[llvm] r178193 - This patch follows is a follow up to r178171, which uses the register
Nadav Rotem
nrotem at apple.com
Wed Mar 27 17:08:22 PDT 2013
Hi Preston,
The test cases are really big. Is there a way to make them smaller and still be able to test the reloading optimization ?
Thanks,
Nadav
On 03/27/13, Preston Gurd <preston.gurd at intel.com> wrote:
> Author: pgurd
> Date: Wed Mar 27 18:16:18 2013
> New Revision: 178193
>
> URL: http://llvm.org/viewvc/llvm-project?rev=178193&view=rev
> Log:
> This patch follows is a follow up to r178171, which uses the register
> form of call in preference to memory indirect on Atom.
>
> In this case, the patch applies the optimization to the code for reloading
> spilled registers.
>
> The patch also includes changes to sibcall.ll and movgs.ll, which were
> failing on the Atom buildbot after the first patch was applied.
>
> This patch by Sriram Murali.
>
>
> Added:
> llvm/trunk/test/CodeGen/X86/atom-call-reg-indirect-foldedreload32.ll
> llvm/trunk/test/CodeGen/X86/atom-call-reg-indirect-foldedreload64.ll
> Modified:
> llvm/trunk/lib/Target/X86/X86InstrInfo.cpp
> llvm/trunk/test/CodeGen/X86/movgs.ll
> llvm/trunk/test/CodeGen/X86/sibcall.ll
>
> Modified: llvm/trunk/lib/Target/X86/X86InstrInfo.cpp
> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86InstrInfo.cpp?rev=178193&r1=178192&r2=178193&view=diff
> ==============================================================================
> --- llvm/trunk/lib/Target/X86/X86InstrInfo.cpp (original)
> +++ llvm/trunk/lib/Target/X86/X86InstrInfo.cpp Wed Mar 27 18:16:18 2013
> @@ -3655,7 +3655,16 @@ X86InstrInfo::foldMemoryOperandImpl(Mach
> const SmallVectorImpl<MachineOperand> &MOs,
> unsigned Size, unsigned Align) const {
> const DenseMap<unsigned, std::pair<unsigned,unsigned> > *OpcodeTablePtr = 0;
> + bool isCallRegIndirect = TM.getSubtarget<X86Subtarget>().callRegIndirect();
> bool isTwoAddrFold = false;
> +
> + // Atom favors register form of call. So, we do not fold loads into calls
> + // when X86Subtarget is Atom.
> + if (isCallRegIndirect &&
> + (MI->getOpcode() == X86::CALL32r || MI->getOpcode() == X86::CALL64r)) {
> + return NULL;
> + }
> +
> unsigned NumOps = MI->getDesc().getNumOperands();
> bool isTwoAddr = NumOps > 1 &&
> MI->getDesc().getOperandConstraint(1, MCOI::TIED_TO) != -1;
>
> Added: llvm/trunk/test/CodeGen/X86/atom-call-reg-indirect-foldedreload32.ll
> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/atom-call-reg-indirect-foldedreload32.ll?rev=178193&view=auto
> ==============================================================================
> --- llvm/trunk/test/CodeGen/X86/atom-call-reg-indirect-foldedreload32.ll (added)
> +++ llvm/trunk/test/CodeGen/X86/atom-call-reg-indirect-foldedreload32.ll Wed Mar 27 18:16:18 2013
> @@ -0,0 +1,204 @@
> +; RUN: llc < %s -mtriple=i386-linux-gnu -mcpu=atom 2>&1 | \
> +; RUN: grep "calll" | not grep "("
> +; RUN: llc < %s -mtriple=i386-linux-gnu -mcpu=core2 2>&1 | \
> +; RUN: grep "calll" | grep "4-byte Folded Reload"
> +
> +%struct.targettype = type {i32}
> +%struct.op_ptr1 = type opaque
> +%struct.op_ptr2 = type opaque
> +%union.anon = type { [8 x i32], [48 x i8] }
> +%struct.const1 = type { [64 x i16], i8 }
> +%struct.const2 = type { [17 x i8], [256 x i8], i8 }
> +
> +%struct.ref1 = type { void (%struct.ref2*)*, i32 (%struct.ref2*)*, void (%struct.ref2*)*, i32 (%struct.ref2*, i8***)*, %struct.op_ptr2** }
