Temporarily Revert "Add basic loop fusion pass."

As it's causing some bot failures (and per request from kbarton).

This reverts commit r358543/ab70da07286e618016e78247e4a24fcb84077fda.

llvm-svn: 358546

6 files changed, 0 insertions, 406 deletions

diff --git a/llvm/test/Transforms/Inline/ARM/inline-fp.ll b/llvm/test/Transforms/Inline/ARM/inline-fp.ll
deleted file mode 100644
index be3dd2a93fd..00000000000
--- a/llvm/test/Transforms/Inline/ARM/inline-fp.ll
+++ /dev/null
@@ -1,113 +0,0 @@
-; RUN: opt -S -inline -mtriple=arm-eabi -pass-remarks=.* -pass-remarks-missed=.* < %s 2>&1 | FileCheck %s -check-prefix=NOFP
-; RUN: opt -S -inline -mtriple=arm-eabi -mattr=+vfp2 -pass-remarks=.* -pass-remarks-missed=.* < %s 2>&1 | FileCheck %s -check-prefix=FULLFP
-; RUN: opt -S -inline -mtriple=arm-eabi -mattr=+vfp2,+fp-only-sp -pass-remarks=.* -pass-remarks-missed=.* < %s 2>&1 | FileCheck %s -check-prefix=SINGLEFP
-; Make sure that soft float implementations are calculated as being more expensive
-; to the inliner.
-
-; NOFP-DAG: single not inlined into test_single because too costly to inline (cost=125, threshold=75)
-; NOFP-DAG: single not inlined into test_single because too costly to inline (cost=125, threshold=75)
-; NOFP-DAG: single_cheap inlined into test_single_cheap with (cost=-15, threshold=75)
-; NOFP-DAG: single_cheap inlined into test_single_cheap with (cost=-15015, threshold=75)
-; NOFP-DAG: double not inlined into test_double because too costly to inline (cost=125, threshold=75)
-; NOFP-DAG: double not inlined into test_double because too costly to inline (cost=125, threshold=75)
-; NOFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
-; NOFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
-
-; FULLFP-DAG: single inlined into test_single with (cost=0, threshold=75)
-; FULLFP-DAG: single inlined into test_single with (cost=-15000, threshold=75)
-; FULLFP-DAG: single_cheap inlined into test_single_cheap with (cost=-15, threshold=75)
-; FULLFP-DAG: single_cheap inlined into test_single_cheap with (cost=-15015, threshold=75)
-; FULLFP-DAG: double inlined into test_double with (cost=0, threshold=75)
-; FULLFP-DAG: double inlined into test_double with (cost=-15000, threshold=75)
-; FULLFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
-; FULLFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
-
-; SINGLEFP-DAG: single inlined into test_single with (cost=0, threshold=75)
-; SINGLEFP-DAG: single inlined into test_single with (cost=-15000, threshold=75)
-; SINGLEFP-DAG: single_cheap inlined into test_single_cheap with (cost=-15, threshold=75)
-; SINGLEFP-DAG: single_cheap inlined into test_single_cheap with (cost=-15015, threshold=75)
-; SINGLEFP-DAG: double not inlined into test_double because too costly to inline (cost=125, threshold=75)
-; SINGLEFP-DAG: double not inlined into test_double because too costly to inline (cost=125, threshold=75)
-; SINGLEFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
-; SINGLEFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
-
-define i32 @test_single(i32 %a, i8 %b, i32 %c, i8 %d) #0 {
-  %call = call float @single(i32 %a, i8 zeroext %b)
-  %call2 = call float @single(i32 %c, i8 zeroext %d)
-  ret i32 0
