Imported Upstream version 5.18.0.167

Former-commit-id: 289509151e0fee68a1b591a20c9f109c3c789d3a

external/llvm/test/Transforms/LoopUnroll/X86/lit.local.cfg

@@ -1,3 +0,0 @@
-if not 'X86' in config.root.targets:
-    config.unsupported = True
-

external/llvm/test/Transforms/LoopUnroll/X86/mmx.ll

@@ -1,24 +0,0 @@
-; RUN: opt < %s -S -loop-unroll | FileCheck %s
-target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
-target triple = "x86_64-unknown-linux-gnu"
-
-define x86_mmx @f() #0 {
-entry:
-  br label %for.body
-
-for.body:                                         ; preds = %for.body, %entry
-  %phi = phi i32 [ 1, %entry ], [ %add, %for.body ]
-  %add = add i32 %phi, 1
-  %cmp = icmp eq i32 %phi, 0
-  br i1 %cmp, label %exit, label %for.body
-
-exit:                                             ; preds = %for.body
-  %ret = phi x86_mmx [ undef, %for.body ]
-  ; CHECK: %[[ret_ph:.*]] = phi x86_mmx [ undef, %entry
-  ; CHECK: %[[ret_ph1:.*]]  = phi x86_mmx [ undef,
-  ; CHECK: %[[ret:.*]] = phi x86_mmx [ %[[ret_ph]], {{.*}} ], [ %[[ret_ph1]],
-  ; CHECK: ret x86_mmx %[[ret]]
-  ret x86_mmx %ret
-}
-
-attributes #0 = { "target-cpu"="x86-64" }

