHECK-BE-NEXT: vspltb 2, 2, 7
 }
 
@@ -385,8 +385,8 @@ entry:
 ; CHECK: lxsibzx 34, 0, 3
 ; CHECK-NEXT: vspltb 2, 2, 7
 ; CHECK-BE-LABEL: vecscus
-; CHECK-BE: li [[OFFSET:[0-9]+]], 1
-; CHECK-BE-NEXT: lxsibzx 34, 3, [[OFFSET]]
+; CHECK-BE: addi [[OFFSET:[0-9]+]], [[OFFSET]], 1
+; CHECK-BE-NEXT: lxsibzx 34, 0, [[OFFSET]]
 ; CHECK-BE-NEXT: vspltb 2, 2, 7
 }
 
@@ -487,8 +487,8 @@ entry:
 ; CHECK: lxsibzx 34, 0, 3
 ; CHECK-NEXT: vspltb 2, 2, 7
 ; CHECK-BE-LABEL: vecucss
-; CHECK-BE: li [[OFFSET:[0-9]+]], 1
-; CHECK-BE-NEXT: lxsibzx 34, 3, [[OFFSET]]
+; CHECK-BE: addi [[OFFSET:[0-9]+]], [[OFFSET]], 1
+; CHECK-BE-NEXT: lxsibzx 34, 0, [[OFFSET]]
 ; CHECK-BE-NEXT: vspltb 2, 2, 7
 }
 
@@ -540,8 +540,8 @@ entry:
 ; CHECK: lxsibzx 34, 0, 3
 ; CHECK-NEXT: vspltb 2, 2, 7
 ; CHECK-BE-LABEL: vecscss
-; CHECK-BE: li [[OFFSET:[0-9]+]], 1
-; CHECK-BE-NEXT: lxsibzx 34, 3, [[OFFSET]]
+; CHECK-BE: addi [[OFFSET:[0-9]+]], [[OFFSET]], 1
+; CHECK-BE-NEXT: lxsibzx 34, 0, [[OFFSET]]
 ; CHECK-BE-NEXT: vspltb 2, 2, 7
 }