[llvm] r363802 - [TargetLowering] SimplifyDemandedBits SIGN_EXTEND_VECTOR_INREG -> ANY/ZERO_EXTEND_VECTOR_INREG

Simon Pilgrim via llvm-commits llvm-commits at lists.llvm.org
Tue Jun 25 00:37:50 PDT 2019


Is this on X86 or some other target? The SimplifyDemanded* functions can 
be a little quick to change opcodes without proper legal op testing....

If you can send me a repro I'll take a look.

Simon.

On 25/06/2019 00:58, Eric Christopher wrote:
> Hi Simon,
>
> I'm seeing at least one occurrence of "fatal error: error in backend:
> Cannot emit physreg copy instruction" after this patch attempting to
> build an mp4 library. I'm not entirely sure from where or how (inline
> assembly, normal code, etc), but wanted to let you know as we
> investigate. The code has, of course, been building up to this point
> so my inclination is to revert and get a testcase reduced out of the
> sources.
>
> Thoughts?
>
> -eric
>
> On Wed, Jun 19, 2019 at 6:54 AM Simon Pilgrim via llvm-commits
> <llvm-commits at lists.llvm.org> wrote:
>> Author: rksimon
>> Date: Wed Jun 19 06:58:02 2019
>> New Revision: 363802
>>
>> URL: http://llvm.org/viewvc/llvm-project?rev=363802&view=rev
>> Log:
>> [TargetLowering] SimplifyDemandedBits SIGN_EXTEND_VECTOR_INREG -> ANY/ZERO_EXTEND_VECTOR_INREG
>>
>> Simplify SIGN_EXTEND_VECTOR_INREG if the extended bits are not required/known zero.
>>
>> Matches what we already do for SIGN_EXTEND.
>>
>> Modified:
>>      llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp
>>      llvm/trunk/test/CodeGen/X86/pmul.ll
>>      llvm/trunk/test/CodeGen/X86/xop-ifma.ll
>>
>> Modified: llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp
>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp?rev=363802&r1=363801&r2=363802&view=diff
>> ==============================================================================
>> --- llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp (original)
>> +++ llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp Wed Jun 19 06:58:02 2019
>> @@ -1413,9 +1413,11 @@ bool TargetLowering::SimplifyDemandedBit
>>       bool IsVecInReg = Op.getOpcode() == ISD::SIGN_EXTEND_VECTOR_INREG;
>>
>>       // If none of the top bits are demanded, convert this into an any_extend.
>> -    // TODO: Add SIGN_EXTEND_VECTOR_INREG - ANY_EXTEND_VECTOR_INREG fold.
>> -    if (DemandedBits.getActiveBits() <= InBits && !IsVecInReg)
>> -      return TLO.CombineTo(Op, TLO.DAG.getNode(ISD::ANY_EXTEND, dl, VT, Src));
>> +    if (DemandedBits.getActiveBits() <= InBits)
>> +      return TLO.CombineTo(
>> +          Op, TLO.DAG.getNode(IsVecInReg ? ISD::ANY_EXTEND_VECTOR_INREG
>> +                                         : ISD::ANY_EXTEND,
>> +                              dl, VT, Src));
>>
>>       APInt InDemandedBits = DemandedBits.trunc(InBits);
>>       APInt InDemandedElts = DemandedElts.zextOrSelf(InElts);
>> @@ -1434,9 +1436,11 @@ bool TargetLowering::SimplifyDemandedBit
>>       Known = Known.sext(BitWidth);
>>
>>       // If the sign bit is known zero, convert this to a zero extend.
>> -    // TODO: Add SIGN_EXTEND_VECTOR_INREG - ZERO_EXTEND_VECTOR_INREG fold.
>> -    if (Known.isNonNegative() && !IsVecInReg)
>> -      return TLO.CombineTo(Op, TLO.DAG.getNode(ISD::ZERO_EXTEND, dl, VT, Src));
>> +    if (Known.isNonNegative())
>> +      return TLO.CombineTo(