> +%struct.ref2 = type { %struct.localref13*, %struct.localref15*, %struct.localref12*, i8*, i8, i32, %struct.localref11*, i32, i32, i32, i32, i32, i32, i32, double, i8, i8, i32, i8, i8, i8, i32, i8, i32, i8, i8, i8, i32, i32, i32, i32, i32, i32, i8**, i32, i32, i32, i32, i32, [64 x i32]*, [4 x %struct.const1*], [4 x %struct.const2*], [4 x %struct.const2*], i32, %struct.ref3*, i8, i8, [16 x i8], [16 x i8], [16 x i8], i32, i8, i8, i8, i8, i16, i16, i8, i8, i8, %struct.localref10*, i32, i32, i32, i32, i8*, i32, [4 x %struct.ref3*], i32, i32, i32, [10 x i32], i32, i32, i32, i32, i32, %struct.localref8*, %struct.localref9*, %struct.ref1*, %struct.localref7*, %struct.localref6*, %struct.localref5*, %struct.localref1*, %struct.ref4*, %struct.localref2*, %struct.localref3*, %struct.localref4* }
> +%struct.ref3 = type { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i8, i32, i32, i32, i32, i32, i32, %struct.const1*, i8* }
> +%struct.ref4 = type { void (%struct.ref2*)*, [5 x void (%struct.ref2*, %struct.ref3*, i16*, i8**, i32)*] }
> +
> +%struct.localref1 = type { void (%struct.ref2*)*, i8 (%struct.ref2*, [64 x i16]**)*, i8 }
> +%struct.localref2 = type { void (%struct.ref2*)*, void (%struct.ref2*, i8***, i32*, i32, i8**, i32*, i32)*, i8 }
> +%struct.localref3 = type { void (%struct.ref2*)*, void (%struct.ref2*, i8***, i32, i8**, i32)* }
> +%struct.localref4 = type { {}*, void (%struct.ref2*, i8**, i8**, i32)*, void (%struct.ref2*)*, void (%struct.ref2*)* }
> +%struct.localref5 = type { void (%struct.ref2*)*, i32 (%struct.ref2*)*, i8 (%struct.ref2*)*, i8, i8, i32, i32 }
> +%struct.localref6 = type { i32 (%struct.ref2*)*, void (%struct.ref2*)*, void (%struct.ref2*)*, void (%struct.ref2*)*, i8, i8 }
> +%struct.localref7 = type { void (%struct.ref2*, i32)*, void (%struct.ref2*, i8***, i32*, i32, i8**, i32*, i32)* }
> +%struct.localref8 = type { void (%struct.ref2*)*, void (%struct.ref2*)*, i8 }
> +%struct.localref9 = type { void (%struct.ref2*, i32)*, void (%struct.ref2*, i8**, i32*, i32)* }
> +%struct.localref10 = type { %struct.localref10*, i8, i32, i32, i8* }
> +%struct.localref11 = type { i8*, %struct.targettype, void (%struct.ref2*)*, i8 (%struct.ref2*)*, void (%struct.ref2*, %struct.targettype)*, i8 (%struct.ref2*, i32)*, void (%struct.ref2*)* }
> +%struct.localref12 = type { {}*, %struct.targettype, %struct.targettype, i32, i32 }
> +%struct.localref13 = type { void (%struct.localref14*)*, void (%struct.localref14*, i32)*, void (%struct.localref14*)*, void (%struct.localref14*, i8*)*, void (%struct.localref14*)*, i32, %union.anon, i32, %struct.targettype, i8**, i32, i8**, i32, i32 }
> +%struct.localref14 = type { %struct.localref13*, %struct.localref15*, %struct.localref12*, i8*, i8, i32 }
> +%struct.localref15 = type { i8* (%struct.localref14*, i32, %struct.targettype)*, i8* (%struct.localref14*, i32, %struct.targettype)*, i8** (%struct.localref14*, i32, i32, i32)*, [64 x i16]** (%struct.localref14*, i32, i32, i32)*, %struct.op_ptr1* (%struct.localref14*, i32, i8, i32, i32, i32)*, %struct.op_ptr2* (%struct.localref14*, i32, i8, i32, i32, i32)*, {}*, i8** (%struct.localref14*, %struct.op_ptr1*, i32, i32, i8)*, [64 x i16]** (%struct.localref14*, %struct.op_ptr2*, i32, i32, i8)*, void (%struct.localref14*, i32)*, {}*, %struct.targettype, %struct.targettype}
> +
> +define internal i32 @foldedreload(%struct.ref2* %cinfo, i8*** nocapture %output1) {