-}
-
-define i32 @test_single_cheap(i32 %a, i8 %b, i32 %c, i8 %d) #0 {
-  %call = call float @single_cheap(i32 %a, i8 zeroext %b)
-  %call2 = call float @single_cheap(i32 %c, i8 zeroext %d)
-  ret i32 0
-}
-
-define i32 @test_double(i32 %a, i8 %b, i32 %c, i8 %d) #0 {
-  %call = call double @double(i32 %a, i8 zeroext %b)
-  %call2 = call double @double(i32 %c, i8 zeroext %d)
-  ret i32 0
-}
-
-define i32 @test_single_force_soft(i32 %a, i8 %b, i32 %c, i8 %d) #1 {
-  %call = call float @single_force_soft(i32 %a, i8 zeroext %b) #1
-  %call2 = call float @single_force_soft(i32 %c, i8 zeroext %d) #1
-  ret i32 0
-}
-
-define internal float @single(i32 %response, i8 zeroext %value1) #0 {
-entry:
-  %conv = zext i8 %value1 to i32
-  %sub = add nsw i32 %conv, -1
-  %conv1 = sitofp i32 %sub to float
-  %0 = tail call float @llvm.pow.f32(float 0x3FF028F5C0000000, float %conv1)
-  %mul = fmul float %0, 2.620000e+03
-  %conv2 = sitofp i32 %response to float
-  %sub3 = fsub float %conv2, %mul
-  %div = fdiv float %sub3, %mul
-  ret float %div
-}
-
-define internal float @single_cheap(i32 %response, i8 zeroext %value1) #0 {
-entry:
-  %conv = zext i8 %value1 to i32
-  %sub = add nsw i32 %conv, -1
-  %conv1 = bitcast i32 %sub to float
-  %conv2 = bitcast i32 %response to float
-  %0 = tail call float @llvm.pow.f32(float %conv2, float %conv1)
-  %1 = tail call float @llvm.pow.f32(float %0, float %0)
-  %2 = tail call float @llvm.pow.f32(float %1, float %1)
-  ret float %2
-}
-
-define internal double @double(i32 %response, i8 zeroext %value1) #0 {
-entry:
-  %conv = zext i8 %value1 to i32
-  %sub = add nsw i32 %conv, -1
-  %conv1 = sitofp i32 %sub to double
-  %0 = tail call double @llvm.pow.f64(double 0x3FF028F5C0000000, double %conv1)
-  %mul = fmul double %0, 2.620000e+03
-  %conv2 = sitofp i32 %response to double
-  %sub3 = fsub double %conv2, %mul
-  %div = fdiv double %sub3, %mul
-  ret double %div
-}
-
-define internal float @single_force_soft(i32 %response, i8 zeroext %value1) #1 {
-entry:
-  %conv = zext i8 %value1 to i32
-  %sub = add nsw i32 %conv, -1
-  %conv1 = sitofp i32 %sub to float
-  %0 = tail call float @llvm.pow.f32(float 0x3FF028F5C0000000, float %conv1)
-  %mul = fmul float %0, 2.620000e+03
-  %conv2 = sitofp i32 %response to float
-  %sub3 = fsub float %conv2, %mul
-  %div = fdiv float %sub3, %mul
-  ret float %div
-}
-
-declare float @llvm.pow.f32(float, float) optsize minsize
-declare double @llvm.pow.f64(double, double) optsize minsize
-
-attributes #0 = { optsize }
-attributes #1 = { optsize "use-soft-float"="true" "target-features"="+soft-float" }
diff --git a/llvm/test/Transforms/Inline/ARM/inline-target-attr.ll b/llvm/test/Transforms/Inline/ARM/inline-target-attr.ll
deleted file mode 100644
index 5bbecd20352..00000000000
--- a/llvm/test/Transforms/Inline/ARM/inline-target-attr.ll
+++ /dev/null
@@ -1,60 +0,0 @@
-; RUN: opt < %s -mtriple=arm-unknown-linux-gnu -S -inline | FileCheck %s
-; RUN: opt < %s -mtriple=arm-unknown-linux-gnu -S -passes='cgscc(inline)' | FileCheck %s
-; Check that we only inline when we have compatible target attributes.
-; ARM has implemented a target attribute that will verify that the attribute
-; sets are compatible.
