From f2c8f3b181e1a0f1a45e6893d15317386bf73977 Mon Sep 17 00:00:00 2001 From: Nemanja Ivanovic Date: Tue, 22 Oct 2019 12:20:38 +0000 Subject: [PATCH] [PowerPC] Turn on CR-Logical reducer pass This re-commits r375152 which was pulled in r375233 because it broke the EXPENSIVE_CHECKS bot on Windows. The reason for the failure was a bug in the pass that the commit turned on by default. This patch fixes that bug and turns the pass back on. This patch has been verified on the buildbot that originally failed thanks to Simon Pilgrim. Differential revision: https://reviews.llvm.org/D52431 llvm-svn: 375497 --- .../Target/PowerPC/PPCReduceCRLogicals.cpp | 9 +++-- llvm/lib/Target/PowerPC/PPCTargetMachine.cpp | 2 +- .../CodeGen/PowerPC/2008-10-28-f128-i32.ll | 39 ++++++++++--------- llvm/test/CodeGen/PowerPC/brcond.ll | 6 ++- llvm/test/CodeGen/PowerPC/pr42492.ll | 14 ++++--- .../test/CodeGen/PowerPC/tocSaveInPrologue.ll | 15 +++---- llvm/test/CodeGen/PowerPC/vec-min-max.ll | 23 +++++------ 7 files changed, 58 insertions(+), 50 deletions(-) diff --git a/llvm/lib/Target/PowerPC/PPCReduceCRLogicals.cpp b/llvm/lib/Target/PowerPC/PPCReduceCRLogicals.cpp index ac20fae983cd..3b71ed219c17 100644 --- a/llvm/lib/Target/PowerPC/PPCReduceCRLogicals.cpp +++ b/llvm/lib/Target/PowerPC/PPCReduceCRLogicals.cpp @@ -381,10 +381,10 @@ private: const MachineBranchProbabilityInfo *MBPI; // A vector to contain all the CR logical operations - std::vector AllCRLogicalOps; + SmallVector AllCRLogicalOps; void initialize(MachineFunction &MFParm); void collectCRLogicals(); - bool handleCROp(CRLogicalOpInfo &CRI); + bool handleCROp(unsigned Idx); bool splitBlockOnBinaryCROp(CRLogicalOpInfo &CRI); static bool isCRLogical(MachineInstr &MI) { unsigned Opc = MI.getOpcode(); @@ -398,7 +398,7 @@ private: // Not using a range-based for loop here as the vector may grow while being // operated on. for (unsigned i = 0; i < AllCRLogicalOps.size(); i++) - Changed |= handleCROp(AllCRLogicalOps[i]); + Changed |= handleCROp(i); return Changed; } @@ -578,10 +578,11 @@ void PPCReduceCRLogicals::initialize(MachineFunction &MFParam) { /// a unary CR logical might be used to change the condition code on a /// comparison feeding it. A nullary CR logical might simply be removable /// if the user of the bit it [un]sets can be transformed. -bool PPCReduceCRLogicals::handleCROp(CRLogicalOpInfo &CRI) { +bool PPCReduceCRLogicals::handleCROp(unsigned Idx) { // We can definitely split a block on the inputs to a binary CR operation // whose defs and (single) use are within the same block. bool Changed = false; + CRLogicalOpInfo CRI = AllCRLogicalOps[Idx]; if (CRI.IsBinary && CRI.ContainedInBlock && CRI.SingleUse && CRI.FeedsBR && CRI.DefsSingleUse) { Changed = splitBlockOnBinaryCROp(CRI); diff --git a/llvm/lib/Target/PowerPC/PPCTargetMachine.cpp b/llvm/lib/Target/PowerPC/PPCTargetMachine.cpp index 015790659840..abefee8b339d 100644 --- a/llvm/lib/Target/PowerPC/PPCTargetMachine.cpp +++ b/llvm/lib/Target/PowerPC/PPCTargetMachine.cpp @@ -93,7 +93,7 @@ EnableMachineCombinerPass("ppc-machine-combiner", static cl::opt ReduceCRLogical("ppc-reduce-cr-logicals", cl::desc("Expand eligible cr-logical binary ops to branches"), - cl::init(false), cl::Hidden); + cl::init(true), cl::Hidden); extern "C" void LLVMInitializePowerPCTarget() { // Register the targets RegisterTargetMachine A(getThePPC32Target()); diff --git a/llvm/test/CodeGen/PowerPC/2008-10-28-f128-i32.ll b/llvm/test/CodeGen/PowerPC/2008-10-28-f128-i32.ll index cc495b321fc5..c851e73b1f1f 100644 --- a/llvm/test/CodeGen/PowerPC/2008-10-28-f128-i32.ll +++ b/llvm/test/CodeGen/PowerPC/2008-10-28-f128-i32.ll @@ -36,7 +36,7 @@ define i64 @__fixunstfdi(ppc_fp128 %a) nounwind readnone { ; CHECK-NEXT: # %bb.1: # %bb5 ; CHECK-NEXT: li 3, 0 ; CHECK-NEXT: li 4, 0 -; CHECK-NEXT: b .LBB0_16 +; CHECK-NEXT: b .LBB0_17 ; CHECK-NEXT: .LBB0_2: # %bb1 ; CHECK-NEXT: lfd 0, 400(1) ; CHECK-NEXT: lis 3, 15856 @@ -166,13 +166,11 @@ define i64 @__fixunstfdi(ppc_fp128 %a) nounwind readnone { ; CHECK-NEXT: bl __gcc_qsub@PLT ; CHECK-NEXT: stfd 2, 176(1) ; CHECK-NEXT: stfd 1, 168(1) -; CHECK-NEXT: fcmpu 0, 2, 27 +; CHECK-NEXT: fcmpu 1, 2, 27 ; CHECK-NEXT: lwz 3, 180(1) -; CHECK-NEXT: fcmpu 1, 1, 27 -; CHECK-NEXT: crandc 20, 6, 0 -; CHECK-NEXT: cror 21, 5, 7 +; CHECK-NEXT: fcmpu 0, 1, 27 +; CHECK-NEXT: crandc 20, 2, 4 ; CHECK-NEXT: stw 3, 268(1) -; CHECK-NEXT: cror 20, 21, 20 ; CHECK-NEXT: lwz 3, 176(1) ; CHECK-NEXT: stw 3, 264(1) ; CHECK-NEXT: lwz 3, 172(1) @@ -181,8 +179,11 @@ define i64 @__fixunstfdi(ppc_fp128 %a) nounwind readnone { ; CHECK-NEXT: lwz 3, 168(1) ; CHECK-NEXT: stw 3, 272(1) ; CHECK-NEXT: lfd 31, 272(1) -; CHECK-NEXT: bc 12, 20, .LBB0_13 -; CHECK-NEXT: # %bb.10: # %bb2 +; CHECK-NEXT: bc 12, 20, .LBB0_14 +; CHECK-NEXT: # %bb.10: # %bb1 +; CHECK-NEXT: cror 20, 1, 3 +; CHECK-NEXT: bc 12, 20, .LBB0_14 +; CHECK-NEXT: # %bb.11: # %bb2 ; CHECK-NEXT: fneg 28, 31 ; CHECK-NEXT: stfd 28, 48(1) ; CHECK-NEXT: lis 3, 16864 @@ -231,15 +232,15 @@ define i64 @__fixunstfdi(ppc_fp128 %a) nounwind readnone { ; CHECK-NEXT: crandc 20, 6, 1 ; CHECK-NEXT: cror 20, 4, 20 ; CHECK-NEXT: addis 3, 3, -32768 -; CHECK-NEXT: bc 12, 20, .LBB0_12 -; CHECK-NEXT: # %bb.11: # %bb2 +; CHECK-NEXT: bc 12, 20, .LBB0_13 +; CHECK-NEXT: # %bb.12: # %bb2 ; CHECK-NEXT: ori 3, 4, 0 -; CHECK-NEXT: b .LBB0_12 -; CHECK-NEXT: .LBB0_12: # %bb2 +; CHECK-NEXT: b .LBB0_13 +; CHECK-NEXT: .LBB0_13: # %bb2 ; CHECK-NEXT: subfic 4, 3, 0 ; CHECK-NEXT: subfe 3, 29, 30 -; CHECK-NEXT: b .LBB0_16 -; CHECK-NEXT: .LBB0_13: # %bb3 +; CHECK-NEXT: b .LBB0_17 +; CHECK-NEXT: .LBB0_14: # %bb3 ; CHECK-NEXT: stfd 31, 112(1) ; CHECK-NEXT: li 3, 0 ; CHECK-NEXT: stw 3, 148(1) @@ -286,13 +287,13 @@ define i64 @__fixunstfdi(ppc_fp128 %a) nounwind readnone { ; CHECK-NEXT: crandc 20, 6, 0 ; CHECK-NEXT: cror 20, 5, 20 ; CHECK-NEXT: addis 3, 3, -32768 -; CHECK-NEXT: bc 12, 20, .LBB0_14 -; CHECK-NEXT: b .LBB0_15 -; CHECK-NEXT: .LBB0_14: # %bb3 -; CHECK-NEXT: addi 4, 3, 0 +; CHECK-NEXT: bc 12, 20, .LBB0_15 +; CHECK-NEXT: b .LBB0_16 ; CHECK-NEXT: .LBB0_15: # %bb3 +; CHECK-NEXT: addi 4, 3, 0 +; CHECK-NEXT: .LBB0_16: # %bb3 ; CHECK-NEXT: mr 3, 30 -; CHECK-NEXT: .LBB0_16: # %bb5 +; CHECK-NEXT: .LBB0_17: # %bb5 ; CHECK-NEXT: lfd 31, 456(1) # 8-byte Folded Reload ; CHECK-NEXT: lfd 30, 448(1) # 8-byte Folded Reload ; CHECK-NEXT: lfd 29, 440(1) # 8-byte Folded Reload diff --git a/llvm/test/CodeGen/PowerPC/brcond.ll b/llvm/test/CodeGen/PowerPC/brcond.ll index 5bf8c6c1f355..b8c98427f107 100644 --- a/llvm/test/CodeGen/PowerPC/brcond.ll +++ b/llvm/test/CodeGen/PowerPC/brcond.ll @@ -1,5 +1,7 @@ -; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-unknown < %s | FileCheck %s -; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-unknown < %s | FileCheck %s +; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-unknown \ +; RUN: -ppc-reduce-cr-logicals=false < %s | FileCheck %s +; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-unknown \ +; RUN: -ppc-reduce-cr-logicals=false < %s | FileCheck %s define signext i32 @testi32slt(i32 signext %c1, i32 signext %c2, i32 signext %c3, i32 signext %c4, i32 signext %a1, i32 signext %a2) #0 { ; CHECK-LABEL: testi32slt diff --git a/llvm/test/CodeGen/PowerPC/pr42492.ll b/llvm/test/CodeGen/PowerPC/pr42492.ll index 3aa9ccdbf69a..e404d5d72cd0 100644 --- a/llvm/test/CodeGen/PowerPC/pr42492.ll +++ b/llvm/test/CodeGen/PowerPC/pr42492.ll @@ -14,13 +14,15 @@ define void @f(i8*, i8*, i64*) { ; CHECK-NEXT: li 4, 0 ; CHECK-NEXT: .p2align 5 ; CHECK-NEXT: .LBB0_2: # -; CHECK-NEXT: cmplwi 4, 14 -; CHECK-NEXT: cmpd 1, 3, 4 ; CHECK-NEXT: sldi 6, 6, 4 -; CHECK-NEXT: cror 20, 6, 1 -; CHECK-NEXT: addi 4, 4, 1 -; CHECK-NEXT: bc 4, 20, .LBB0_2 -; CHECK-NEXT: # %bb.3: +; CHECK-NEXT: cmplwi 4, 14 +; CHECK-NEXT: addi 7, 4, 1 +; CHECK-NEXT: bc 12, 1, .LBB0_4 +; CHECK-NEXT: # %bb.3: # +; CHECK-NEXT: cmpd 3, 4 +; CHECK-NEXT: mr 4, 7 +; CHECK-NEXT: bc 4, 2, .LBB0_2 +; CHECK-NEXT: .LBB0_4: ; CHECK-NEXT: std 6, 8(5) ; CHECK-NEXT: blr diff --git