> + %1 = getelementptr inbounds %struct.ref2* %cinfo, i32 0, i32 79
> + %2 = load %struct.ref1** %1, align 4
> + %3 = getelementptr inbounds %struct.ref2* %cinfo, i32 0, i32 68
> + %4 = load i32* %3, align 4
> + %5 = add i32 %4, -1
> + %6 = getelementptr inbounds %struct.ref2* %cinfo, i32 0, i32 64
> + %7 = load i32* %6, align 4
> + %8 = add i32 %7, -1
> + %9 = getelementptr inbounds %struct.ref1* %2, i32 1, i32 1
> + %10 = bitcast i32 (%struct.ref2*)** %9 to i32*
> + %11 = load i32* %10, align 4
> + %12 = getelementptr inbounds %struct.ref1* %2, i32 1, i32 2
> + %13 = bitcast void (%struct.ref2*)** %12 to i32*
> + %14 = load i32* %13, align 4
> + %15 = icmp slt i32 %11, %14
> + br i1 %15, label %.lr.ph18, label %._crit_edge19
> +
> +.lr.ph18:
> + %16 = getelementptr inbounds %struct.ref1* %2, i32 1
> + %17 = bitcast %struct.ref1* %16 to i32*
> + %18 = getelementptr inbounds %struct.ref1* %16, i32 0, i32 0
> + %19 = getelementptr inbounds %struct.ref2* %cinfo, i32 0, i32 66
> + %20 = getelementptr inbounds %struct.ref2* %cinfo, i32 0, i32 84
> + %21 = getelementptr inbounds %struct.ref2* %cinfo, i32 0, i32 36
> + %22 = getelementptr inbounds %struct.ref1* %2, i32 1, i32 3
> + %23 = bitcast i32 (%struct.ref2*, i8***)** %22 to [10 x [64 x i16]*]*
> + %.pre = load i32* %17, align 4
> + br label %24
> +
> +; <label>:24
> + %25 = phi i32 [ %14, %.lr.ph18 ], [ %89, %88 ]
> + %26 = phi i32 [ %.pre, %.lr.ph18 ], [ 0, %88 ]
> + %var1.015 = phi i32 [ %11, %.lr.ph18 ], [ %90, %88 ]
> + %27 = icmp ugt i32 %26, %5
> + br i1 %27, label %88, label %.preheader7.lr.ph
> +
> +.preheader7.lr.ph:
> + %.pre24 = load i32* %19, align 4
> + br label %.preheader7
> +
> +.preheader7:
> + %28 = phi i32 [ %.pre24, %.preheader7.lr.ph ], [ %85, %._crit_edge11 ]
> + %var2.012 = phi i32 [ %26, %.preheader7.lr.ph ], [ %86, %._crit_edge11 ]
> + %29 = icmp sgt i32 %28, 0
> + br i1 %29, label %.lr.ph10, label %._crit_edge11
> +
> +.lr.ph10:
> + %30 = phi i32 [ %28, %.preheader7 ], [ %82, %81 ]
> + %var4.09 = phi i32 [ 0, %.preheader7 ], [ %var4.1.lcssa, %81 ]
> + %ci.08 = phi i32 [ 0, %.preheader7 ], [ %83, %81 ]
> + %31 = getelementptr inbounds %struct.ref2* %cinfo, i32 0, i32 67, i32 %ci.08
> + %32 = load %struct.ref3** %31, align 4
> + %33 = getelementptr inbounds %struct.ref3* %32, i32 0, i32 1
> + %34 = load i32* %33, align 4
> + %35 = load %struct.ref4** %20, align 4
> + %36 = getelementptr inbounds %struct.ref4* %35, i32 0, i32 1, i32 %34
> + %37 = load void (%struct.ref2*, %struct.ref3*, i16*, i8**, i32)** %36, align 4
> + %38 = getelementptr inbounds %struct.ref3* %32, i32 0, i32 17
> + %39 = load i32* %38, align 4
> + %40 = getelementptr inbounds %struct.ref3* %32, i32 0, i32 9
> + %41 = load i32* %40, align 4
> + %42 = getelementptr inbounds %struct.ref3* %32, i32 0, i32 16
> + %43 = load i32* %42, align 4
> + %44 = mul i32 %43, %var2.012
> + %45 = getelementptr inbounds %struct.ref3* %32, i32 0, i32 14
> + %46 = load i32* %45, align 4
> + %47 = icmp sgt i32 %46, 0
> + br i1 %47, label %.lr.ph6, label %81
> +
> +.lr.ph6:
> + %48 = getelementptr inbounds i8*** %output1, i32 %34
> + %49 = mul nsw i32 %41, %var1.015
> + %50 = load i8*** %48, align 4
> + %51 = getelementptr inbounds i8** %50, i32 %49
> + %52 = getelementptr inbounds %struct.ref3* %32, i32 0, i32 13
> + %53 = getelementptr inbounds %struct.ref3* %32, i32 0, i32 18
> + %54 = icmp sgt i32 %39, 0
> + br i1 %54, label %.lr.ph6.split.us, label %.lr.ph6..lr.ph6.split_crit_edge