external/llvm/test/Transforms/LoopUnroll/X86/partial.ll

@@ -1,130 +0,0 @@
-; RUN: opt < %s -S -loop-unroll -mcpu=nehalem | FileCheck %s
-; RUN: opt < %s -S -loop-unroll -mcpu=core -unroll-runtime=0 | FileCheck -check-prefix=CHECK-NOUNRL %s
-target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
-target triple = "x86_64-unknown-linux-gnu"
-
-define void @foo(i32* noalias nocapture readnone %ip, double %alpha, double* noalias nocapture %a, double* noalias nocapture readonly %b) #0 {
-entry:
-  br label %vector.body
-
-vector.body:                                      ; preds = %vector.body, %entry
-  %index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
-  %0 = getelementptr inbounds double, double* %b, i64 %index
-  %1 = bitcast double* %0 to <2 x double>*
-  %wide.load = load <2 x double>, <2 x double>* %1, align 8
-  %.sum9 = or i64 %index, 2
-  %2 = getelementptr double, double* %b, i64 %.sum9
-  %3 = bitcast double* %2 to <2 x double>*
-  %wide.load8 = load <2 x double>, <2 x double>* %3, align 8
-  %4 = fadd <2 x double> %wide.load, <double 1.000000e+00, double 1.000000e+00>
-  %5 = fadd <2 x double> %wide.load8, <double 1.000000e+00, double 1.000000e+00>
-  %6 = getelementptr inbounds double, double* %a, i64 %index
-  %7 = bitcast double* %6 to <2 x double>*
-  store <2 x double> %4, <2 x double>* %7, align 8
-  %.sum10 = or i64 %index, 2
-  %8 = getelementptr double, double* %a, i64 %.sum10
-  %9 = bitcast double* %8 to <2 x double>*
-  store <2 x double> %5, <2 x double>* %9, align 8
-  %index.next = add i64 %index, 4
-  %10 = icmp eq i64 %index.next, 1600
-  br i1 %10, label %for.end, label %vector.body
-
-; FIXME: We should probably unroll this loop by a factor of 2, but the cost
-; model needs to be fixed to account for instructions likely to be folded
-; as part of an addressing mode.
-; CHECK-LABEL: @foo
-; CHECK-NOUNRL-LABEL: @foo
-
-for.end:                                          ; preds = %vector.body
-  ret void
-}
-
-define void @bar(i32* noalias nocapture readnone %ip, double %alpha, double* noalias nocapture %a, double* noalias nocapture readonly %b) #0 {
-entry:
-  br label %vector.body
-
-vector.body:                                      ; preds = %vector.body, %entry
-  %index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
-  %v0 = getelementptr inbounds double, double* %b, i64 %index
-  %v1 = bitcast double* %v0 to <2 x double>*
-  %wide.load = load <2 x double>, <2 x double>* %v1, align 8
-  %v4 = fadd <2 x double> %wide.load, <double 1.000000e+00, double 1.000000e+00>
-  %v5 = fmul <2 x double> %v4, <double 8.000000e+00, double 8.000000e+00>
-  %v6 = getelementptr inbounds double, double* %a, i64 %index
-  %v7 = bitcast double* %v6 to <2 x double>*
-  store <2 x double> %v5, <2 x double>* %v7, align 8
-  %index.next = add i64 %index, 2
-  %v10 = icmp eq i64 %index.next, 1600
-  br i1 %v10, label %for.end, label %vector.body
-
-; FIXME: We should probably unroll this loop by a factor of 2, but the cost
-; model needs to first to fixed to account for instructions likely to be folded
-; as part of an addressing mode.
-
-; CHECK-LABEL: @bar
-; CHECK: fadd
-; CHECK-NEXT: fmul
-; CHECK: fadd
-; CHECK-NEXT: fmul
-
-; CHECK-NOUNRL-LABEL: @bar
-; CHECK-NOUNRL: fadd
-; CHECK-NOUNRL-NEXT: fmul
-; CHECK-NOUNRL-NOT: fadd
-
-for.end:                                          ; preds = %vector.body
-  ret void
-}
-
-define zeroext i16 @test1(i16* nocapture readonly %arr, i32 %n) #0 {
-entry:
-  %cmp25 = icmp eq i32 %n, 0
-  br i1 %cmp25, label %for.end, label %for.body
-
-for.body:                                         ; preds = %entry, %for.body
-  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
-  %reduction.026 = phi i16 [ %add14, %for.body ], [ 0, %entry ]
-  %arrayidx = getelementptr inbounds i16, i16* %arr, i64 %indvars.iv
-  %0 = load i16, i16* %arrayidx, align 2
-  %mul = shl i16 %0, 1
-  %add = add i16 %mul, %reduction.026
-  %sext = mul i64 %indvars.iv, 12884901888
-  %idxprom3 = ashr exact i64 %sext, 32
-  %arrayidx4 = getelementptr inbounds i16, i16* %arr, i64 %idxprom3
-  %1 = load i16, i16* %arrayidx4, align 2
-  %mul2 = shl i16 %1, 1
-  %add7 = add i16 %add, %mul2
-  %sext28 = mul i64 %indvars.iv, 21474836480
-  %idxprom10 = ashr exact i64 %sext28, 32
-  %arrayidx11 = getelementptr inbounds i16, i16* %arr, i64 %idxprom10
-  %2 = load i16, i16* %arrayidx11, align 2
-  %mul3 = shl i16 %2, 1
-  %add14 = add i16 %add7, %mul3
-  %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, %n
-  br i1 %exitcond, label %for.end, label %for.body
-
-for.end:                                          ; preds = %for.body, %entry
-  %reduction.0.lcssa = phi i16 [ 0, %entry ], [ %add14, %for.body ]
-  ret i16 %reduction.0.lcssa
-
-; This loop is too large to be partially unrolled (size=16)
-
-; CHECK-LABEL: @test1
-; CHECK: br
-; CHECK: br
-; CHECK: br
-; CHECK: br
-; CHECK-NOT: br
-
-; CHECK-NOUNRL-LABEL: @test1
-; CHECK-NOUNRL: br
-; CHECK-NOUNRL: br
-; CHECK-NOUNRL: br
-; CHECK-NOUNRL: br
-; CHECK-NOUNRL-NOT: br
-}
-
-attributes #0 = { nounwind uwtable }
-

