[llvm] r364557 - Recommit [PowerPC] Update P9 vector costs for insert/extract element

Jordan Rupprecht via llvm-commits llvm-commits at lists.llvm.org
Mon Jul 1 22:08:32 PDT 2019


Here's as far as I could get:

$ cat repro.ll
source_filename = "repro.ll"
target datalayout = "e-m:e-i64:64-n32:64"
target triple = "powerpc64le-grtev4-linux-gnu"

define dso_local void @foo() {
  %1 = tail call i64 @bar()
  %2 = insertelement <2 x i64> undef, i64 %1, i32 1
  %3 = sext <2 x i64> %2 to <2 x i128>
  %4 = sub nsw <2 x i128> zeroinitializer, %3
  %5 = icmp slt <2 x i128> %4, <i128 1, i128 1>
  %6 = select <2 x i1> %5, <2 x i128> %4, <2 x i128> <i128 1, i128 1>
  %7 = trunc <2 x i128> %6 to <2 x i64>
  %8 = shl <2 x i64> %7, <i64 32, i64 32>
  %9 = ashr exact <2 x i64> %8, <i64 32, i64 32>
  store <2 x i64> %9, <2 x i64>* undef, align 8
  ret void
}

declare i64 @bar()

$ llc repro.ll
LLVM ERROR: Cannot select: t56: v1i128 = smin t54, t122
  t54: v1i128 = sub nsw t123, t102
    t123: v1i128 = bitcast t108
      t108: v4i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>,
Constant:i32<0>, Constant:i32<0>
        t107: i32 = Constant<0>
        t107: i32 = Constant<0>
        t107: i32 = Constant<0>
        t107: i32 = Constant<0>
    t102: v1i128 = bitcast t101
      t101: v2i64 = BUILD_VECTOR t12, t100
        t12: i64,ch,glue = CopyFromReg t10, Register:i64 $x3, t10:1
          t11: i64 = Register $x3
          t10: ch,glue = callseq_end t9, TargetConstant:i64<32>,
TargetConstant:i64<0>, t9:1
            t2: i64 = TargetConstant<32>
            t3: i64 = TargetConstant<0>
            t9: ch,glue = PPCISD::CALL_NOP t4, TargetGlobalAddress:i64<i64
()* @bar> 0, Register:i64 $x2, RegisterMask:Untyped


              t6: i64 = TargetGlobalAddress<i64 ()* @bar> 0
              t7: i64 = Register $x2
              t8: Untyped = RegisterMask
        t100: i64 = sra t12, Constant:i32<63>
          t12: i64,ch,glue = CopyFromReg t10, Register:i64 $x3, t10:1
            t11: i64 = Register $x3
            t10: ch,glue = callseq_end t9, TargetConstant:i64<32>,
TargetConstant:i64<0>, t9:1
              t2: i64 = TargetConstant<32>
              t3: i64 = TargetConstant<0>
              t9: ch,glue = PPCISD::CALL_NOP t4,
TargetGlobalAddress:i64<i64 ()* @bar> 0, Register:i64 $x2,
RegisterMask:Untyped

                t6: i64 = TargetGlobalAddress<i64 ()* @bar> 0
                t7: i64 = Register $x2
                t8: Untyped = RegisterMask
          t99: i32 = Constant<63>
  t122: v1i128 = bitcast t121
    t121: v2f64,ch = PPCISD::XXSWAPD t120:1, t120
      t120: v2f64,ch = PPCISD::LXVD2X<(load 16 from constant-pool)> t0, t113
        t113: i64,ch = PPCISD::TOC_ENTRY<(load 8 from got)>
TargetConstantPool:i64<<2 x i64> <i64 1, i64 0>> 0, Register:i64 $x2


          t112: i64 = TargetConstantPool<<2 x i64> <i64 1, i64 0>> 0
          t7: i64 = Register $x2
In function: foo

On Mon, Jul 1, 2019 at 5:12 PM Eric Christopher <echristo at gmail.com> wrote:

