caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
4e9082ef95db5d760df4cce00a4351fa122176d6
clang-p2996/llvm/test/CodeGen/Thumb2/LowOverheadLoops/tail-pred-pattern-fail.ll
Sam Parker 312409e464 [ARM] MVE Tail Predication 
The MVE and LOB extensions of Armv8.1m can be combined to enable
'tail predication' which removes the need for a scalar remainder
loop after vectorization. Lane predication is performed implicitly
via a system register. The effects of predication is described in
Section B5.6.3 of the Armv8.1-m Arch Reference Manual, the key points
being:
- For vector operations that perform reduction across the vector and
  produce a scalar result, whether the value is accumulated or not.
- For non-load instructions, the predicate flags determine if the
  destination register byte is updated with the new value or if the
  previous value is preserved.
- For vector store instructions, whether the store occurs or not.
- For vector load instructions, whether the value that is loaded or
  whether zeros are written to that element of the destination
  register.

This patch implements a pass that takes a hardware loop, containing
masked vector instructions, and converts it something that resembles
an MVE tail predicated loop. Currently, if we had code generation,
we'd generate a loop in which the VCTP would generate the predicate
and VPST would then setup the value of VPR.PO. The loads and stores
would be placed in VPT blocks so this is not tail predication, but
normal VPT predication with the predicate based upon a element
counting induction variable. Further work needs to be done to finally
produce a true tail predicated loop.

Because only the loads and stores are predicated, in both the LLVM IR
and MIR level, we will restrict support to only lane-wise operations
(no horizontal reductions). We will perform a final check on MIR
during loop finalisation too.

Another restriction, specific to MVE, is that all the vector
instructions need operate on the same number of elements. This is
because predication is performed at the byte level and this is set
on entry to the loop, or by the VCTP instead.

