vendor/llvm/llvm-trunk-r304149

4 files changed, 73 insertions, 14 deletions

diff --git a/test/Transforms/LoopStrengthReduce/X86/incorrect-offset-scaling.ll b/test/Transforms/LoopStrengthReduce/X86/incorrect-offset-scaling.ll
index 3adb8bcf514d..00c3222b0051 100644
--- a/test/Transforms/LoopStrengthReduce/X86/incorrect-offset-scaling.ll
+++ b/test/Transforms/LoopStrengthReduce/X86/incorrect-offset-scaling.ll
@@ -25,7 +25,7 @@ L2:                                               ; preds = %idxend.8
 if6:                                              ; preds = %idxend.8
   %r2 = add i64 %0, -1
   %r3 = load i64, i64* %1, align 8
-; CHECK-NOT:  %r2
+; CHECK:  %r2 = add i64 %0, -1
 ; CHECK:  %r3 = load i64
   br label %ib
 
@@ -36,13 +36,11 @@ ib:                                               ; preds = %if6
   %r4 = mul i64 %r3, %r0
   %r5 = add i64 %r2, %r4
   %r6 = icmp ult i64 %r5, undef
-; CHECK:  [[MUL1:%[0-9]+]] = mul i64 %lsr.iv, %r3
-; CHECK:  [[ADD1:%[0-9]+]] = add i64 [[MUL1]], -1
-; CHECK:  add i64 %{{.}}, [[ADD1]]
-; CHECK:  %r6
+; CHECK:  %r4 = mul i64 %r3, %lsr.iv
+; CHECK:  %r5 = add i64 %r2, %r4
+; CHECK:  %r6 = icmp ult i64 %r5, undef
+; CHECK:  %r7 = getelementptr i64, i64* undef, i64 %r5
   %r7 = getelementptr i64, i64* undef, i64 %r5
   store i64 1, i64* %r7, align 8
-; CHECK:  [[MUL2:%[0-9]+]] = mul i64 %lsr.iv, %r3
-; CHECK:  [[ADD2:%[0-9]+]] = add i64 [[MUL2]], -1
   br label %L
 }
diff --git a/test/Transforms/LoopStrengthReduce/lsr-expand-quadratic.ll b/test/Transforms/LoopStrengthReduce/X86/lsr-expand-quadratic.ll
index aa688d999e60..a7731bfcec56 100644
--- a/test/Transforms/LoopStrengthReduce/lsr-expand-quadratic.ll
+++ b/test/Transforms/LoopStrengthReduce/X86/lsr-expand-quadratic.ll
@@ -1,5 +1,14 @@
+; REQUIRES: x86
 ; RUN: opt -loop-reduce -S < %s | FileCheck %s
 
+; Strength reduction analysis here relies on IV Users analysis, that
+; only finds users among instructions with types that are treated as
+; legal by the data layout. When running this test on pure non-x86
+; configs (for example, ARM 64), it gets confused with the target
+; triple and uses a default data layout instead. This default layout
+; does not have any legal types (even i32), so the transformation
+; does not happen.
+
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx"
 