> Thanks Jordan!
>
> On Mon, Jul 1, 2019, 4:34 PM Jordan Rupprecht <rupprecht at google.com>
> wrote:
>
>> Reverted in r364876. I'm not sure which of Eric or myself is busier, but
>> I'll also try to get a reproducer.
>>
>> On Fri, Jun 28, 2019 at 6:32 PM Eric Christopher via llvm-commits <
>> llvm-commits at lists.llvm.org> wrote:
>>
>>> Hi Roland,
>>>
>>> I'm seeing an instruction selection crash with this on some internal
>>> code:
>>>
>>> fatal error: error in backend: Cannot select: 0x7fffbabb30d0: v1i128 =
>>> smin 0x7fffbabb3000, 0x7fffbb233820
>>>   0x7fffbabb3000: v1i128 = smax 0x7fffbb233f08, 0x7fffbabb3958
>>>     0x7fffbb233f08: v1i128 = add nsw 0x7fffbabf4820, 0x7fffbabf4a90
>>>       0x7fffbabf4820: v1i128 = bitcast 0x7fffbb233138
>>>         0x7fffbb233138: v2i64 = BUILD_VECTOR 0x7fffbabf48f0,
>>> 0x7fffbb233750
>>>           0x7fffbabf48f0: i64 = extract_vector_elt 0x7fffbb233478,
>>> Constant:i64<0>
>>>             0x7fffbb233478: v2i64,ch = CopyFromReg 0x7fffbb5c8058,
>>> Register:v2i64 %1
>>>               0x7fffbb233410: v2i64 = Register %1
>>>             0x7fffbb233068: i64 = Constant<0>
>>>           0x7fffbb233750: i64 = sra 0x7fffbabf48f0, Constant:i32<63>
>>>             0x7fffbabf48f0: i64 = extract_vector_elt 0x7fffbb233478,
>>> Constant:i64<0>
>>>               0x7fffbb233478: v2i64,ch = CopyFromReg 0x7fffbb5c8058,
>>> Register:v2i64 %1
>>>                 0x7fffbb233410: v2i64 = Register %1
>>>               0x7fffbb233068: i64 = Constant<0>
>>>             0x7fffbb233a28: i32 = Constant<63>
>>>       0x7fffbabf4a90: v1i128 = bitcast 0x7fffbb233af8
>>>         0x7fffbb233af8: v2i64 = BUILD_VECTOR 0x7fffbabf4958,
>>> 0x7fffbabf4750
>>>           0x7fffbabf4958: i64,ch = CopyFromReg 0x7fffbb5c8058,
>>> Register:i64 %3
>>>             0x7fffbb2333a8: i64 = Register %3
>>>           0x7fffbabf4750: i64 = sra 0x7fffbabf4958, Constant:i32<63>
>>>             0x7fffbabf4958: i64,ch = CopyFromReg 0x7fffbb5c8058,
>>> Register:i64 %3
>>>               0x7fffbb2333a8: i64 = Register %3
>>>             0x7fffbb233a28: i32 = Constant<63>
>>>     0x7fffbabb3958: v1i128 = bitcast 0x7fffbabb3618
>>>       0x7fffbabb3618: v4i32 = BUILD_VECTOR Constant:i32<0>,
>>> Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
>>>         0x7fffbb2338f0: i32 = Constant<0>
>>>         0x7fffbb2338f0: i32 = Constant<0>
>>>         0x7fffbb2338f0: i32 = Constant<0>
>>>         0x7fffbb2338f0: i32 = Constant<0>
>>>   0x7fffbb233820: v1i128 = bitcast 0x7fffbabf44e0
>>>     0x7fffbabf44e0: v2f64,ch = PPCISD::XXSWAPD 0x7fffbabf4a28:1,
>>> 0x7fffbabf4a28
>>>       0x7fffbabf4a28: v2f64,ch = PPCISD::LXVD2X<(load 16 from
>>> constant-pool)> 0x7fffbb5c8058, 0x7fffbb233340
>>>         0x7fffbb233340: i64,ch = PPCISD::TOC_ENTRY<(load 8 from got)>
>>> TargetConstantPool:i64<<2 x i64> <i64 9223372036854775807, i64 0>> 0,
>>> Register:i64 $x2
>>>           0x7fffbabb3548: i64 = TargetConstantPool<<2 x i64> <i64
>>> 9223372036854775807, i64 0>> 0
>>>           0x7fffbb2330d0: i64 = Register $x2
>>>
>>> Working on getting it reduced down so you've got a testcase, but I'd
>>> like to revert this in the mean time. FWIW once I get a testcase I
>>> probably will because it's already late on a Friday and you're OoO I'd
>>> imagine :)
>>>
>>> Thanks!
>>>
>>> -eric
>>>
>>> On Thu, Jun 27, 2019 at 9:20 AM Roland Froese via llvm-commits
>>> <llvm-commits at lists.llvm.org> wrote:
>>> >
>>> > Author: froese
>>> > Date: Thu Jun 27 09:20:24 2019
>>> > New Revision: 364557
>>> >
>>> > URL: http://llvm.org/viewvc/llvm-project?rev=364557&view=rev
>>> > Log:
>>> > Recommit [PowerPC] Update P9 vector costs for insert/extract element
>>> >
>>> > Recommit patch D60160 after regression fix patch D63463.
>>> >
>>> > Modified:
>>> >     llvm/trunk/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