> +
> +.lr.ph6..lr.ph6.split_crit_edge:
> + br label %._crit_edge26
> +
> +.lr.ph6.split.us:
> + %55 = phi i32 [ %63, %._crit_edge28 ], [ %46, %.lr.ph6 ]
> + %56 = phi i32 [ %64, %._crit_edge28 ], [ %41, %.lr.ph6 ]
> + %var4.15.us = phi i32 [ %66, %._crit_edge28 ], [ %var4.09, %.lr.ph6 ]
> + %output2.04.us = phi i8** [ %69, %._crit_edge28 ], [ %51, %.lr.ph6 ]
> + %var5.03.us = phi i32 [ %67, %._crit_edge28 ], [ 0, %.lr.ph6 ]
> + %57 = load i32* %21, align 4
> + %58 = icmp ult i32 %57, %8
> + br i1 %58, label %.lr.ph.us, label %59
> +
> +; <label>:59
> + %60 = add nsw i32 %var5.03.us, %var1.015
> + %61 = load i32* %53, align 4
> + %62 = icmp slt i32 %60, %61
> + br i1 %62, label %.lr.ph.us, label %._crit_edge27
> +
> +._crit_edge27:
> + %63 = phi i32 [ %.pre23.pre, %.loopexit.us ], [ %55, %59 ]
> + %64 = phi i32 [ %74, %.loopexit.us ], [ %56, %59 ]
> + %65 = load i32* %52, align 4
> + %66 = add nsw i32 %65, %var4.15.us
> + %67 = add nsw i32 %var5.03.us, 1
> + %68 = icmp slt i32 %67, %63
> + br i1 %68, label %._crit_edge28, label %._crit_edge
> +
> +._crit_edge28:
> + %69 = getelementptr inbounds i8** %output2.04.us, i32 %64
> + br label %.lr.ph6.split.us
> +
> +.lr.ph.us:
> + %var3.02.us = phi i32 [ %75, %.lr.ph.us ], [ %44, %.lr.ph6.split.us ], [ %44, %59 ]
> + %xindex.01.us = phi i32 [ %76, %.lr.ph.us ], [ 0, %.lr.ph6.split.us ], [ 0, %59 ]
> + %70 = add nsw i32 %xindex.01.us, %var4.15.us
> + %71 = getelementptr inbounds [10 x [64 x i16]*]* %23, i32 0, i32 %70
> + %72 = load [64 x i16]** %71, align 4
> + %73 = getelementptr inbounds [64 x i16]* %72, i32 0, i32 0
> + tail call void %37(%struct.ref2* %cinfo, %struct.ref3* %32, i16* %73, i8** %output2.04.us, i32 %var3.02.us) nounwind
> + %74 = load i32* %40, align 4
> + %75 = add i32 %74, %var3.02.us
> + %76 = add nsw i32 %xindex.01.us, 1
> + %exitcond = icmp eq i32 %76, %39
> + br i1 %exitcond, label %.loopexit.us, label %.lr.ph.us
> +
> +.loopexit.us:
> + %.pre23.pre = load i32* %45, align 4
> + br label %._crit_edge27
> +
> +._crit_edge26:
> + %var4.15 = phi i32 [ %var4.09, %.lr.ph6..lr.ph6.split_crit_edge ], [ %78, %._crit_edge26 ]
> + %var5.03 = phi i32 [ 0, %.lr.ph6..lr.ph6.split_crit_edge ], [ %79, %._crit_edge26 ]
> + %77 = load i32* %52, align 4
> + %78 = add nsw i32 %77, %var4.15
> + %79 = add nsw i32 %var5.03, 1
> + %80 = icmp slt i32 %79, %46
> + br i1 %80, label %._crit_edge26, label %._crit_edge
> +
> +._crit_edge:
> + %split = phi i32 [ %66, %._crit_edge27 ], [ %78, %._crit_edge26 ]
> + %.pre25 = load i32* %19, align 4
> + br label %81
> +
> +; <label>:81
> + %82 = phi i32 [ %.pre25, %._crit_edge ], [ %30, %.lr.ph10 ]
> + %var4.1.lcssa = phi i32 [ %split, %._crit_edge ], [ %var4.09, %.lr.ph10 ]
> + %83 = add nsw i32 %ci.08, 1
> + %84 = icmp slt i32 %83, %82
> + br i1 %84, label %.lr.ph10, label %._crit_edge11
> +
> +._crit_edge11:
> + %85 = phi i32 [ %28, %.preheader7 ], [ %82, %81 ]
> + %86 = add i32 %var2.012, 1
> + %87 = icmp ugt i32 %86, %5
> + br i1 %87, label %._crit_edge14, label %.preheader7
> +
> +._crit_edge14:
> + %.pre21 = load i32* %13, align 4
> + br label %88
> +
> +; <label>:88
> + %89 = phi i32 [ %.pre21, %._crit_edge14 ], [ %25, %24 ]
> + store void (%struct.ref2*)* null, void (%struct.ref2*)** %18, align 4
> + %90 = add nsw i32 %var1.015, 1
> + %91 = icmp slt i32 %90, %89
> + br i1 %91, label %24, label %._crit_edge19
> +
> +._crit_edge19:
> + ret i32 3
> +}
>
> Added: llvm/trunk/test/CodeGen/X86/atom-call-reg-indirect-foldedreload64.ll
> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/atom-call-reg-indirect-foldedreload64.ll?rev=178193&view=auto
> ==============================================================================
> --- llvm/trunk/test/CodeGen/X86/atom-call-reg-indirect-foldedreload64.ll (added)
> +++ llvm/trunk/test/CodeGen/X86/atom-call-reg-indirect-foldedreload64.ll Wed Mar 27 18:16:18 2013
> @@ -0,0 +1,213 @@
> +; RUN: llc < %s -mtriple=x86_64-linux-gnu -mcpu=atom 2>&1 | \
> +; RUN: grep "callq" | not grep "("
> +; RUN: llc < %s -mtriple=x86_64-linux-gnu -mcpu=core2 2>&1 | \
> +; RUN: grep "callq" | grep "8-byte Folded Reload"
> +
> +%struct.targettype = type {i64}
> +%struct.op_ptr1 = type opaque
> +%struct.op_ptr2 = type opaque
> +%union.anon = type { [8 x i32], [48 x i8] }
> +%struct.const1 = type { [64 x i16], i8 }
> +%struct.const2 = type { [17 x i8], [256 x i8], i8 }
> +%struct.coef1 = type { %struct.ref1, i32, i32, i32, [10 x [64 x i16]*] }
> +
> +%struct.ref1 = type { void (%struct.ref2*)*, i32 (%struct.ref2*)*, void (%struct.ref2*)*, i32 (%struct.ref2*, i8***)*, %struct.op_ptr2** }
> +%struct.ref2 = type { %struct.localref13*, %struct.localref15*, %struct.localref12*, i8*, i8, i32, %struct.localref11*, i32, i32, i32, i32, i32, i32, i32, double, i8, i8, i32, i8, i8, i8, i32, i8, i32, i8, i8, i8, i32, i32, i32, i32, i32, i32, i8**, i32, i32, i32, i32, i32, [64 x i32]*, [4 x %struct.const1*], [4 x %struct.const2*], [4 x %struct.const2*], i32, %struct.ref3*, i8, i8, [16 x i8], [16 x i8], [16 x i8], i32, i8, i8, i8, i8, i16, i16, i8, i8, i8, %struct.localref10*, i32, i32, i32, i32, i8*, i32, [4 x %struct.ref3*], i32, i32, i32, [10 x i32], i32, i32, i32, i32, i32, %struct.localref8*, %struct.localref9*, %struct.ref1*, %struct.localref7*, %struct.localref6*, %struct.localref5*, %struct.localref1*, %struct.ref4*, %struct.localref2*, %struct.localref3*, %struct.localref4* }
> +%struct.ref3 = type { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i8, i32, i32, i32, i32, i32, i32, %struct.const1*, i8* }
> +%struct.ref4 = type { void (%struct.ref2*)*, [5 x void (%struct.ref2*, %struct.ref3*, i16*, i8**, i32)*] }
> +
> +%struct.localref1 = type { void (%struct.ref2*)*, i8 (%struct.ref2*, [64 x i16]**)*, i8 }
> +%struct.localref2 = type { void (%struct.ref2*)*, void (%struct.ref2*, i8***, i32*, i32, i8**, i32*, i32)*, i8 }
> +%struct.localref3 = type { void (%struct.ref2*)*, void (%struct.ref2*, i8***, i32, i8**, i32)* }
> +%struct.localref4 = type { {}*, void (%struct.ref2*, i8**, i8**, i32)*, void (%struct.ref2*)*, void (%struct.ref2*)* }
> +%struct.localref5 = type { void (%struct.ref2*)*, i32 (%struct.ref2*)*, i8 (%struct.ref2*)*, i8, i8, i32, i32 }
> +%struct.localref6 = type { i32 (%struct.ref2*)*, void (%struct.ref2*)*, void (%struct.ref2*)*, void (%struct.ref2*)*, i8, i8 }
> +%struct.localref7 = type { void (%struct.ref2*, i32)*, void (%struct.ref2*, i8***, i32*, i32, i8**, i32*, i32)* }
> +%struct.localref8 = type { void (%struct.ref2*)*, void (%struct.ref2*)*, i8 }
> +%struct.localref9 = type { void (%struct.ref2*, i32)*, void (%struct.ref2*, i8**, i32*, i32)* }
> +%struct.localref10 = type { %struct.localref10*, i8, i32, i32, i8* }
> +%struct.localref11 = type { i8*, %struct.targettype, void (%struct.ref2*)*, i8 (%struct.ref2*)*, void (%struct.ref2*, %struct.targettype)*, i8 (%struct.ref2*, i32)*, void (%struct.ref2*)* }