Differential Revision: https://reviews.llvm.org/D65884

llvm-svn: 371179
2019-09-06 08:24:41 +00:00

506 lines
27 KiB
LLVM
Raw Blame History

; RUN: opt -mtriple=thumbv8.1m.main -mve-tail-predication -disable-mve-tail-predication=false -mattr=+mve,+lob %s -S -o - | FileCheck %s
; The following functions should all fail to become tail-predicated.
; CHECK-NOT: call i32 @llvm.arm.vctp
; trip.count.minus.1 has been inserted into element 1, not 0.
define dso_local arm_aapcs_vfpcc void @wrong_ph_insert_0(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* noalias nocapture %c, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 3
%tmp9 = lshr i32 %tmp8, 2
%tmp10 = shl nuw i32 %tmp9, 2
%tmp11 = add i32 %tmp10, -4
%tmp12 = lshr i32 %tmp11, 2
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 1
%broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
call void @llvm.set.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%tmp14 = phi i32 [ %tmp13, %vector.ph ], [ %tmp15, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%tmp = getelementptr inbounds i32, i32* %a, i32 %index
%tmp1 = icmp ule <4 x i32> %induction, %broadcast.splat11
%tmp2 = bitcast i32* %tmp to <4 x i32>*
%wide.masked.load = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp2, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp3 = getelementptr inbounds i32, i32* %b, i32 %index
%tmp4 = bitcast i32* %tmp3 to <4 x i32>*
%wide.masked.load12 = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp4, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp5 = mul nsw <4 x i32> %wide.masked.load12, %wide.masked.load
%tmp6 = getelementptr inbounds i32, i32* %c, i32 %index
%tmp7 = bitcast i32* %tmp6 to <4 x i32>*
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp5, <4 x i32>* %tmp7, i32 4, <4 x i1> %tmp1)
%index.next = add i32 %index, 4
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
; The insert isn't using an undef for operand 0.
define dso_local arm_aapcs_vfpcc void @wrong_ph_insert_def(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* noalias nocapture %c, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 3
%tmp9 = lshr i32 %tmp8, 2
%tmp10 = shl nuw i32 %tmp9, 2
%tmp11 = add i32 %tmp10, -4
%tmp12 = lshr i32 %tmp11, 2
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert10 = insertelement <4 x i32> <i32 1, i32 1, i32 1, i32 1>, i32 %trip.count.minus.1, i32 0
%broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
call void @llvm.set.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%tmp14 = phi i32 [ %tmp13, %vector.ph ], [ %tmp15, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%tmp = getelementptr inbounds i32, i32* %a, i32 %index
%tmp1 = icmp ule <4 x i32> %induction, %broadcast.splat11
%tmp2 = bitcast i32* %tmp to <4 x i32>*
%wide.masked.load = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp2, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp3 = getelementptr inbounds i32, i32* %b, i32 %index
%tmp4 = bitcast i32* %tmp3 to <4 x i32>*
%wide.masked.load12 = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp4, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp5 = mul nsw <4 x i32> %wide.masked.load12, %wide.masked.load
%tmp6 = getelementptr inbounds i32, i32* %c, i32 %index
%tmp7 = bitcast i32* %tmp6 to <4 x i32>*
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp5, <4 x i32>* %tmp7, i32 4, <4 x i1> %tmp1)
%index.next = add i32 %index, 4
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
; The shuffle uses a defined value for operand 1.
define dso_local arm_aapcs_vfpcc void @wrong_ph_shuffle_1(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* noalias nocapture %c, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 3
%tmp9 = lshr i32 %tmp8, 2
%tmp10 = shl nuw i32 %tmp9, 2
%tmp11 = add i32 %tmp10, -4
%tmp12 = lshr i32 %tmp11, 2
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32> zeroinitializer
call void @llvm.set.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%tmp14 = phi i32 [ %tmp13, %vector.ph ], [ %tmp15, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%tmp = getelementptr inbounds i32, i32* %a, i32 %index
%tmp1 = icmp ule <4 x i32> %induction, %broadcast.splat11
%tmp2 = bitcast i32* %tmp to <4 x i32>*
%wide.masked.load = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp2, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp3 = getelementptr inbounds i32, i32* %b, i32 %index
%tmp4 = bitcast i32* %tmp3 to <4 x i32>*
%wide.masked.load12 = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp4, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp5 = mul nsw <4 x i32> %wide.masked.load12, %wide.masked.load
%tmp6 = getelementptr inbounds i32, i32* %c, i32 %index
%tmp7 = bitcast i32* %tmp6 to <4 x i32>*
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp5, <4 x i32>* %tmp7, i32 4, <4 x i1> %tmp1)
%index.next = add i32 %index, 4
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
; The shuffle uses a non zero value for operand 2.
define dso_local arm_aapcs_vfpcc void @wrong_ph_shuffle_2(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* noalias nocapture %c, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 3
%tmp9 = lshr i32 %tmp8, 2
%tmp10 = shl nuw i32 %tmp9, 2
%tmp11 = add i32 %tmp10, -4
%tmp12 = lshr i32 %tmp11, 2
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
call void @llvm.set.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%tmp14 = phi i32 [ %tmp13, %vector.ph ], [ %tmp15, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%tmp = getelementptr inbounds i32, i32* %a, i32 %index
%tmp1 = icmp ule <4 x i32> %induction, %broadcast.splat11