>>> >     llvm/trunk/test/Analysis/CostModel/PowerPC/insert_extract.ll
>>> >
>>> > Modified: llvm/trunk/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
>>> > URL:
>>> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/PowerPC/PPCTargetTransformInfo.cpp?rev=364557&r1=364556&r2=364557&view=diff
>>> >
>>> ==============================================================================
>>> > --- llvm/trunk/lib/Target/PowerPC/PPCTargetTransformInfo.cpp (original)
>>> > +++ llvm/trunk/lib/Target/PowerPC/PPCTargetTransformInfo.cpp Thu Jun
>>> 27 09:20:24 2019
>>> > @@ -752,6 +752,35 @@ int PPCTTIImpl::getVectorInstrCost(unsig
>>> >        return 0;
>>> >
>>> >      return Cost;
>>> > +
>>> > +  } else if (Val->getScalarType()->isIntegerTy() && Index != -1U) {
>>> > +    if (ST->hasP9Altivec()) {
>>> > +      if (ISD == ISD::INSERT_VECTOR_ELT)
>>> > +        // A move-to VSR and a permute/insert.  Assume vector
>>> operation cost
>>> > +        // for both (cost will be 2x on P9).
>>> > +        return vectorCostAdjustment(2, Opcode, Val, nullptr);
>>> > +
>>> > +      // It's an extract.  Maybe we can do a cheap move-from VSR.
>>> > +      unsigned EltSize = Val->getScalarSizeInBits();
>>> > +      if (EltSize == 64) {
>>> > +        unsigned MfvsrdIndex = ST->isLittleEndian() ? 1 : 0;
>>> > +        if (Index == MfvsrdIndex)
>>> > +          return 1;
>>> > +      } else if (EltSize == 32) {
>>> > +        unsigned MfvsrwzIndex = ST->isLittleEndian() ? 2 : 1;
>>> > +        if (Index == MfvsrwzIndex)
>>> > +          return 1;
>>> > +      }
>>> > +
>>> > +      // We need a vector extract (or mfvsrld).  Assume vector
>>> operation cost.
>>> > +      // The cost of the load constant for a vector extract is
>>> disregarded
>>> > +      // (invariant, easily schedulable).
>>> > +      return vectorCostAdjustment(1, Opcode, Val, nullptr);
>>> > +
>>> > +    } else if (ST->hasDirectMove())
>>> > +      // Assume permute has standard cost.
>>> > +      // Assume move-to/move-from VSR have 2x standard cost.
>>> > +      return 3;
>>> >    }
>>> >
>>> >    // Estimated cost of a load-hit-store delay.  This was obtained
>>> >
>>> > Modified: llvm/trunk/test/Analysis/CostModel/PowerPC/insert_extract.ll
>>> > URL:
>>> http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Analysis/CostModel/PowerPC/insert_extract.ll?rev=364557&r1=364556&r2=364557&view=diff
>>> >
>>> ==============================================================================
>>> > --- llvm/trunk/test/Analysis/CostModel/PowerPC/insert_extract.ll
>>> (original)
>>> > +++ llvm/trunk/test/Analysis/CostModel/PowerPC/insert_extract.ll Thu
>>> Jun 27 09:20:24 2019
>>> > @@ -14,15 +14,15 @@ define i32 @insert(i32 %arg) {
>>> >  ; CHECK-P7-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret i32 undef
>>> >  ;
>>> >  ; CHECK-P8LE-LABEL: 'insert'
>>> > -; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 10 for
>>> instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0
>>> > +; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 3 for
>>> instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0
>>> >  ; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret i32 undef
>>> >  ;
>>> >  ; CHECK-P9BE-LABEL: 'insert'
>>> > -; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 11 for
>>> instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0
>>> > +; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0
>>> >  ; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret i32 undef
>>> >  ;
>>> >  ; CHECK-P9LE-LABEL: 'insert'
>>> > -; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 11 for
>>> instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0
>>> > +; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0