-
-define i32 @foo() #0 {
-entry:
-  %call = call i32 (...) @baz()
-  ret i32 %call
-; CHECK-LABEL: foo
-; CHECK: call i32 (...) @baz()
-}
-declare i32 @baz(...) #0
-
-define i32 @bar() #1 {
-entry:
-  %call = call i32 @foo()
-  ret i32 %call
-; CHECK-LABEL: bar
-; CHECK: call i32 (...) @baz()
-}
-
-define i32 @qux() #0 {
-entry:
-  %call = call i32 @bar()
-  ret i32 %call
-; CHECK-LABEL: qux
-; CHECK: call i32 @bar()
-}
-
-define i32 @thumb_fn() #2 {
-entry:
-  %call = call i32 @foo()
-  ret i32 %call
-; CHECK-LABEL: thumb_fn
-; CHECK: call i32 @foo
-}
-
-define i32 @strict_align() #3 {
-entry:
-  %call = call i32 @foo()
-  ret i32 %call
-; CHECK-LABEL: strict_align
-; CHECK: call i32 (...) @baz()
-}
-
-define i32 @soft_float_fn() #4 {
-entry:
-  %call = call i32 @foo()
-  ret i32 %call
-; CHECK-LABEL: soft_float_fn
-; CHECK: call i32 @foo
-}
-
-attributes #0 = { "target-cpu"="generic" "target-features"="+dsp,+neon" }
-attributes #1 = { "target-cpu"="generic" "target-features"="+dsp,+neon,+fp16" }
-attributes #2 = { "target-cpu"="generic" "target-features"="+dsp,+neon,+fp16,+thumb-mode" }
-attributes #3 = { "target-cpu"="generic" "target-features"="+dsp,+neon,+strict-align" }
-attributes #4 = { "target-cpu"="generic" "target-features"="+dsp,+neon,+fp16,+soft-float" }
diff --git a/llvm/test/Transforms/Inline/ARM/lit.local.cfg b/llvm/test/Transforms/Inline/ARM/lit.local.cfg
deleted file mode 100644
index 236e1d34416..00000000000
--- a/llvm/test/Transforms/Inline/ARM/lit.local.cfg
+++ /dev/null
@@ -1,2 +0,0 @@
-if not 'ARM' in config.root.targets:
-    config.unsupported = True
diff --git a/llvm/test/Transforms/Inline/ARM/loop-add.ll b/llvm/test/Transforms/Inline/ARM/loop-add.ll
deleted file mode 100644
index a4717bc95b7..00000000000
--- a/llvm/test/Transforms/Inline/ARM/loop-add.ll
+++ /dev/null
@@ -1,95 +0,0 @@
-; RUN: opt -inline %s -S | FileCheck %s
-
-target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
-target triple = "thumbv7m-arm-none-eabi"
-
-; CHECK-LABEL: void @doCalls
-define void @doCalls(i8* nocapture %p1, i8* nocapture %p2, i32 %n) #0 {
-entry:
-  %div = lshr i32 %n, 1
-; CHECK: call void @LoopCall
-  tail call void @LoopCall(i8* %p1, i8* %p2, i32 %div) #0
-
-  %div2 = lshr i32 %n, 2
-; CHECK: call void @LoopCall
-  tail call void @LoopCall(i8* %p1, i8* %p2, i32 %div2) #0
-
-; CHECK-NOT: call void @LoopCall
-  tail call void @LoopCall(i8* %p2, i8* %p1, i32 0) #0
-
-; CHECK-NOT: call void @LoopCall_internal
-  tail call void @LoopCall_internal(i8* %p1, i8* %p2, i32 %div2) #0
-
-  %div3 = lshr i32 %n, 4
-; CHECK-NOT: call void @SimpleCall
-  tail call void @SimpleCall(i8* %p2, i8* %p1, i32 %div3) #0
-  ret void
-}
-
-; CHECK-LABEL: define void @LoopCall
-define void @LoopCall(i8* nocapture %dest, i8* nocapture readonly %source, i32 %num) #0 {
-entry:
-  %c = icmp ne i32 %num, 0
-  br i1 %c, label %while.cond, label %while.end
-
-while.cond:                                       ; preds = %while.body, %entry
-  %num.addr.0 = phi i32 [ %num, %entry ], [ %dec, %while.body ]
-  %p_dest.0 = phi i8* [ %dest, %entry ], [ %incdec.ptr2, %while.body ]
-  %p_source.0 = phi i8* [ %source, %entry ], [ %incdec.ptr, %while.body ]
-  %cmp = icmp eq i32 %num.addr.0, 0
-  br i1 %cmp, label %while.end, label %while.body
-
-while.body:                                       ; preds = %while.cond
-  %incdec.ptr = getelementptr inbounds i8, i8* %p_source.0, i32 1
-  %0 = load i8, i8* %p_source.0, align 1
-  %1 = trunc i32 %num.addr.0 to i8
-  %conv1 = add i8 %0, %1
-  %incdec.ptr2 = getelementptr inbounds i8, i8* %p_dest.0, i32 1