> +%struct.localref12 = type { {}*, %struct.targettype, %struct.targettype, i32, i32 }
> +%struct.localref13 = type { void (%struct.localref14*)*, void (%struct.localref14*, i32)*, void (%struct.localref14*)*, void (%struct.localref14*, i8*)*, void (%struct.localref14*)*, i32, %union.anon, i32, %struct.targettype, i8**, i32, i8**, i32, i32 }
> +%struct.localref14 = type { %struct.localref13*, %struct.localref15*, %struct.localref12*, i8*, i8, i32 }
> +%struct.localref15 = type { i8* (%struct.localref14*, i32, %struct.targettype)*, i8* (%struct.localref14*, i32, %struct.targettype)*, i8** (%struct.localref14*, i32, i32, i32)*, [64 x i16]** (%struct.localref14*, i32, i32, i32)*, %struct.op_ptr1* (%struct.localref14*, i32, i8, i32, i32, i32)*, %struct.op_ptr2* (%struct.localref14*, i32, i8, i32, i32, i32)*, {}*, i8** (%struct.localref14*, %struct.op_ptr1*, i32, i32, i8)*, [64 x i16]** (%struct.localref14*, %struct.op_ptr2*, i32, i32, i8)*, void (%struct.localref14*, i32)*, {}*, %struct.targettype, %struct.targettype}
> +
> +define internal i32 @foldedreload(%struct.ref2* %cinfo, i8*** nocapture %output1) {
> + %1 = getelementptr inbounds %struct.ref2* %cinfo, i64 0, i32 79
> + %2 = load %struct.ref1** %1, align 8
> + %3 = bitcast %struct.ref1* %2 to %struct.coef1*
> + %4 = getelementptr inbounds %struct.ref2* %cinfo, i64 0, i32 68
> + %5 = load i32* %4, align 4
> + %6 = add i32 %5, -1
> + %7 = getelementptr inbounds %struct.ref2* %cinfo, i64 0, i32 64
> + %8 = load i32* %7, align 4
> + %9 = add i32 %8, -1
> + %10 = getelementptr inbounds %struct.coef1* %3, i64 0, i32 2
> + %11 = load i32* %10, align 4
> + %12 = getelementptr inbounds %struct.ref1* %2, i64 1, i32 1
> + %13 = bitcast i32 (%struct.ref2*)** %12 to i32*
> + %14 = load i32* %13, align 4
> + %15 = icmp slt i32 %11, %14
> + br i1 %15, label %.lr.ph18, label %._crit_edge19
> +
> +.lr.ph18:
> + %16 = getelementptr inbounds %struct.ref1* %2, i64 1
> + %17 = bitcast %struct.ref1* %16 to i32*
> + %18 = getelementptr inbounds %struct.ref2* %cinfo, i64 0, i32 66
> + %19 = getelementptr inbounds %struct.ref2* %cinfo, i64 0, i32 84
> + %20 = getelementptr inbounds %struct.ref2* %cinfo, i64 0, i32 36
> + %21 = getelementptr inbounds %struct.ref1* %2, i64 1, i32 2
> + %22 = bitcast void (%struct.ref2*)** %21 to [10 x [64 x i16]*]*
> + %.pre = load i32* %17, align 4
> + br label %23
> +
> +; <label>:23
> + %24 = phi i32 [ %14, %.lr.ph18 ], [ %92, %91 ]
> + %25 = phi i32 [ %.pre, %.lr.ph18 ], [ 0, %91 ]
> + %var1.015 = phi i32 [ %11, %.lr.ph18 ], [ %93, %91 ]
> + %26 = icmp ugt i32 %25, %6
> + br i1 %26, label %91, label %.preheader7.lr.ph
> +
> +.preheader7.lr.ph:
> + %.pre24 = load i32* %18, align 4
> + br label %.preheader7
> +
> +.preheader7:
> + %27 = phi i32 [ %.pre24, %.preheader7.lr.ph ], [ %88, %._crit_edge11 ]
> + %var2.012 = phi i32 [ %25, %.preheader7.lr.ph ], [ %89, %._crit_edge11 ]
> + %28 = icmp sgt i32 %27, 0
> + br i1 %28, label %.lr.ph10, label %._crit_edge11
> +
> +.lr.ph10:
> + %29 = phi i32 [ %27, %.preheader7 ], [ %85, %84 ]
> + %indvars.iv21 = phi i64 [ 0, %.preheader7 ], [ %indvars.iv.next22, %84 ]
> + %var4.09 = phi i32 [ 0, %.preheader7 ], [ %var4.1.lcssa, %84 ]
> + %30 = getelementptr inbounds %struct.ref2* %cinfo, i64 0, i32 67, i64 %indvars.iv21
> + %31 = load %struct.ref3** %30, align 8
> + %32 = getelementptr inbounds %struct.ref3* %31, i64 0, i32 1
