Skip to content

Commit

Permalink
[VP] Check if VP ops with functional intrinsics are speculatable
Browse files Browse the repository at this point in the history 
Noticed whilst working on llvm#69494. VP intrinsics whose functional equivalent is
an intrinsic were being marked as their lanes being non-speculatable, even if
the underlying intrinsic was speculatable.

This meant that

  %1 = call <4 x i32> @llvm.vp.umax(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)

would be expanded out to

  %.splatinsert = insertelement <4 x i32> poison, i32 %evl, i64 0
  %.splat = shufflevector <4 x i32> %.splatinsert, <4 x i32> poison, <4 x i32> zeroinitializer
  %1 = icmp ult <4 x i32> <i32 0, i32 1, i32 2, i32 3>, %.splat
  %2 = and <4 x i1> %1, %mask
  %3 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> %x, <4 x i32> %y)

instead of

  %1 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> %x, <4 x i32> %y)

The cause of this was isSafeToSpeculativelyExecuteWithOpcode checking the
function attributes for the VP instruction itself, not the functional
intrinsic.  Since isSafeToSpeculativelyExecuteWithOpcode expects an already
materialized instruction, we can't use it directly for the intrinsic case. So
this fixes it by manually checking the function attributes on the intrinsic.
  • Loading branch information
@lukel97
lukel97 committed Oct 18, 2023
1 parent 3927b9a commit adfce64
Show file tree
Hide file tree
Showing 2 changed files with 68 additions and 33 deletions.
9 changes: 6 additions & 3 deletions llvm/lib/CodeGen/ExpandVectorPredication.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -123,9 +123,12 @@ static bool maySpeculateLanes(VPIntrinsic &VPI) {
if (isa<VPReductionIntrinsic>(VPI))
return false;
// Fallback to whether the intrinsic is speculatable.
std::optional<unsigned> OpcOpt = VPI.getFunctionalOpcode();
unsigned FunctionalOpc = OpcOpt.value_or((unsigned)Instruction::Call);
return isSafeToSpeculativelyExecuteWithOpcode(FunctionalOpc, &VPI);
if (auto IntrID = VPI.getFunctionalIntrinsicID())
return Intrinsic::getAttributes(VPI.getContext(), *IntrID)
.hasFnAttr(Attribute::AttrKind::Speculatable);
if (auto Opc = VPI.getFunctionalOpcode())
return isSafeToSpeculativelyExecuteWithOpcode(*Opc, &VPI);
return false;
}

//// } Helpers
Expand Down
92 changes: 62 additions & 30 deletions llvm/test/CodeGen/Generic/expand-vp.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,10 @@ declare <8 x i32> @llvm.vp.sdiv.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.srem.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.udiv.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.urem.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.smax.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.smin.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.umax.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.umin.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
; Bit arith
declare <8 x i32> @llvm.vp.and.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.xor.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
Expand Down Expand Up @@ -52,12 +56,16 @@ define void @test_vp_int_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x i32> %i2, <8 x i3
%r4 = call <8 x i32> @llvm.vp.srem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r5 = call <8 x i32> @llvm.vp.udiv.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r6 = call <8 x i32> @llvm.vp.urem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r7 = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r8 = call <8 x i32> @llvm.vp.or.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r9 = call <8 x i32> @llvm.vp.xor.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%rA = call <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%rB = call <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%rC = call <8 x i32> @llvm.vp.shl.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r7 = call <8 x i32> @llvm.vp.smax.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r8 = call <8 x i32> @llvm.vp.smin.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r9 = call <8 x i32> @llvm.vp.umax.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%rA = call <8 x i32> @llvm.vp.umin.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%rB = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%rC = call <8 x i32> @llvm.vp.or.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%rD = call <8 x i32> @llvm.vp.xor.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%rE = call <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%rF = call <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r10 = call <8 x i32> @llvm.vp.shl.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
ret void
}