@@ -7,16 +16,23 @@ target triple = "x86_64-apple-macosx"
 ;
 ; SCEV expander cannot expand quadratic recurrences outside of the
 ; loop. This recurrence depends on %sub.us, so can't be expanded.
+; We cannot fold SCEVUnknown (sub.us) with recurrences since it is
+; declared after the loop.
 ;
 ; CHECK-LABEL: @test2
 ; CHECK-LABEL: test2.loop:
-; CHECK: %lsr.iv = phi i32 [ %lsr.iv.next, %test2.loop ], [ -16777216, %entry ]
-; CHECK: %lsr.iv.next = add nsw i32 %lsr.iv, 16777216
+; CHECK:  %lsr.iv1 = phi i32 [ %lsr.iv.next2, %test2.loop ], [ -16777216, %entry ]
+; CHECK:  %lsr.iv = phi i32 [ %lsr.iv.next, %test2.loop ], [ -1, %entry ]
+; CHECK:  %lsr.iv.next = add nsw i32 %lsr.iv, 1
+; CHECK:  %lsr.iv.next2 = add nsw i32 %lsr.iv1, 16777216
 ;
 ; CHECK-LABEL: for.end:
-; CHECK: %sub.cond.us = sub nsw i32 %inc1115.us, %sub.us
-; CHECK: %sext.us = mul i32 %lsr.iv.next, %sub.cond.us
-; CHECK: %f = ashr i32 %sext.us, 24
+; CHECK:  %tobool.us = icmp eq i32 %lsr.iv.next2, 0
+; CHECK:  %sub.us = select i1 %tobool.us, i32 0, i32 0
+; CHECK:  %1 = sub i32 0, %sub.us
+; CHECK:  %2 = add i32 %1, %lsr.iv.next
+; CHECK:  %sext.us = mul i32 %lsr.iv.next2, %2
+; CHECK:  %f = ashr i32 %sext.us, 24
 ; CHECK: ret i32 %f
 define i32 @test2() {
 entry:
diff --git a/test/Transforms/LoopStrengthReduce/nonintegral.ll b/test/Transforms/LoopStrengthReduce/nonintegral.ll
new file mode 100644
index 000000000000..5648e3aa74af
--- /dev/null
+++ b/test/Transforms/LoopStrengthReduce/nonintegral.ll
@@ -0,0 +1,45 @@
+; RUN: opt -S -loop-reduce < %s | FileCheck %s
+
+; Address Space 10 is non-integral. The optimizer is not allowed to use
+; ptrtoint/inttoptr instructions. Make sure that this doesn't happen
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128-ni:10:11:12"
+target triple = "x86_64-unknown-linux-gnu"
+
+define void @japi1__unsafe_getindex_65028(i64 addrspace(10)* %arg) {
+; CHECK-NOT: inttoptr
+; CHECK-NOT: ptrtoint
+; How exactly SCEV chooses to materialize isn't all that important, as
+; long as it doesn't try to round-trip through integers. As of this writing,
+; it emits a byte-wise gep, which is fine.
+; CHECK: getelementptr i64, i64 addrspace(10)* {{.*}}, i64 {{.*}}
+top:
+  br label %L86
+
+L86:                                              ; preds = %L86, %top
+  %i.0 = phi i64 [ 0, %top ], [ %tmp, %L86 ]
+  %tmp = add i64 %i.0, 1
+  br i1 undef, label %L86, label %if29
+
+if29:                                             ; preds = %L86
+  %tmp1 = shl i64 %tmp, 1
+  %tmp2 = add i64 %tmp1, -2
+  br label %if31
+
+if31:                                             ; preds = %if38, %if29
+  %"#temp#1.sroa.0.022" = phi i64 [ 0, %if29 ], [ %tmp3, %if38 ]
+  br label %L119
+
+L119:                                             ; preds = %L119, %if31
+  %i5.0 = phi i64 [ %"#temp#1.sroa.0.022", %if31 ], [ %tmp3, %L119 ]
+  %tmp3 = add i64 %i5.0, 1
+  br i1 undef, label %L119, label %if38
+
+if38:                                             ; preds = %L119
+  %tmp4 = add i64 %tmp2, %i5.0
+  %tmp5 = getelementptr i64, i64 addrspace(10)* %arg, i64 %tmp4
+  %tmp6 = load i64, i64 addrspace(10)* %tmp5
+  br i1 undef, label %done, label %if31
+
+done:                                             ; preds = %if38
+  ret void
+}
diff --git a/test/Transforms/LoopStrengthReduce/post-inc-icmpzero.ll b/test/Transforms/LoopStrengthReduce/post-inc-icmpzero.ll
index fbf55fd81d23..cbf177c0d4b9 100644
--- a/test/Transforms/LoopStrengthReduce/post-inc-icmpzero.ll
+++ b/test/Transforms/LoopStrengthReduce/post-inc-icmpzero.ll
@@ -25,6 +25,8 @@ define void @_Z15IntegerToStringjjR7Vector2(i32 %i, i32 %radix, %struct.Vector2*
 entry:
   %buffer = alloca [33 x i16], align 16
   %add.ptr = getelementptr inbounds [33 x i16], [33 x i16]* %buffer, i64 0, i64 33
+  %sub.ptr.lhs.cast = ptrtoint i16* %add.ptr to i64
+  %sub.ptr.rhs.cast = ptrtoint i16* %add.ptr to i64
   br label %do.body
 
 do.body:                                          ; preds = %do.body, %entry
@@ -46,8 +48,6 @@ do.body:                                          ; preds = %do.body, %entry
 do.end:                                           ; preds = %do.body
   %xap.0 = inttoptr i64 %0 to i1*
   %cap.0 = ptrtoint i1* %xap.0 to i64
-  %sub.ptr.lhs.cast = ptrtoint i16* %add.ptr to i64
-  %sub.ptr.rhs.cast = ptrtoint i16* %incdec.ptr to i64
   %sub.ptr.sub = sub i64 %sub.ptr.lhs.cast, %sub.ptr.rhs.cast
   %sub.ptr.div39 = lshr exact i64 %sub.ptr.sub, 1
   %conv11 = trunc i64 %sub.ptr.div39 to i32