vendor/llvm/llvm-release_38-r260756

5 files changed, 89 insertions, 34 deletions

diff --git a/test/Transforms/InstCombine/icmp.ll b/test/Transforms/InstCombine/icmp.ll
index 7d6ec96b5328..1e64cd7f5820 100644
--- a/test/Transforms/InstCombine/icmp.ll
+++ b/test/Transforms/InstCombine/icmp.ll
@@ -1672,3 +1672,15 @@ define i1 @cmp_slt_rhs_inc(float %x, i32 %i) {
   %cmp = icmp slt i32 %conv, %inc
   ret i1 %cmp
 }
+
+; CHECK-LABEL: @PR26407
+; CHECK-NEXT: %[[addx:.*]] = add i32 %x, 2147483647
+; CHECK-NEXT: %[[addy:.*]] = add i32 %y, 2147483647
+; CHECK-NEXT: %[[cmp:.*]] = icmp uge i32 %[[addx]], %[[addy]]
+; CHECK-NEXT: ret i1 %[[cmp]]
+define i1 @PR26407(i32 %x, i32 %y) {
+  %addx = add i32 %x, 2147483647
+  %addy = add i32 %y, 2147483647
+  %cmp = icmp uge i32 %addx, %addy
+  ret i1 %cmp
+}
diff --git a/test/Transforms/InstCombine/insert-extract-shuffle.ll b/test/Transforms/InstCombine/insert-extract-shuffle.ll
index 47c2a139a479..8ed4db8bbbc3 100644
--- a/test/Transforms/InstCombine/insert-extract-shuffle.ll
+++ b/test/Transforms/InstCombine/insert-extract-shuffle.ll
@@ -175,3 +175,33 @@ bb3:
   ret <4 x double> %tmp4
 }
 
+; PR26354: https://llvm.org/bugs/show_bug.cgi?id=26354
+; Don't create a shufflevector if we know that we're not going to replace the insertelement.
+
+define double @pr26354(<2 x double>* %tmp, i1 %B) {
+; CHECK-LABEL: @pr26354(
+; CHECK:       %ld = load <2 x double>, <2 x double>* %tmp
+; CHECK-NEXT:  %e1 = extractelement <2 x double> %ld, i32 0
+; CHECK-NEXT:  br i1 %B, label %if, label %end
+; CHECK:       if:
+; CHECK-NEXT:  %e2 = extractelement <2 x double> %ld, i32 1
+; CHECK-NEXT:  %i1 = insertelement <4 x double>
+; CHECK-NEXT:  br label %end
+
+entry:
+  %ld = load <2 x double>, <2 x double>* %tmp
+  %e1 = extractelement <2 x double> %ld, i32 0
+  %e2 = extractelement <2 x double> %ld, i32 1
+  br i1 %B, label %if, label %end
+
+if:
+  %i1 = insertelement <4 x double> zeroinitializer, double %e2, i32 3
+  br label %end
+
+end:
+  %ph = phi <4 x double> [ undef, %entry ], [ %i1, %if ]
+  %e3 = extractelement <4 x double> %ph, i32 1
+  %mu = fmul double %e1, %e3
+  ret double %mu
+}
+
diff --git a/test/Transforms/InstCombine/unpack-fca.ll b/test/Transforms/InstCombine/unpack-fca.ll
index 9b8d10457491..435983924b77 100644
--- a/test/Transforms/InstCombine/unpack-fca.ll
+++ b/test/Transforms/InstCombine/unpack-fca.ll
@@ -136,3 +136,18 @@ define %B @structB(%B* %b.ptr) {
   %1 = load %B, %B* %b.ptr, align 8
   ret %B %1
 }
+
+%struct.S = type <{ i8, %struct.T }>
+%struct.T = type { i32, i32 }
+
+; Make sure that we do not increase alignment of packed struct element
+define i32 @packed_alignment(%struct.S* dereferenceable(9) %s) {
+; CHECK-LABEL: packed_alignment
+; CHECK-NEXT: %tv.elt1 = getelementptr inbounds %struct.S, %struct.S* %s, i64 0, i32 1, i32 1
+; CHECK-NEXT: %tv.unpack2 = load i32, i32* %tv.elt1, align 1
+; CHECK-NEXT: ret i32 %tv.unpack2
+  %t = getelementptr inbounds %struct.S, %struct.S* %s, i32 0, i32 1
+  %tv = load %struct.T, %struct.T* %t, align 1
+  %v = extractvalue %struct.T %tv, 1
+  ret i32 %v
+}
diff --git a/test/Transforms/LoopVectorize/AArch64/loop-vectorization-factors.ll b/test/Transforms/LoopVectorize/AArch64/loop-vectorization-factors.ll
index eee310491805..51f899c2f645 100644
--- a/test/Transforms/LoopVectorize/AArch64/loop-vectorization-factors.ll
+++ b/test/Transforms/LoopVectorize/AArch64/loop-vectorization-factors.ll
@@ -205,39 +205,5 @@ for.body:                                         ; preds = %for.body, %for.body
   br i1 %exitcond, label %for.cond.cleanup, label %for.body
 }
 