external/llvm/test/Transforms/LoopUnroll/X86/store_cost.ll

@@ -1,104 +0,0 @@
-; REQUIRES: asserts
-; RUN: opt -mcpu=core-avx2 -loop-unroll --debug-only=loop-unroll -S -unroll-allow-partial < %s 2>&1 | FileCheck %s
-
-target triple = "x86_64-unknown-linux-gnu"
-
-; CHECK: Loop Unroll: F[foo] Loop %loop.2.header
-; CHECK: Loop Size = 27
-; CHECK-NOT: UNROLLING loop %loop.2.header
-; CHECK: Loop Unroll: F[foo] Loop %loop.header
-; CHECK:   Loop Size = 25
-; CHECK: UNROLLING loop %loop.header by 2 
-
-define void @foo(i32 * %out) {
-entry:
-  %0 = alloca [1024 x i32]
-  %x0 = alloca [1024 x i32]
-  %x01 = alloca [1024 x i32]
-  %x02 = alloca [1024 x i32]
-  %x03 = alloca [1024 x i32]
-  %x04 = alloca [1024 x i32]
-  %x05 = alloca [1024 x i32]
-  %x06 = alloca [1024 x i32]
-  br label %loop.header
-
-loop.header:
-  %counter = phi i32 [0, %entry], [%inc, %loop.inc]
-  br label %loop.body
-
-loop.body:
-  %ptr = getelementptr [1024 x i32], [1024 x i32]* %0, i32 0, i32 %counter
-  store i32 %counter, i32* %ptr
-  %val = add i32 %counter, 5
-  %xptr = getelementptr [1024 x i32], [1024 x i32]* %x0, i32 0, i32 %counter
-  store i32 %val, i32* %xptr
-  %val1 = add i32 %counter, 6
-  %xptr1 = getelementptr [1024 x i32], [1024 x i32]* %x01, i32 0, i32 %counter
-  store i32 %val1, i32* %xptr1
-  %val2 = add i32 %counter, 7
-  %xptr2 = getelementptr [1024 x i32], [1024 x i32]* %x02, i32 0, i32 %counter
-  store i32 %val2, i32* %xptr2
-  %val3 = add i32 %counter, 8
-  %xptr3 = getelementptr [1024 x i32], [1024 x i32]* %x03, i32 0, i32 %counter
-  store i32 %val3, i32* %xptr3
-  %val4 = add i32 %counter, 9
-  %xptr4 = getelementptr [1024 x i32], [1024 x i32]* %x04, i32 0, i32 %counter
-  store i32 %val4, i32* %xptr4
-  %val5 = add i32 %counter, 10
-  %xptr5 = getelementptr [1024 x i32], [1024 x i32]* %x05, i32 0, i32 %counter
-  store i32 %val5, i32* %xptr5
-  br label %loop.inc
-
-loop.inc:
-  %inc = add i32 %counter, 2
-  %1 = icmp sge i32 %inc, 1023
-  br i1 %1, label  %exit.0, label %loop.header
-
-exit.0:
-  %2 = getelementptr [1024 x i32], [1024 x i32]* %0, i32 0, i32 5
-  %3 = load i32, i32* %2
-  store i32 %3, i32 * %out
-  br label %loop.2.header
-
-
-loop.2.header:
-  %counter.2 = phi i32 [0, %exit.0], [%inc.2, %loop.2.inc]
-  br label %loop.2.body
-
-loop.2.body:
-  %ptr.2 = getelementptr [1024 x i32], [1024 x i32]* %0, i32 0, i32 %counter.2
-  store i32 %counter.2, i32* %ptr.2
-  %val.2 = add i32 %counter.2, 5
-  %xptr.2 = getelementptr [1024 x i32], [1024 x i32]* %x0, i32 0, i32 %counter.2
-  store i32 %val.2, i32* %xptr.2
-  %val1.2 = add i32 %counter.2, 6
-  %xptr1.2 = getelementptr [1024 x i32], [1024 x i32]* %x01, i32 0, i32 %counter.2
-  store i32 %val1, i32* %xptr1.2
-  %val2.2 = add i32 %counter.2, 7
-  %xptr2.2 = getelementptr [1024 x i32], [1024 x i32]* %x02, i32 0, i32 %counter.2
-  store i32 %val2, i32* %xptr2.2
-  %val3.2 = add i32 %counter.2, 8
-  %xptr3.2 = getelementptr [1024 x i32], [1024 x i32]* %x03, i32 0, i32 %counter.2
-  store i32 %val3.2, i32* %xptr3.2
-  %val4.2 = add i32 %counter.2, 9
-  %xptr4.2 = getelementptr [1024 x i32], [1024 x i32]* %x04, i32 0, i32 %counter.2
-  store i32 %val4.2, i32* %xptr4.2
-  %val5.2 = add i32 %counter.2, 10
-  %xptr5.2 = getelementptr [1024 x i32], [1024 x i32]* %x05, i32 0, i32 %counter.2
-  store i32 %val5.2, i32* %xptr5.2
-  %xptr6.2 = getelementptr [1024 x i32], [1024 x i32]* %x06, i32 0, i32 %counter.2
-  store i32 %val5.2, i32* %xptr6.2
-  br label %loop.2.inc
-
-loop.2.inc:
-  %inc.2 = add i32 %counter.2, 2
-  %4 = icmp sge i32 %inc.2, 1023
-  br i1 %4, label  %exit.2, label %loop.2.header
-
-exit.2:
-  %x2 = getelementptr [1024 x i32], [1024 x i32]* %0, i32 0, i32 6
-  %x3 = load i32, i32* %x2
-  %out2 = getelementptr i32, i32 * %out, i32 1
-  store i32 %3, i32 * %out2
-  ret void
-}