-  store i8 %conv1, i8* %p_dest.0, align 1
-  %dec = add i32 %num.addr.0, -1
-  br label %while.cond
-
-while.end:                                        ; preds = %while.cond
-  ret void
-}
-
-; CHECK-LABEL-NOT: define void @LoopCall_internal
-define internal void @LoopCall_internal(i8* nocapture %dest, i8* nocapture readonly %source, i32 %num) #0 {
-entry:
-  %c = icmp ne i32 %num, 0
-  br i1 %c, label %while.cond, label %while.end
-
-while.cond:                                       ; preds = %while.body, %entry
-  %num.addr.0 = phi i32 [ %num, %entry ], [ %dec, %while.body ]
-  %p_dest.0 = phi i8* [ %dest, %entry ], [ %incdec.ptr2, %while.body ]
-  %p_source.0 = phi i8* [ %source, %entry ], [ %incdec.ptr, %while.body ]
-  %cmp = icmp eq i32 %num.addr.0, 0
-  br i1 %cmp, label %while.end, label %while.body
-
-while.body:                                       ; preds = %while.cond
-  %incdec.ptr = getelementptr inbounds i8, i8* %p_source.0, i32 1
-  %0 = load i8, i8* %p_source.0, align 1
-  %1 = trunc i32 %num.addr.0 to i8
-  %conv1 = add i8 %0, %1
-  %incdec.ptr2 = getelementptr inbounds i8, i8* %p_dest.0, i32 1
-  store i8 %conv1, i8* %p_dest.0, align 1
-  %dec = add i32 %num.addr.0, -1
-  br label %while.cond
-
-while.end:                                        ; preds = %while.cond
-  ret void
-}
-
-; CHECK-LABEL: define void @SimpleCall
-define void @SimpleCall(i8* nocapture %dest, i8* nocapture readonly %source, i32 %num) #0 {
-entry:
-  %arrayidx = getelementptr inbounds i8, i8* %source, i32 %num
-  %0 = load i8, i8* %arrayidx, align 1
-  %1 = xor i8 %0, 127
-  %arrayidx2 = getelementptr inbounds i8, i8* %dest, i32 %num
-  store i8 %1, i8* %arrayidx2, align 1
-  ret void
-}
-
-attributes #0 = { minsize optsize }
-
diff --git a/llvm/test/Transforms/Inline/ARM/loop-memcpy.ll b/llvm/test/Transforms/Inline/ARM/loop-memcpy.ll
deleted file mode 100644
index 3b3625c6027..00000000000
--- a/llvm/test/Transforms/Inline/ARM/loop-memcpy.ll
+++ /dev/null
@@ -1,87 +0,0 @@
-; RUN: opt -inline %s -S | FileCheck %s
-
-target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
-target triple = "thumbv7m-arm-none-eabi"
-
-; CHECK-LABEL: define void @matcpy
-define void @matcpy(i8* %dest, i8* %source, i32 %num) #0 {
-entry:
-  %0 = ptrtoint i8* %dest to i32
-  %1 = ptrtoint i8* %source to i32
-  %2 = xor i32 %0, %1
-  %3 = and i32 %2, 3
-  %cmp = icmp eq i32 %3, 0
-  br i1 %cmp, label %if.then, label %if.else20
-
-if.then:                                          ; preds = %entry
-  %sub = sub i32 0, %0
-  %and2 = and i32 %sub, 3
-  %add = or i32 %and2, 4
-  %cmp3 = icmp ugt i32 %add, %num
-  br i1 %cmp3, label %if.else, label %if.then4
-
-if.then4:                                         ; preds = %if.then
-  %sub5 = sub i32 %num, %and2
-  %shr = and i32 %sub5, -4
-  %sub7 = sub i32 %sub5, %shr
-  %tobool = icmp eq i32 %and2, 0
-  br i1 %tobool, label %if.end, label %if.then8
-
-if.then8:                                         ; preds = %if.then4
-; CHECK: call fastcc void @memcpy
-  call fastcc void @memcpy(i8* %dest, i8* %source, i32 %and2) #0
-  %add.ptr = getelementptr inbounds i8, i8* %dest, i32 %and2
-  %add.ptr9 = getelementptr inbounds i8, i8* %source, i32 %and2
-  br label %if.end
-
-if.end:                                           ; preds = %if.then4, %if.then8
-  %p_dest.0 = phi i8* [ %add.ptr, %if.then8 ], [ %dest, %if.then4 ]
-  %p_source.0 = phi i8* [ %add.ptr9, %if.then8 ], [ %source, %if.then4 ]
-  %tobool14 = icmp eq i32 %sub7, 0
-  br i1 %tobool14, label %if.end22, label %if.then15
-
-if.then15:                                        ; preds = %if.end