a/llvm/test/CodeGen/PowerPC/tocSaveInPrologue.ll b/llvm/test/CodeGen/PowerPC/tocSaveInPrologue.ll index d9f85f17703d..79f57eb05d1e 100644 --- a/llvm/test/CodeGen/PowerPC/tocSaveInPrologue.ll +++ b/llvm/test/CodeGen/PowerPC/tocSaveInPrologue.ll @@ -16,16 +16,17 @@ define dso_local void @test(void (i32)* nocapture %fp, i32 signext %Arg, i32 sig ; CHECK-NEXT: std r0, 16(r1) ; CHECK-NEXT: stdu r1, -64(r1) ; CHECK-NEXT: mr r29, r5 -; CHECK-NEXT: cmpwi cr1, r4, 11 ; CHECK-NEXT: mr r30, r3 ; CHECK-NEXT: extsw r28, r4 ; CHECK-NEXT: std r2, 24(r1) ; CHECK-NEXT: cmpwi r29, 1 -; CHECK-NEXT: cror 4*cr5+lt, lt, 4*cr1+lt -; CHECK-NEXT: bc 12, 4*cr5+lt, .LBB0_2 +; CHECK-NEXT: bc 12, lt, .LBB0_3 +; CHECK-NEXT: # %bb.1: # %entry +; CHECK-NEXT: cmpwi cr0, r4, 11 +; CHECK-NEXT: bc 12, lt, .LBB0_3 ; CHECK-NEXT: .p2align 5 -; CHECK-NEXT: .LBB0_1: # %for.body.us -; CHECK-NEXT: # =>This Inner Loop Header: Depth=1 +; CHECK-NEXT: .LBB0_2: # %for.body.us +; CHECK-NEXT: # ; CHECK-NEXT: mtctr r30 ; CHECK-NEXT: mr r3, r28 ; CHECK-NEXT: mr r12, r30 @@ -33,8 +34,8 @@ define dso_local void @test(void (i32)* nocapture %fp, i32 signext %Arg, i32 sig ; CHECK-NEXT: ld 2, 24(r1) ; CHECK-NEXT: addi r29, r29, -1 ; CHECK-NEXT: cmplwi r29, 0 -; CHECK-NEXT: bne cr0, .LBB0_1 -; CHECK-NEXT: .LBB0_2: # %for.cond.cleanup +; CHECK-NEXT: bne cr0, .LBB0_2 +; CHECK-NEXT: .LBB0_3: # %for.cond.cleanup ; CHECK-NEXT: mtctr r30 ; CHECK-NEXT: mr r3, r28 ; CHECK-NEXT: mr r12, r30 diff --git a/llvm/test/CodeGen/PowerPC/vec-min-max.ll b/llvm/test/CodeGen/PowerPC/vec-min-max.ll index 8269e1c3c7b8..e29ef336879a 100644 --- a/llvm/test/CodeGen/PowerPC/vec-min-max.ll +++ b/llvm/test/CodeGen/PowerPC/vec-min-max.ll @@ -240,22 +240,23 @@ entry: define i128 @invalidv1i128(<2 x i128> %v1, <2 x i128> %v2) { ; CHECK-LABEL: invalidv1i128: ; CHECK: # %bb.0: +; CHECK-NEXT: mfvsrd 3, 36 ; CHECK-NEXT: xxswapd 0, 36 -; CHECK-NEXT: mfvsrd 4, 36 -; CHECK-NEXT: mfvsrd 5, 34 +; CHECK-NEXT: mfvsrd 4, 34 +; CHECK-NEXT: xxswapd 1, 34 +; CHECK-NEXT: cmpld 4, 3 +; CHECK-NEXT: cmpd 1, 4, 3 ; CHECK-NEXT: mfvsrd 3, 0 -; CHECK-NEXT: xxswapd 0, 34 -; CHECK-NEXT: cmpld 5, 4 -; CHECK-NEXT: cmpd 1, 5, 4 ; CHECK-NEXT: crandc 20, 4, 2 -; CHECK-NEXT: mfvsrd 6, 0 -; CHECK-NEXT: cmpld 1, 6, 3 -; CHECK-NEXT: crand 21, 2, 4 -; CHECK-NEXT: cror 20, 21, 20 -; CHECK-NEXT: bc 12, 20, .LBB12_2 +; CHECK-NEXT: mfvsrd 4, 1 +; CHECK-NEXT: cmpld 1, 4, 3 +; CHECK-NEXT: bc 12, 20, .LBB12_3 ; CHECK-NEXT: # %bb.1: +; CHECK-NEXT: crand 20, 2, 4 +; CHECK-NEXT: bc 12, 20, .LBB12_3 +; CHECK-NEXT: # %bb.2: ; CHECK-NEXT: vmr 2, 4 -; CHECK-NEXT: .LBB12_2: +; CHECK-NEXT: .LBB12_3: ; CHECK-NEXT: xxswapd 0, 34 ; CHECK-NEXT: mfvsrd 4, 34 ; CHECK-NEXT: mfvsrd 3, 0