-; CHECK-LABEL: @add_g
-; CHECK: load <16 x i8>
-; CHECK: xor <16 x i8>
-; CHECK: icmp ult <16 x i8>
-; CHECK: select <16 x i1> {{.*}}, <16 x i8>
-; CHECK: store <16 x i8>
-define void @add_g(i8* noalias nocapture readonly %p, i8* noalias nocapture readonly %q, i8* noalias nocapture %r, i8 %arg1, i32 %len) #0 {
-  %1 = icmp sgt i32 %len, 0
-  br i1 %1, label %.lr.ph, label %._crit_edge
-
-.lr.ph:                                           ; preds = %0
-  %2 = sext i8 %arg1 to i64
-  br label %3
-
-._crit_edge:                                      ; preds = %3, %0
-  ret void
-
-; <label>:3                                       ; preds = %3, %.lr.ph
-  %indvars.iv = phi i64 [ 0, %.lr.ph ], [ %indvars.iv.next, %3 ]
-  %x4 = getelementptr inbounds i8, i8* %p, i64 %indvars.iv
-  %x5 = load i8, i8* %x4
-  %x7 = getelementptr inbounds i8, i8* %q, i64 %indvars.iv
-  %x8 = load i8, i8* %x7
-  %x9 = zext i8 %x5 to i32
-  %x10 = xor i32 %x9, 255
-  %x11 = icmp ult i32 %x10, 24
-  %x12 = select i1 %x11, i32 %x10, i32 24
-  %x13 = trunc i32 %x12 to i8
-  store i8 %x13, i8* %x4
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
-  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
-  %exitcond = icmp eq i32 %lftr.wideiv, %len
-  br i1 %exitcond, label %._crit_edge, label %3
-}
 
 attributes #0 = { nounwind }
diff --git a/test/Transforms/SimplifyCFG/X86/switch_to_lookup_table.ll b/test/Transforms/SimplifyCFG/X86/switch_to_lookup_table.ll
index cae1a91bd43d..6953cf9c8b33 100644
--- a/test/Transforms/SimplifyCFG/X86/switch_to_lookup_table.ll
+++ b/test/Transforms/SimplifyCFG/X86/switch_to_lookup_table.ll
@@ -1302,3 +1302,35 @@ l6:
 ; CHECK: entry
 ; CHECK-NEXT: switch
 }
+
+; Speculation depth must be limited to avoid a zero-cost instruction cycle.
+
+; CHECK-LABEL: @PR26308(
+; CHECK:       cleanup4:
+; CHECK-NEXT:  br label %cleanup4
+
+define i32 @PR26308(i1 %B, i64 %load) {
+entry:
+  br label %while.body
+
+while.body:
+  br label %cleanup
+
+cleanup:
+  %cleanup.dest.slot.0 = phi i1 [ false, %while.body ]
+  br i1 %cleanup.dest.slot.0, label %for.cond, label %cleanup4
+
+for.cond:
+  %e.0 = phi i64* [ undef, %cleanup ], [ %incdec.ptr, %for.cond2 ]
+  %pi = ptrtoint i64* %e.0 to i64
+  %incdec.ptr = getelementptr inbounds i64, i64* %e.0, i64 1
+  br label %for.cond2
+
+for.cond2:
+  %storemerge = phi i64 [ %pi, %for.cond ], [ %load, %for.cond2 ]
+  br i1 %B, label %for.cond2, label %for.cond
+
+cleanup4:
+  br label %while.body
+}
+