>>> >  ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret i32 undef
>>> >  ;
>>> >    %x = insertelement <4 x i32> undef, i32 %arg, i32 0
>>> > @@ -40,11 +40,11 @@ define i32 @extract(<4 x i32> %arg) {
>>> >  ; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret i32 %x
>>> >  ;
>>> >  ; CHECK-P9BE-LABEL: 'extract'
>>> > -; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %x = extractelement <4 x i32> %arg, i32 0
>>> > +; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %x = extractelement <4 x i32> %arg, i32 0
>>> >  ; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret i32 %x
>>> >  ;
>>> >  ; CHECK-P9LE-LABEL: 'extract'
>>> > -; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %x = extractelement <4 x i32> %arg, i32 0
>>> > +; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %x = extractelement <4 x i32> %arg, i32 0
>>> >  ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret i32 %x
>>> >  ;
>>> >    %x = extractelement <4 x i32> %arg, i32 0
>>> > @@ -83,15 +83,15 @@ define void @test4xi32(<4 x i32> %v1, i3
>>> >  ; CHECK-P7-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret void
>>> >  ;
>>> >  ; CHECK-P8LE-LABEL: 'test4xi32'
>>> > -; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 10 for
>>> instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
>>> > +; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 3 for
>>> instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
>>> >  ; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret void
>>> >  ;
>>> >  ; CHECK-P9BE-LABEL: 'test4xi32'
>>> > -; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 11 for
>>> instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
>>> > +; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
>>> >  ; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret void
>>> >  ;
>>> >  ; CHECK-P9LE-LABEL: 'test4xi32'
>>> > -; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 11 for
>>> instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
>>> > +; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
>>> >  ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret void
>>> >  ;
>>> >    %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
>>> > @@ -114,17 +114,17 @@ define void @vexti32(<4 x i32> %p1) {
>>> >  ; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret void
>>> >  ;
>>> >  ; CHECK-P9BE-LABEL: 'vexti32'
>>> > -; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i1 = extractelement <4 x i32> %p1, i32 0
>>> > -; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i2 = extractelement <4 x i32> %p1, i32 1
>>> > -; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i3 = extractelement <4 x i32> %p1, i32 2
>>> > -; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i4 = extractelement <4 x i32> %p1, i32 3
>>> > +; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %i1 = extractelement <4 x i32> %p1, i32 0
>>> > +; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 1 for
>>> instruction: %i2 = extractelement <4 x i32> %p1, i32 1
>>> > +; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %i3 = extractelement <4 x i32> %p1, i32 2
>>> > +; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %i4 = extractelement <4 x i32> %p1, i32 3
>>> >  ; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret void
>>> >  ;
>>> >  ; CHECK-P9LE-LABEL: 'vexti32'
>>> > -; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i1 = extractelement <4 x i32> %p1, i32 0
>>> > -; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i2 = extractelement <4 x i32> %p1, i32 1
>>> > -; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i3 = extractelement <4 x i32> %p1, i32 2
>>> > -; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i4 = extractelement <4 x i32> %p1, i32 3
>>> > +; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %i1 = extractelement <4 x i32> %p1, i32 0