%tmp2 = bitcast i32* %tmp to <4 x i32>*
%wide.masked.load = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp2, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp3 = getelementptr inbounds i32, i32* %b, i32 %index
%tmp4 = bitcast i32* %tmp3 to <4 x i32>*
%wide.masked.load12 = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp4, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp5 = mul nsw <4 x i32> %wide.masked.load12, %wide.masked.load
%tmp6 = getelementptr inbounds i32, i32* %c, i32 %index
%tmp7 = bitcast i32* %tmp6 to <4 x i32>*
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp5, <4 x i32>* %tmp7, i32 4, <4 x i1> %tmp1)
%index.next = add i32 %index, 4
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
; %N - 2
define dso_local arm_aapcs_vfpcc void @trip_count_minus_2(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* noalias nocapture %c, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 3
%tmp9 = lshr i32 %tmp8, 2
%tmp10 = shl nuw i32 %tmp9, 2
%tmp11 = add i32 %tmp10, -4
%tmp12 = lshr i32 %tmp11, 2
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%trip.count.minus.2 = add i32 %N, -2
%broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.2, i32 1
%broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
call void @llvm.set.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%tmp14 = phi i32 [ %tmp13, %vector.ph ], [ %tmp15, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%tmp = getelementptr inbounds i32, i32* %a, i32 %index
%tmp1 = icmp ule <4 x i32> %induction, %broadcast.splat11
%tmp2 = bitcast i32* %tmp to <4 x i32>*
%wide.masked.load = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp2, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp3 = getelementptr inbounds i32, i32* %b, i32 %index
%tmp4 = bitcast i32* %tmp3 to <4 x i32>*
%wide.masked.load12 = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp4, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp5 = mul nsw <4 x i32> %wide.masked.load12, %wide.masked.load
%tmp6 = getelementptr inbounds i32, i32* %c, i32 %index
%tmp7 = bitcast i32* %tmp6 to <4 x i32>*
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp5, <4 x i32>* %tmp7, i32 4, <4 x i1> %tmp1)
%index.next = add i32 %index, 4
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
; index has been inserted at element 1, not 0.
define dso_local arm_aapcs_vfpcc void @wrong_loop_insert(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* noalias nocapture %c, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 3
%tmp9 = lshr i32 %tmp8, 2
%tmp10 = shl nuw i32 %tmp9, 2
%tmp11 = add i32 %tmp10, -4
%tmp12 = lshr i32 %tmp11, 2
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
call void @llvm.set.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%tmp14 = phi i32 [ %tmp13, %vector.ph ], [ %tmp15, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 1
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%tmp = getelementptr inbounds i32, i32* %a, i32 %index
%tmp1 = icmp ule <4 x i32> %induction, %broadcast.splat11
%tmp2 = bitcast i32* %tmp to <4 x i32>*
%wide.masked.load = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp2, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp3 = getelementptr inbounds i32, i32* %b, i32 %index
%tmp4 = bitcast i32* %tmp3 to <4 x i32>*
%wide.masked.load12 = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp4, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp5 = mul nsw <4 x i32> %wide.masked.load12, %wide.masked.load
%tmp6 = getelementptr inbounds i32, i32* %c, i32 %index
%tmp7 = bitcast i32* %tmp6 to <4 x i32>*
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp5, <4 x i32>* %tmp7, i32 4, <4 x i1> %tmp1)
%index.next = add i32 %index, 4
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
define dso_local arm_aapcs_vfpcc void @wrong_loop_invalid_index_splat(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* noalias nocapture %c, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 3
%tmp9 = lshr i32 %tmp8, 2
%tmp10 = shl nuw i32 %tmp9, 2
%tmp11 = add i32 %tmp10, -4
%tmp12 = lshr i32 %tmp11, 2
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
call void @llvm.set.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%tmp14 = phi i32 [ %tmp13, %vector.ph ], [ %tmp15, %vector.body ]
%incorrect = add i32 %index, 1
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %incorrect, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%tmp = getelementptr inbounds i32, i32* %a, i32 %index
%tmp1 = icmp ule <4 x i32> %induction, %broadcast.splat11
%tmp2 = bitcast i32* %tmp to <4 x i32>*
%wide.masked.load = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp2, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp3 = getelementptr inbounds i32, i32* %b, i32 %index
%tmp4 = bitcast i32* %tmp3 to <4 x i32>*
%wide.masked.load12 = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp4, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp5 = mul nsw <4 x i32> %wide.masked.load12, %wide.masked.load
%tmp6 = getelementptr inbounds i32, i32* %c, i32 %index
%tmp7 = bitcast i32* %tmp6 to <4 x i32>*
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp5, <4 x i32>* %tmp7, i32 4, <4 x i1> %tmp1)
%index.next = add i32 %index, 4
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
; Now using ult, not ule for the vector icmp
define dso_local arm_aapcs_vfpcc void @wrong_pred_opcode(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* noalias nocapture %c, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 3
%tmp9 = lshr i32 %tmp8, 2
%tmp10 = shl nuw i32 %tmp9, 2
%tmp11 = add i32 %tmp10, -4