>> +          Op, TLO.DAG.getNode(IsVecInReg ? ISD::ZERO_EXTEND_VECTOR_INREG
>> +                                         : ISD::ZERO_EXTEND,
>> +                              dl, VT, Src));
>>       break;
>>     }
>>     case ISD::ANY_EXTEND: {
>>
>> Modified: llvm/trunk/test/CodeGen/X86/pmul.ll
>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/pmul.ll?rev=363802&r1=363801&r2=363802&view=diff
>> ==============================================================================
>> --- llvm/trunk/test/CodeGen/X86/pmul.ll (original)
>> +++ llvm/trunk/test/CodeGen/X86/pmul.ll Wed Jun 19 06:58:02 2019
>> @@ -1326,15 +1326,13 @@ define <8 x i64> @mul_v8i64_sext(<8 x i1
>>   ; SSE41-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[1,1,2,3]
>>   ; SSE41-NEXT:    pmovsxwq %xmm3, %xmm6
>>   ; SSE41-NEXT:    pmovsxwq %xmm0, %xmm7
>> -; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[2,3,0,1]
>> -; SSE41-NEXT:    pmovsxdq %xmm0, %xmm3
>> +; SSE41-NEXT:    pshufd {{.*#+}} xmm3 = xmm2[2,2,3,3]
>>   ; SSE41-NEXT:    pmuldq %xmm4, %xmm3
>> -; SSE41-NEXT:    pmovsxdq %xmm2, %xmm2
>> +; SSE41-NEXT:    pmovzxdq {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero
>>   ; SSE41-NEXT:    pmuldq %xmm5, %xmm2
>> -; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
>> -; SSE41-NEXT:    pmovsxdq %xmm0, %xmm4
>> +; SSE41-NEXT:    pshufd {{.*#+}} xmm4 = xmm1[2,2,3,3]
>>   ; SSE41-NEXT:    pmuldq %xmm6, %xmm4
>> -; SSE41-NEXT:    pmovsxdq %xmm1, %xmm0
>> +; SSE41-NEXT:    pmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
>>   ; SSE41-NEXT:    pmuldq %xmm7, %xmm0
>>   ; SSE41-NEXT:    movdqa %xmm4, %xmm1
>>   ; SSE41-NEXT:    retq
>>
>> Modified: llvm/trunk/test/CodeGen/X86/xop-ifma.ll
>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/xop-ifma.ll?rev=363802&r1=363801&r2=363802&view=diff
>> ==============================================================================
>> --- llvm/trunk/test/CodeGen/X86/xop-ifma.ll (original)
>> +++ llvm/trunk/test/CodeGen/X86/xop-ifma.ll Wed Jun 19 06:58:02 2019
>> @@ -67,12 +67,10 @@ define <8 x i32> @test_mul_v8i32_add_v8i
>>   define <4 x i64> @test_mulx_v4i32_add_v4i64(<4 x i32> %a0, <4 x i32> %a1, <4 x i64> %a2) {
>>   ; XOP-AVX1-LABEL: test_mulx_v4i32_add_v4i64:
>>   ; XOP-AVX1:       # %bb.0:
>> -; XOP-AVX1-NEXT:    vpmovsxdq %xmm0, %xmm3
>> -; XOP-AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
>> -; XOP-AVX1-NEXT:    vpmovsxdq %xmm0, %xmm0
>> -; XOP-AVX1-NEXT:    vpmovsxdq %xmm1, %xmm4
>> -; XOP-AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
>> -; XOP-AVX1-NEXT:    vpmovsxdq %xmm1, %xmm1
>> +; XOP-AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm3 = xmm0[0],zero,xmm0[1],zero
>> +; XOP-AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,1,3,3]
>> +; XOP-AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm4 = xmm1[0],zero,xmm1[1],zero
>> +; XOP-AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,1,3,3]
>>   ; XOP-AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm5
>>   ; XOP-AVX1-NEXT:    vpmacsdql %xmm5, %xmm1, %xmm0, %xmm0
>>   ; XOP-AVX1-NEXT:    vpmacsdql %xmm2, %xmm4, %xmm3, %xmm1
>>
>>
>> _______________________________________________
>> llvm-commits mailing list
>> llvm-commits at lists.llvm.org
>> https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits


More information about the llvm-commits mailing list