>>> > +; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %i2 = extractelement <4 x i32> %p1, i32 1
>>> > +; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 1 for
>>> instruction: %i3 = extractelement <4 x i32> %p1, i32 2
>>> > +; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %i4 = extractelement <4 x i32> %p1, i32 3
>>> >  ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret void
>>> >  ;
>>> >    %i1 = extractelement <4 x i32> %p1, i32 0
>>> > @@ -146,13 +146,13 @@ define void @vexti64(<2 x i64> %p1) {
>>> >  ; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret void
>>> >  ;
>>> >  ; CHECK-P9BE-LABEL: 'vexti64'
>>> > -; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i1 = extractelement <2 x i64> %p1, i32 0
>>> > -; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i2 = extractelement <2 x i64> %p1, i32 1
>>> > +; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 1 for
>>> instruction: %i1 = extractelement <2 x i64> %p1, i32 0
>>> > +; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %i2 = extractelement <2 x i64> %p1, i32 1
>>> >  ; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret void
>>> >  ;
>>> >  ; CHECK-P9LE-LABEL: 'vexti64'
>>> > -; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i1 = extractelement <2 x i64> %p1, i32 0
>>> > -; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i2 = extractelement <2 x i64> %p1, i32 1
>>> > +; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %i1 = extractelement <2 x i64> %p1, i32 0
>>> > +; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 1 for
>>> instruction: %i2 = extractelement <2 x i64> %p1, i32 1
>>> >  ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret void
>>> >  ;
>>> >    %i1 = extractelement <2 x i64> %p1, i32 0
>>> > @@ -172,13 +172,13 @@ define void @vext(<8 x i16> %p1, <16 x i
>>> >  ; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret void
>>> >  ;
>>> >  ; CHECK-P9BE-LABEL: 'vext'
>>> > -; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i1 = extractelement <8 x i16> %p1, i32 0
>>> > -; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i2 = extractelement <16 x i8> %p2, i32 0
>>> > +; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %i1 = extractelement <8 x i16> %p1, i32 0
>>> > +; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %i2 = extractelement <16 x i8> %p2, i32 0
>>> >  ; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret void
>>> >  ;
>>> >  ; CHECK-P9LE-LABEL: 'vext'
>>> > -; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i1 = extractelement <8 x i16> %p1, i32 0
>>> > -; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 4 for
>>> instruction: %i2 = extractelement <16 x i8> %p2, i32 0
>>> > +; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %i1 = extractelement <8 x i16> %p1, i32 0
>>> > +; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 2 for
>>> instruction: %i2 = extractelement <16 x i8> %p2, i32 0
>>> >  ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for
>>> instruction: ret void
>>> >  ;
>>> >    %i1 = extractelement <8 x i16> %p1, i32 0
>>> >
>>> >
>>> > _______________________________________________
>>> > llvm-commits mailing list
>>> > llvm-commits at lists.llvm.org
>>> > https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits
>>> _______________________________________________
>>> llvm-commits mailing list
>>> llvm-commits at lists.llvm.org
>>> https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits
>>>
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190701/e8183e48/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 4849 bytes
Desc: S/MIME Cryptographic Signature
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190701/e8183e48/attachment.bin>


More information about the llvm-commits mailing list