Allow a register to be redefined multiple times in a basic block.

LiveVariableAnalysis was a bit picky about a register only being redefined once,
but that really isn't necessary.

Here is an example of chained INSERT_SUBREGs that we can handle now:

68      %reg1040<def> = INSERT_SUBREG %reg1040, %reg1028<kill>, 14
                register: %reg1040 +[70,134:0)
76      %reg1040<def> = INSERT_SUBREG %reg1040, %reg1029<kill>, 13
                register: %reg1040 replace range with [70,78:1) RESULT: %reg1040,0.000000e+00 = [70,78:1)[78,134:0)  0@78-(134) 1@70-(78)
84      %reg1040<def> = INSERT_SUBREG %reg1040, %reg1030<kill>, 12
                register: %reg1040 replace range with [78,86:2) RESULT: %reg1040,0.000000e+00 = [70,78:1)[78,86:2)[86,134:0)  0@86-(134) 1@70-(78) 2@78-(86)
92      %reg1040<def> = INSERT_SUBREG %reg1040, %reg1031<kill>, 11
                register: %reg1040 replace range with [86,94:3) RESULT: %reg1040,0.000000e+00 = [70,78:1)[78,86:2)[86,94:3)[94,134:0)  0@94-(134) 1@70-(78) 2@78-(86) 3@86-(94)

rdar://problem/8096390

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@106152 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/LiveIntervalAnalysis.cpp b/lib/CodeGen/LiveIntervalAnalysis.cpp
index 349ea2c446ce8368e56b9aa7b8ebb776999a4a63..22d62524f39bd8a5ba64a6aa0e6ca9c522b531f6 100644 (file)
--- a/lib/CodeGen/LiveIntervalAnalysis.cpp
+++ b/lib/CodeGen/LiveIntervalAnalysis.cpp
@@ -434,11 +434,6 @@ void LiveIntervals::handleVirtualRegisterDef(MachineBasicBlock *mbb,
       // are actually two values in the live interval.  Because of this we
       // need to take the LiveRegion that defines this register and split it
       // into two values.
-      // Two-address vregs should always only be redefined once.  This means
-      // that at this point, there should be exactly one value number in it.
-      assert((PartReDef || interval.containsOneValue()) &&
-             "Unexpected 2-addr liveint!");
-      SlotIndex DefIndex = interval.getValNumInfo(0)->def.getDefIndex();
       SlotIndex RedefIndex = MIIdx.getDefIndex();
       if (MO.isEarlyClobber())
         RedefIndex = MIIdx.getUseIndex();
@@ -446,8 +441,9 @@ void LiveIntervals::handleVirtualRegisterDef(MachineBasicBlock *mbb,
       const LiveRange *OldLR =
         interval.getLiveRangeContaining(RedefIndex.getUseIndex());
       VNInfo *OldValNo = OldLR->valno;
+      SlotIndex DefIndex = OldValNo->def.getDefIndex();
 
-      // Delete the initial value, which should be short and continuous,
+      // Delete the previous value, which should be short and continuous,
       // because the 2-addr copy must be in the same MBB as the redef.
       interval.removeRange(DefIndex, RedefIndex);
 

diff --git a/test/CodeGen/Thumb2/crash.ll b/test/CodeGen/Thumb2/crash.ll
new file mode 100644 (file)
index 0000000..19b1d25
--- /dev/null
+++ b/test/CodeGen/Thumb2/crash.ll
@@ -0,0 +1,21 @@
+; RUN: llc < %s -mtriple=thumbv7-apple-darwin -mcpu=cortex-a8
+target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f32:32:32-f64:32:32-v64:64:64-v128:128:128-a0:0:32-n32"
+target triple = "thumbv7-apple-darwin10"
+
+; This function would crash LiveIntervalAnalysis by creating a chain of 4 INSERT_SUBREGs of the same register.
+define arm_apcscc void @NEON_vst4q_u32(i32* nocapture %sp0, i32* nocapture %sp1, i32* nocapture %sp2, i32* nocapture %sp3, i32* %dp) nounwind {
+entry:
+  %0 = bitcast i32* %sp0 to <4 x i32>*            ; <<4 x i32>*> [#uses=1]
+  %1 = load <4 x i32>* %0, align 16               ; <<4 x i32>> [#uses=1]
+  %2 = bitcast i32* %sp1 to <4 x i32>*            ; <<4 x i32>*> [#uses=1]
+  %3 = load <4 x i32>* %2, align 16               ; <<4 x i32>> [#uses=1]
+  %4 = bitcast i32* %sp2 to <4 x i32>*            ; <<4 x i32>*> [#uses=1]
+  %5 = load <4 x i32>* %4, align 16               ; <<4 x i32>> [#uses=1]
+  %6 = bitcast i32* %sp3 to <4 x i32>*            ; <<4 x i32>*> [#uses=1]
+  %7 = load <4 x i32>* %6, align 16               ; <<4 x i32>> [#uses=1]
+  %8 = bitcast i32* %dp to i8*                    ; <i8*> [#uses=1]
+  tail call void @llvm.arm.neon.vst4.v4i32(i8* %8, <4 x i32> %1, <4 x i32> %3, <4 x i32> %5, <4 x i32> %7)
+  ret void
+}
+
+declare void @llvm.arm.neon.vst4.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>) nounwind