Expand All @@ -70,6 +78,10 @@ declare <vscale x 4 x i32> @llvm.vp.sdiv.nxv4i32(<vscale x 4 x i32>, <vscale x 4
declare <vscale x 4 x i32> @llvm.vp.srem.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i1>, i32)
declare <vscale x 4 x i32> @llvm.vp.udiv.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i1>, i32)
declare <vscale x 4 x i32> @llvm.vp.urem.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i1>, i32)
declare <vscale x 4 x i32> @llvm.vp.smax.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i1>, i32)
declare <vscale x 4 x i32> @llvm.vp.smin.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i1>, i32)
declare <vscale x 4 x i32> @llvm.vp.umax.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i1>, i32)
declare <vscale x 4 x i32> @llvm.vp.umin.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i1>, i32)
; Bit arith
declare <vscale x 4 x i32> @llvm.vp.and.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i1>, i32)
declare <vscale x 4 x i32> @llvm.vp.xor.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i1>, i32)
Expand All @@ -87,12 +99,16 @@ define void @test_vp_int_vscale(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1,
%r4 = call <vscale x 4 x i32> @llvm.vp.srem.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%r5 = call <vscale x 4 x i32> @llvm.vp.udiv.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%r6 = call <vscale x 4 x i32> @llvm.vp.urem.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%r7 = call <vscale x 4 x i32> @llvm.vp.and.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%r8 = call <vscale x 4 x i32> @llvm.vp.or.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%r9 = call <vscale x 4 x i32> @llvm.vp.xor.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%rA = call <vscale x 4 x i32> @llvm.vp.ashr.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%rB = call <vscale x 4 x i32> @llvm.vp.lshr.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%rC = call <vscale x 4 x i32> @llvm.vp.shl.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%r7 = call <vscale x 4 x i32> @llvm.vp.smax.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%r8 = call <vscale x 4 x i32> @llvm.vp.smin.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%r9 = call <vscale x 4 x i32> @llvm.vp.umax.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%rA = call <vscale x 4 x i32> @llvm.vp.umin.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%rB = call <vscale x 4 x i32> @llvm.vp.and.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%rC = call <vscale x 4 x i32> @llvm.vp.or.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%rD = call <vscale x 4 x i32> @llvm.vp.xor.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%rE = call <vscale x 4 x i32> @llvm.vp.ashr.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%rF = call <vscale x 4 x i32> @llvm.vp.lshr.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
%r10 = call <vscale x 4 x i32> @llvm.vp.shl.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
ret void
}

Expand Down Expand Up @@ -166,6 +182,10 @@ define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x
; ALL-CONVERT: %{{.+}} = udiv <8 x i32> %i0, %{{.+}}
; ALL-CONVERT-NOT: %{{.+}} = urem <8 x i32> %i0, %i1
; ALL-CONVERT: %{{.+}} = urem <8 x i32> %i0, %{{.+}}
; ALL-CONVERT-NEXT: %{{.+}} = call <8 x i32> @llvm.smax.v8i32(<8 x i32> %i0, <8 x i32> %i1)
; ALL-CONVERT-NEXT: %{{.+}} = call <8 x i32> @llvm.smin.v8i32(<8 x i32> %i0, <8 x i32> %i1)
; ALL-CONVERT-NEXT: %{{.+}} = call <8 x i32> @llvm.umax.v8i32(<8 x i32> %i0, <8 x i32> %i1)
; ALL-CONVERT-NEXT: %{{.+}} = call <8 x i32> @llvm.umin.v8i32(<8 x i32> %i0, <8 x i32> %i1)
; ALL-CONVERT-NEXT: %{{.+}} = and <8 x i32> %i0, %i1
; ALL-CONVERT-NEXT: %{{.+}} = or <8 x i32> %i0, %i1
; ALL-CONVERT-NEXT: %{{.+}} = xor <8 x i32> %i0, %i1
Expand Down Expand Up @@ -263,12 +283,16 @@ define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x
; LEGAL_LEGAL-NEXT: %r4 = call <8 x i32> @llvm.vp.srem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r5 = call <8 x i32> @llvm.vp.udiv.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r6 = call <8 x i32> @llvm.vp.urem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r7 = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r8 = call <8 x i32> @llvm.vp.or.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r9 = call <8 x i32> @llvm.vp.xor.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rA = call <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rB = call <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rC = call <8 x i32> @llvm.vp.shl.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r7 = call <8 x i32> @llvm.vp.smax.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r8 = call <8 x i32> @llvm.vp.smin.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r9 = call <8 x i32> @llvm.vp.umax.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rA = call <8 x i32> @llvm.vp.umin.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rB = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rC = call <8 x i32> @llvm.vp.or.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rD = call <8 x i32> @llvm.vp.xor.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rE = call <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rF = call <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r10 = call <8 x i32> @llvm.vp.shl.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: ret void