%tmp12 = lshr i32 %tmp11, 2
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
call void @llvm.set.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%tmp14 = phi i32 [ %tmp13, %vector.ph ], [ %tmp15, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%tmp = getelementptr inbounds i32, i32* %a, i32 %index
%tmp1 = icmp ult <4 x i32> %induction, %broadcast.splat11
%tmp2 = bitcast i32* %tmp to <4 x i32>*
%wide.masked.load = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp2, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp3 = getelementptr inbounds i32, i32* %b, i32 %index
%tmp4 = bitcast i32* %tmp3 to <4 x i32>*
%wide.masked.load12 = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp4, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp5 = mul nsw <4 x i32> %wide.masked.load12, %wide.masked.load
%tmp6 = getelementptr inbounds i32, i32* %c, i32 %index
%tmp7 = bitcast i32* %tmp6 to <4 x i32>*
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp5, <4 x i32>* %tmp7, i32 4, <4 x i1> %tmp1)
%index.next = add i32 %index, 4
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
; The add in the body uses 1, 2, 3, 4
define void @wrong_body_broadcast_splat(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* noalias nocapture %c, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 3
%tmp9 = lshr i32 %tmp8, 2
%tmp10 = shl nuw i32 %tmp9, 2
%tmp11 = add i32 %tmp10, -4
%tmp12 = lshr i32 %tmp11, 2
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
call void @llvm.set.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%tmp14 = phi i32 [ %tmp13, %vector.ph ], [ %tmp15, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 1, i32 2, i32 3, i32 4>
%tmp = getelementptr inbounds i32, i32* %a, i32 %index
%tmp1 = icmp ule <4 x i32> %induction, %broadcast.splat11
%tmp2 = bitcast i32* %tmp to <4 x i32>*
%wide.masked.load = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp2, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp3 = getelementptr inbounds i32, i32* %b, i32 %index
%tmp4 = bitcast i32* %tmp3 to <4 x i32>*
%wide.masked.load12 = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp4, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp5 = mul nsw <4 x i32> %wide.masked.load12, %wide.masked.load
%tmp6 = getelementptr inbounds i32, i32* %c, i32 %index
%tmp7 = bitcast i32* %tmp6 to <4 x i32>*
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp5, <4 x i32>* %tmp7, i32 4, <4 x i1> %tmp1)
%index.next = add i32 %index, 4
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
; Using a variable for the loop body broadcast.
define void @wrong_body_broadcast_splat_2(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* noalias nocapture %c, i32 %N, <4 x i32> %offsets) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 3
%tmp9 = lshr i32 %tmp8, 2
%tmp10 = shl nuw i32 %tmp9, 2
%tmp11 = add i32 %tmp10, -4
%tmp12 = lshr i32 %tmp11, 2
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
call void @llvm.set.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%tmp14 = phi i32 [ %tmp13, %vector.ph ], [ %tmp15, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, %offsets
%tmp = getelementptr inbounds i32, i32* %a, i32 %index
%tmp1 = icmp ule <4 x i32> %induction, %broadcast.splat11
%tmp2 = bitcast i32* %tmp to <4 x i32>*
%wide.masked.load = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp2, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp3 = getelementptr inbounds i32, i32* %b, i32 %index
%tmp4 = bitcast i32* %tmp3 to <4 x i32>*
%wide.masked.load12 = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp4, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp5 = mul nsw <4 x i32> %wide.masked.load12, %wide.masked.load
%tmp6 = getelementptr inbounds i32, i32* %c, i32 %index
%tmp7 = bitcast i32* %tmp6 to <4 x i32>*
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp5, <4 x i32>* %tmp7, i32 4, <4 x i1> %tmp1)
%index.next = add i32 %index, 4
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
; adding 5, instead of 4, to index.
define void @wrong_index_add(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* noalias nocapture %c, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 3
%tmp9 = lshr i32 %tmp8, 2
%tmp10 = shl nuw i32 %tmp9, 2
%tmp11 = add i32 %tmp10, -4
%tmp12 = lshr i32 %tmp11, 2
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
call void @llvm.set.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%tmp14 = phi i32 [ %tmp13, %vector.ph ], [ %tmp15, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%tmp = getelementptr inbounds i32, i32* %a, i32 %index
%tmp1 = icmp ule <4 x i32> %induction, %broadcast.splat11
%tmp2 = bitcast i32* %tmp to <4 x i32>*
%wide.masked.load = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp2, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp3 = getelementptr inbounds i32, i32* %b, i32 %index
%tmp4 = bitcast i32* %tmp3 to <4 x i32>*
%wide.masked.load12 = tail call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %tmp4, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp5 = mul nsw <4 x i32> %wide.masked.load12, %wide.masked.load
%tmp6 = getelementptr inbounds i32, i32* %c, i32 %index
%tmp7 = bitcast i32* %tmp6 to <4 x i32>*
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp5, <4 x i32>* %tmp7, i32 4, <4 x i1> %tmp1)
%index.next = add i32 %index, 5
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>) #1
declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>) #2
declare void @llvm.set.loop.iterations.i32(i32) #3
declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #3
Reference in New Issue View Git Blame Copy Permalink