forked from OSchip/llvm-project
77 lines
3.1 KiB
LLVM
77 lines
3.1 KiB
LLVM
; RUN: llc -O2 -march=hexagon < %s | FileCheck %s
|
|
; Rely on the comments generated by llc. Make sure there are no add/addasl
|
|
; instructions in while.body13 (before the loads).
|
|
; CHECK: while.body13
|
|
; CHECK-NOT: add
|
|
; CHECK: memw
|
|
|
|
%struct.1 = type { i32, i32 }
|
|
%struct.2 = type { [24 x i32], [24 x i32], [24 x i32], [24 x i32], [24 x i32], [24 x i32], [24 x i32], [24 x i32], [24 x i32], [24 x i32], [24 x i32], [24 x i32], [24 x i32], [24 x i32], [24 x i32], [24 x i32], [24 x i32], [3 x i32], [24 x i32], [8 x %struct.1], [5 x i32] }
|
|
|
|
@A1 = global i64 zeroinitializer
|
|
@A2 = global i64 zeroinitializer
|
|
@B1 = global i32 zeroinitializer
|
|
@B2 = global i32 zeroinitializer
|
|
@C1 = global i8 zeroinitializer
|
|
|
|
declare i32 @llvm.hexagon.S2.cl0(i32) nounwind readnone
|
|
declare i32 @llvm.hexagon.S2.setbit.r(i32, i32) nounwind readnone
|
|
declare i64 @llvm.hexagon.M2.vmpy2s.s0(i32, i32) nounwind readnone
|
|
declare i64 @llvm.hexagon.M2.vmac2s.s0(i64, i32, i32) nounwind readnone
|
|
declare i64 @llvm.hexagon.A2.vaddws(i64, i64) nounwind readnone
|
|
declare i64 @llvm.hexagon.A2.vsubws(i64, i64) nounwind readnone
|
|
declare i32 @llvm.hexagon.A4.modwrapu(i32, i32) nounwind readnone
|
|
|
|
define void @foo(i32 %n) nounwind {
|
|
entry:
|
|
br label %while.body
|
|
|
|
while.body:
|
|
%count = phi i32 [ 0, %entry ], [ %next, %while.end ]
|
|
%idx = phi i32 [ 0, %entry ], [ %15, %while.end ]
|
|
%0 = load i32, i32* @B1, align 4
|
|
%1 = load i32, i32* @B2, align 8
|
|
%2 = and i32 %1, %0
|
|
br label %while.body13
|
|
|
|
while.body13: ; preds = %while.body, %if.end
|
|
%3 = phi i64 [ %13, %if.end ], [ 0, %while.body ]
|
|
%4 = phi i64 [ %14, %if.end ], [ 0, %while.body ]
|
|
%m = phi i32 [ %6, %if.end ], [ %2, %while.body ]
|
|
%5 = tail call i32 @llvm.hexagon.S2.cl0(i32 %m)
|
|
%6 = tail call i32 @llvm.hexagon.S2.setbit.r(i32 %m, i32 %5)
|
|
%cgep85 = getelementptr [10 x %struct.2], [10 x %struct.2]* inttoptr (i32 -121502345 to [10 x %struct.2]*), i32 0, i32 %idx
|
|
%cgep90 = getelementptr %struct.2, %struct.2* %cgep85, i32 0, i32 12, i32 %5
|
|
%7 = load i32, i32* %cgep90, align 4
|
|
%8 = tail call i64 @llvm.hexagon.M2.vmpy2s.s0(i32 %7, i32 %7)
|
|
%cgep91 = getelementptr %struct.2, %struct.2* %cgep85, i32 0, i32 13, i32 %5
|
|
%9 = load i32, i32* %cgep91, align 4
|
|
%10 = tail call i64 @llvm.hexagon.M2.vmac2s.s0(i64 %8, i32 %9, i32 %9)
|
|
%11 = load i8, i8* @C1, align 1
|
|
%and24 = and i8 %11, 1
|
|
%cmp = icmp eq i8 %and24, 0
|
|
br i1 %cmp, label %if.then, label %if.end
|
|
|
|
if.then: ; preds = %while.body13
|
|
%12 = tail call i64 @llvm.hexagon.A2.vaddws(i64 %3, i64 %10)
|
|
store i64 %12, i64* @A1, align 8
|
|
br label %if.end
|
|
|
|
if.end: ; preds = %if.then, %while.body13
|
|
%13 = phi i64 [ %12, %if.then ], [ %3, %while.body13 ]
|
|
%14 = tail call i64 @llvm.hexagon.A2.vsubws(i64 %4, i64 %10)
|
|
%tobool12 = icmp eq i32 %6, 0
|
|
br i1 %tobool12, label %while.end, label %while.body13
|
|
|
|
while.end:
|
|
%add40 = add i32 %idx, 1
|
|
%15 = tail call i32 @llvm.hexagon.A4.modwrapu(i32 %add40, i32 10) nounwind
|
|
%next = add i32 %count, 1
|
|
%cc = icmp eq i32 %next, %n
|
|
br i1 %cc, label %end, label %while.body
|
|
|
|
end:
|
|
store i64 %10, i64* @A2, align 8
|
|
ret void
|
|
}
|