; LEGAL_LEGAL:define void @test_vp_int_vscale(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i32> %i2, <vscale x 4 x i32> %f3, <vscale x 4 x i1> %m, i32 %n) {
Expand All @@ -279,12 +303,16 @@ define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x
; LEGAL_LEGAL-NEXT: %r4 = call <vscale x 4 x i32> @llvm.vp.srem.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r5 = call <vscale x 4 x i32> @llvm.vp.udiv.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r6 = call <vscale x 4 x i32> @llvm.vp.urem.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r7 = call <vscale x 4 x i32> @llvm.vp.and.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r8 = call <vscale x 4 x i32> @llvm.vp.or.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r9 = call <vscale x 4 x i32> @llvm.vp.xor.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rA = call <vscale x 4 x i32> @llvm.vp.ashr.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rB = call <vscale x 4 x i32> @llvm.vp.lshr.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rC = call <vscale x 4 x i32> @llvm.vp.shl.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r7 = call <vscale x 4 x i32> @llvm.vp.smax.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r8 = call <vscale x 4 x i32> @llvm.vp.smin.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r9 = call <vscale x 4 x i32> @llvm.vp.umax.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rA = call <vscale x 4 x i32> @llvm.vp.umin.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rB = call <vscale x 4 x i32> @llvm.vp.and.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rC = call <vscale x 4 x i32> @llvm.vp.or.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rD = call <vscale x 4 x i32> @llvm.vp.xor.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rE = call <vscale x 4 x i32> @llvm.vp.ashr.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %rF = call <vscale x 4 x i32> @llvm.vp.lshr.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r10 = call <vscale x 4 x i32> @llvm.vp.shl.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: ret void

; LEGAL_LEGAL: define void @test_vp_reduce_int_v4(i32 %start, <4 x i32> %vi, <4 x i1> %m, i32 %n) {
Expand Down Expand Up @@ -342,12 +370,16 @@ define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x
; DISCARD_LEGAL-NOT: %r4 = call <8 x i32> @llvm.vp.srem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NOT: %r5 = call <8 x i32> @llvm.vp.udiv.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NOT: %r6 = call <8 x i32> @llvm.vp.urem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL: %r7 = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NEXT: %r8 = call <8 x i32> @llvm.vp.or.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NEXT: %r9 = call <8 x i32> @llvm.vp.xor.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NEXT: %rA = call <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NEXT: %rB = call <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NEXT: %rC = call <8 x i32> @llvm.vp.shl.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL: %r7 = call <8 x i32> @llvm.vp.smax.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL: %r8 = call <8 x i32> @llvm.vp.smin.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL: %r9 = call <8 x i32> @llvm.vp.umax.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL: %rA = call <8 x i32> @llvm.vp.umin.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NEXT: %rB = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NEXT: %rC = call <8 x i32> @llvm.vp.or.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NEXT: %rD = call <8 x i32> @llvm.vp.xor.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NEXT: %rE = call <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NEXT: %rF = call <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NEXT: %r10 = call <8 x i32> @llvm.vp.shl.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NEXT: ret void

; TODO compute vscale only once and use caching.
Expand Down

0 comments on commit adfce64

Please sign in to comment.