diff options
| -rw-r--r-- | lib/CodeGen/VirtRegRewriter.cpp | 8 | ||||
| -rw-r--r-- | test/CodeGen/ARM/2010-05-20-NEONSpillCrash.ll | 45 |
2 files changed, 52 insertions, 1 deletions
diff --git a/lib/CodeGen/VirtRegRewriter.cpp b/lib/CodeGen/VirtRegRewriter.cpp index 9c32480..871d836 100644 --- a/lib/CodeGen/VirtRegRewriter.cpp +++ b/lib/CodeGen/VirtRegRewriter.cpp @@ -1895,6 +1895,11 @@ LocalRewriter::RewriteMBB(LiveIntervals *LIs, // Clear kill info. SmallSet<unsigned, 2> KilledMIRegs; + + // Keep track of the registers we have already spilled in case there are + // multiple defs of the same register in MI. + SmallSet<unsigned, 8> SpilledMIRegs; + RegKills.reset(); KillOps.clear(); KillOps.resize(TRI->getNumRegs(), NULL); @@ -2412,6 +2417,7 @@ LocalRewriter::RewriteMBB(LiveIntervals *LIs, } // Process all of the spilled defs. + SpilledMIRegs.clear(); for (unsigned i = 0, e = MI.getNumOperands(); i != e; ++i) { MachineOperand &MO = MI.getOperand(i); if (!(MO.isReg() && MO.getReg() && MO.isDef())) @@ -2505,7 +2511,7 @@ LocalRewriter::RewriteMBB(LiveIntervals *LIs, MI.getOperand(i).setReg(RReg); MI.getOperand(i).setSubReg(0); - if (!MO.isDead()) { + if (!MO.isDead() && SpilledMIRegs.insert(VirtReg)) { MachineInstr *&LastStore = MaybeDeadStores[StackSlot]; SpillRegToStackSlot(MII, -1, PhysReg, StackSlot, RC, true, LastStore, Spills, ReMatDefs, RegKills, KillOps); diff --git a/test/CodeGen/ARM/2010-05-20-NEONSpillCrash.ll b/test/CodeGen/ARM/2010-05-20-NEONSpillCrash.ll new file mode 100644 index 0000000..b6fbf9b --- /dev/null +++ b/test/CodeGen/ARM/2010-05-20-NEONSpillCrash.ll @@ -0,0 +1,45 @@ +; RUN: llc < %s -march=arm -mattr=+neon -O0 + +; This test would crash the rewriter when trying to handle a spill after one of +; the @llvm.arm.neon.vld3.v8i8 defined three parts of a register. + +%struct.__neon_int8x8x3_t = type { <8 x i8>, <8 x i8>, <8 x i8> } + +declare %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8*) nounwind readonly + +declare void @llvm.arm.neon.vst3.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>) nounwind + +define <8 x i8> @t3(i8* %A1, i8* %A2, i8* %A3, i8* %A4, i8* %A5, i8* %A6, i8* %A7, i8* %A8, i8* %B) nounwind { + %tmp1b = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A2) ; <%struct.__neon_int8x8x3_t> [#uses=2] + %tmp2b = extractvalue %struct.__neon_int8x8x3_t %tmp1b, 0 ; <<8 x i8>> [#uses=1] + %tmp4b = extractvalue %struct.__neon_int8x8x3_t %tmp1b, 1 ; <<8 x i8>> [#uses=1] + %tmp1d = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A4) ; <%struct.__neon_int8x8x3_t> [#uses=2] + %tmp2d = extractvalue %struct.__neon_int8x8x3_t %tmp1d, 0 ; <<8 x i8>> [#uses=1] + %tmp4d = extractvalue %struct.__neon_int8x8x3_t %tmp1d, 1 ; <<8 x i8>> [#uses=1] + %tmp1e = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A5) ; <%struct.__neon_int8x8x3_t> [#uses=1] + %tmp2e = extractvalue %struct.__neon_int8x8x3_t %tmp1e, 0 ; <<8 x i8>> [#uses=1] + %tmp1f = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A6) ; <%struct.__neon_int8x8x3_t> [#uses=1] + %tmp2f = extractvalue %struct.__neon_int8x8x3_t %tmp1f, 0 ; <<8 x i8>> [#uses=1] + %tmp1g = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A7) ; <%struct.__neon_int8x8x3_t> [#uses=2] + %tmp2g = extractvalue %struct.__neon_int8x8x3_t %tmp1g, 0 ; <<8 x i8>> [#uses=1] + %tmp4g = extractvalue %struct.__neon_int8x8x3_t %tmp1g, 1 ; <<8 x i8>> [#uses=1] + %tmp1h = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A8) ; <%struct.__neon_int8x8x3_t> [#uses=2] + %tmp2h = extractvalue %struct.__neon_int8x8x3_t %tmp1h, 0 ; <<8 x i8>> [#uses=1] + %tmp3h = extractvalue %struct.__neon_int8x8x3_t %tmp1h, 2 ; <<8 x i8>> [#uses=1] + %tmp2bd = add <8 x i8> %tmp2b, %tmp2d ; <<8 x i8>> [#uses=1] + %tmp4bd = add <8 x i8> %tmp4b, %tmp4d ; <<8 x i8>> [#uses=1] + %tmp2abcd = mul <8 x i8> undef, %tmp2bd ; <<8 x i8>> [#uses=1] + %tmp4abcd = mul <8 x i8> undef, %tmp4bd ; <<8 x i8>> [#uses=2] + call void @llvm.arm.neon.vst3.v8i8(i8* %A1, <8 x i8> %tmp4abcd, <8 x i8> zeroinitializer, <8 x i8> %tmp2abcd) + %tmp2ef = sub <8 x i8> %tmp2e, %tmp2f ; <<8 x i8>> [#uses=1] + %tmp2gh = sub <8 x i8> %tmp2g, %tmp2h ; <<8 x i8>> [#uses=1] + %tmp3gh = sub <8 x i8> zeroinitializer, %tmp3h ; <<8 x i8>> [#uses=1] + %tmp4ef = sub <8 x i8> zeroinitializer, %tmp4g ; <<8 x i8>> [#uses=1] + %tmp2efgh = mul <8 x i8> %tmp2ef, %tmp2gh ; <<8 x i8>> [#uses=1] + %tmp3efgh = mul <8 x i8> undef, %tmp3gh ; <<8 x i8>> [#uses=1] + %tmp4efgh = mul <8 x i8> %tmp4ef, undef ; <<8 x i8>> [#uses=2] + call void @llvm.arm.neon.vst3.v8i8(i8* %A2, <8 x i8> %tmp4efgh, <8 x i8> %tmp3efgh, <8 x i8> %tmp2efgh) + %tmp4 = sub <8 x i8> %tmp4efgh, %tmp4abcd ; <<8 x i8>> [#uses=1] + tail call void @llvm.arm.neon.vst3.v8i8(i8* %B, <8 x i8> zeroinitializer, <8 x i8> undef, <8 x i8> undef) + ret <8 x i8> %tmp4 +} |