> + %33 = load i32* %32, align 4
> + %34 = sext i32 %33 to i64
> + %35 = load %struct.ref4** %19, align 8
> + %36 = getelementptr inbounds %struct.ref4* %35, i64 0, i32 1, i64 %34
> + %37 = load void (%struct.ref2*, %struct.ref3*, i16*, i8**, i32)** %36, align 8
> + %38 = getelementptr inbounds %struct.ref3* %31, i64 0, i32 17
> + %39 = load i32* %38, align 4
> + %40 = getelementptr inbounds %struct.ref3* %31, i64 0, i32 9
> + %41 = load i32* %40, align 4
> + %42 = getelementptr inbounds %struct.ref3* %31, i64 0, i32 16
> + %43 = load i32* %42, align 4
> + %44 = mul i32 %43, %var2.012
> + %45 = getelementptr inbounds %struct.ref3* %31, i64 0, i32 14
> + %46 = load i32* %45, align 4
> + %47 = icmp sgt i32 %46, 0
> + br i1 %47, label %.lr.ph6, label %84
> +
> +.lr.ph6:
> + %48 = mul nsw i32 %41, %var1.015
> + %49 = getelementptr inbounds i8*** %output1, i64 %34
> + %50 = sext i32 %48 to i64
> + %51 = load i8*** %49, align 8
> + %52 = getelementptr inbounds i8** %51, i64 %50
> + %53 = getelementptr inbounds %struct.ref3* %31, i64 0, i32 13
> + %54 = getelementptr inbounds %struct.ref3* %31, i64 0, i32 18
> + %55 = icmp sgt i32 %39, 0
> + br i1 %55, label %.lr.ph6.split.us, label %.lr.ph6..lr.ph6.split_crit_edge
> +
> +.lr.ph6..lr.ph6.split_crit_edge:
> + br label %._crit_edge28
> +
> +.lr.ph6.split.us:
> + %56 = phi i32 [ %64, %._crit_edge30 ], [ %46, %.lr.ph6 ]
> + %57 = phi i32 [ %65, %._crit_edge30 ], [ %41, %.lr.ph6 ]
> + %var4.15.us = phi i32 [ %67, %._crit_edge30 ], [ %var4.09, %.lr.ph6 ]
> + %output2.04.us = phi i8** [ %71, %._crit_edge30 ], [ %52, %.lr.ph6 ]
> + %var5.03.us = phi i32 [ %68, %._crit_edge30 ], [ 0, %.lr.ph6 ]
> + %58 = load i32* %20, align 4
> + %59 = icmp ult i32 %58, %9
> + br i1 %59, label %.lr.ph.us, label %60
> +
> +; <label>:60
> + %61 = add nsw i32 %var5.03.us, %var1.015
> + %62 = load i32* %54, align 4
> + %63 = icmp slt i32 %61, %62
> + br i1 %63, label %.lr.ph.us, label %._crit_edge29
> +
> +._crit_edge29:
> + %64 = phi i32 [ %.pre25.pre, %.loopexit.us ], [ %56, %60 ]
> + %65 = phi i32 [ %77, %.loopexit.us ], [ %57, %60 ]
> + %66 = load i32* %53, align 4
> + %67 = add nsw i32 %66, %var4.15.us
> + %68 = add nsw i32 %var5.03.us, 1
> + %69 = icmp slt i32 %68, %64
> + br i1 %69, label %._crit_edge30, label %._crit_edge
> +
> +._crit_edge30:
> + %70 = sext i32 %65 to i64
> + %71 = getelementptr inbounds i8** %output2.04.us, i64 %70
> + br label %.lr.ph6.split.us
> +
> +; <label>:72
> + %indvars.iv = phi i64 [ 0, %.lr.ph.us ], [ %indvars.iv.next, %72 ]
> + %var3.02.us = phi i32 [ %44, %.lr.ph.us ], [ %78, %72 ]
> + %73 = add nsw i64 %indvars.iv, %79
> + %74 = getelementptr inbounds [10 x [64 x i16]*]* %22, i64 0, i64 %73
> + %75 = load [64 x i16]** %74, align 8
> + %76 = getelementptr inbounds [64 x i16]* %75, i64 0, i64 0
> + tail call void %37(%struct.ref2* %cinfo, %struct.ref3* %31, i16* %76, i8** %output2.04.us, i32 %var3.02.us) nounwind
> + %77 = load i32* %40, align 4
> + %78 = add i32 %77, %var3.02.us
> + %indvars.iv.next = add i64 %indvars.iv, 1
> + %lftr.wideiv = trunc i64 %indvars.iv.next to i32
> + %exitcond = icmp eq i32 %lftr.wideiv, %39
> + br i1 %exitcond, label %.loopexit.us, label %72
> +
> +.loopexit.us:
> + %.pre25.pre = load i32* %45, align 4
> + br label %._crit_edge29
> +
> +.lr.ph.us:
> + %79 = sext i32 %var4.15.us to i64
> + br label %72
> +
> +._crit_edge28:
> + %var4.15 = phi i32 [ %var4.09, %.lr.ph6..lr.ph6.split_crit_edge ], [ %81, %._crit_edge28 ]
> + %var5.03 = phi i32 [ 0, %.lr.ph6..lr.ph6.split_crit_edge ], [ %82, %._crit_edge28 ]
> + %80 = load i32* %53, align 4
> + %81 = add nsw i32 %80, %var4.15
> + %82 = add nsw i32 %var5.03, 1
> + %83 = icmp slt i32 %82, %46
> + br i1 %83, label %._crit_edge28, label %._crit_edge
> +
> +._crit_edge:
> + %split = phi i32 [ %67, %._crit_edge29 ], [ %81, %._crit_edge28 ]
> + %.pre27 = load i32* %18, align 4
> + br label %84
> +
> +; <label>:84
> + %85 = phi i32 [ %.pre27, %._crit_edge ], [ %29, %.lr.ph10 ]
> + %var4.1.lcssa = phi i32 [ %split, %._crit_edge ], [ %var4.09, %.lr.ph10 ]
> + %indvars.iv.next22 = add i64 %indvars.iv21, 1
> + %86 = trunc i64 %indvars.iv.next22 to i32
> + %87 = icmp slt i32 %86, %85
> + br i1 %87, label %.lr.ph10, label %._crit_edge11
> +
> +._crit_edge11:
> + %88 = phi i32 [ %27, %.preheader7 ], [ %85, %84 ]
> + %89 = add i32 %var2.012, 1
> + %90 = icmp ugt i32 %89, %6
> + br i1 %90, label %._crit_edge14, label %.preheader7
> +
> +._crit_edge14:
> + %.pre23 = load i32* %13, align 4
> + br label %91
> +
> +; <label>:91
> + %92 = phi i32 [ %.pre23, %._crit_edge14 ], [ %24, %23 ]
> + store i32 0, i32* %17, align 4
> + %93 = add nsw i32 %var1.015, 1
> + %94 = icmp slt i32 %93, %92
> + br i1 %94, label %23, label %._crit_edge19
> +
> +._crit_edge19:
> + ret i32 3
> +}
>
> Modified: llvm/trunk/test/CodeGen/X86/movgs.ll
> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/movgs.ll?rev=178193&r1=178192&r2=178193&view=diff
> ==============================================================================
> --- llvm/trunk/test/CodeGen/X86/movgs.ll (original)
> +++ llvm/trunk/test/CodeGen/X86/movgs.ll Wed Mar 27 18:16:18 2013
> @@ -1,6 +1,6 @@
> -; RUN: llc < %s -march=x86 -mtriple=i386-linux-gnu -mattr=sse41 | FileCheck %s --check-prefix=X32
> -; RUN: llc < %s -mtriple=x86_64-linux -mattr=sse41 | FileCheck %s --check-prefix=X64
> -; RUN: llc < %s -mtriple=x86_64-win32 -mattr=sse41 | FileCheck %s --check-prefix=X64
> +; RUN: llc < %s -march=x86 -mtriple=i386-linux-gnu -mcpu=penryn -mattr=sse41 | FileCheck %s --check-prefix=X32
> +; RUN: llc < %s -mtriple=x86_64-linux -mcpu=penryn -mattr=sse41 | FileCheck %s --check-prefix=X64
> +; RUN: llc < %s -mtriple=x86_64-win32 -mcpu=penryn -mattr=sse41 | FileCheck %s --check-prefix=X64
>
> define i32 @test1() nounwind readonly {
> entry:
>
> Modified: llvm/trunk/test/CodeGen/X86/sibcall.ll
> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/sibcall.ll?rev=178193&r1=178192&r2=178193&view=diff
> ==============================================================================
> --- llvm/trunk/test/CodeGen/X86/sibcall.ll (original)
> +++ llvm/trunk/test/CodeGen/X86/sibcall.ll Wed Mar 27 18:16:18 2013
> @@ -1,5 +1,5 @@
> -; RUN: llc < %s -mtriple=i686-linux -mattr=+sse2 -asm-verbose=false | FileCheck %s -check-prefix=32
> -; RUN: llc < %s -mtriple=x86_64-linux -mattr=+sse2 -asm-verbose=false | FileCheck %s -check-prefix=64
> +; RUN: llc < %s -mtriple=i686-linux -mcpu=core2 -mattr=+sse2 -asm-verbose=false | FileCheck %s -check-prefix=32
> +; RUN: llc < %s -mtriple=x86_64-linux -mcpu=core2 -mattr=+sse2 -asm-verbose=false | FileCheck %s -check-prefix=64
>
> define void @t1(i32 %x) nounwind ssp {
> entry:
>
>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20130327/6539dcc2/attachment.html>
More information about the llvm-commits
mailing list