-  %add.ptr13 = getelementptr inbounds i8, i8* %p_source.0, i32 %shr
-  %add.ptr11 = getelementptr inbounds i8, i8* %p_dest.0, i32 %shr
-; CHECK: call fastcc void @memcpy
-  call fastcc void @memcpy(i8* %add.ptr11, i8* %add.ptr13, i32 %sub7) #0
-  br label %if.end22
-
-if.else:                                          ; preds = %if.then
-  call fastcc void @memcpy(i8* %dest, i8* %source, i32 %num) #0
-  br label %if.end22
-
-if.else20:                                        ; preds = %entry
-  call fastcc void @memcpy(i8* %dest, i8* %source, i32 %num) #0
-  br label %if.end22
-
-if.end22:                                         ; preds = %if.then15, %if.end, %if.else, %if.else20
-  ret void
-}
-
-; CHECK-LABEL: define internal void @memcpy
-define internal void @memcpy(i8* nocapture %dest, i8* nocapture readonly %source, i32 %num) #0 {
-entry:
-  br label %while.cond
-
-while.cond:                                       ; preds = %while.body, %entry
-  %num.addr.0 = phi i32 [ %num, %entry ], [ %dec, %while.body ]
-  %p_dest.0 = phi i8* [ %dest, %entry ], [ %incdec.ptr1, %while.body ]
-  %p_source.0 = phi i8* [ %source, %entry ], [ %incdec.ptr, %while.body ]
-  %cmp = icmp eq i32 %num.addr.0, 0
-  br i1 %cmp, label %while.end, label %while.body
-
-while.body:                                       ; preds = %while.cond
-  %incdec.ptr = getelementptr inbounds i8, i8* %p_source.0, i32 1
-  %0 = load i8, i8* %p_source.0, align 1
-  %incdec.ptr1 = getelementptr inbounds i8, i8* %p_dest.0, i32 1
-  store i8 %0, i8* %p_dest.0, align 1
-  %dec = add i32 %num.addr.0, -1
-  br label %while.cond
-
-while.end:                                        ; preds = %while.cond
-  ret void
-}
-
-attributes #0 = { minsize optsize }
-
diff --git a/llvm/test/Transforms/Inline/ARM/loop-noinline.ll b/llvm/test/Transforms/Inline/ARM/loop-noinline.ll
deleted file mode 100644
index 8438d16b03e..00000000000
--- a/llvm/test/Transforms/Inline/ARM/loop-noinline.ll
+++ /dev/null
@@ -1,49 +0,0 @@
-; RUN: opt -inline %s -S | FileCheck %s
-
-target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
-target triple = "thumbv7m-arm-none-eabi"
-
-; Check we don't inline loops at -Oz. They tend to be larger than we
-; expect.
-
-; CHECK: define i8* @H
-@digits = constant [16 x i8] c"0123456789ABCDEF", align 1
-define i8* @H(i8* %p, i32 %val, i32 %num) #0 {
-entry:
-  br label %do.body
-
-do.body:                                          ; preds = %do.body, %entry
-  %p.addr.0 = phi i8* [ %p, %entry ], [ %incdec.ptr, %do.body ]
-  %val.addr.0 = phi i32 [ %val, %entry ], [ %shl, %do.body ]
-  %num.addr.0 = phi i32 [ %num, %entry ], [ %dec, %do.body ]
-  %shr = lshr i32 %val.addr.0, 28
-  %arrayidx = getelementptr inbounds [16 x i8], [16 x i8]* @digits, i32 0, i32 %shr
-  %0 = load i8, i8* %arrayidx, align 1
-  %incdec.ptr = getelementptr inbounds i8, i8* %p.addr.0, i32 1
-  store i8 %0, i8* %p.addr.0, align 1
-  %shl = shl i32 %val.addr.0, 4
-  %dec = add i32 %num.addr.0, -1
-  %tobool = icmp eq i32 %dec, 0
-  br i1 %tobool, label %do.end, label %do.body
-
-do.end:                                           ; preds = %do.body
-  %scevgep = getelementptr i8, i8* %p, i32 %num
-  ret i8* %scevgep
-}
-
-define nonnull i8* @call1(i8* %p, i32 %val, i32 %num) #0 {
-entry:
-; CHECK: tail call i8* @H
-  %call = tail call i8* @H(i8* %p, i32 %val, i32 %num) #0
-  ret i8* %call
-}
-
-define nonnull i8* @call2(i8* %p, i32 %val) #0 {
-entry:
-; CHECK: tail call i8* @H
-  %call = tail call i8* @H(i8* %p, i32 %val, i32 32) #0
-  ret i8* %call
-}
-
-attributes #0 = { minsize optsize }
-