llvm-project/llvm/test/CodeGen/X86/cmov.ll

221 lines
6.4 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -verify-machineinstrs -mtriple=x86_64-unknown-unknown -disable-cgp-select2branch -x86-cmov-converter=false | FileCheck %s
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"
define i32 @test1(i32 %x, i32 %n, i32 %w, i32* %vp) nounwind readnone {
; CHECK-LABEL: test1:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: btl %esi, %edi
; CHECK-NEXT: movl $12, %eax
; CHECK-NEXT: cmovael (%rcx), %eax
; CHECK-NEXT: retq
entry:
%0 = lshr i32 %x, %n
%1 = and i32 %0, 1
%toBool = icmp eq i32 %1, 0
%v = load i32, i32* %vp
%.0 = select i1 %toBool, i32 %v, i32 12
ret i32 %.0
}
define i32 @test2(i32 %x, i32 %n, i32 %w, i32* %vp) nounwind readnone {
; CHECK-LABEL: test2:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: btl %esi, %edi
; CHECK-NEXT: movl $12, %eax
; CHECK-NEXT: cmovbl (%rcx), %eax
; CHECK-NEXT: retq
entry:
%0 = lshr i32 %x, %n
%1 = and i32 %0, 1
%toBool = icmp eq i32 %1, 0
%v = load i32, i32* %vp
%.0 = select i1 %toBool, i32 12, i32 %v
ret i32 %.0
}
; x86's 32-bit cmov zeroes the high 32 bits of the destination. Make
; sure CodeGen takes advantage of that to avoid an unnecessary
; zero-extend (movl) after the cmov.
declare void @bar(i64) nounwind
define void @test3(i64 %a, i64 %b, i1 %p) nounwind {
; CHECK-LABEL: test3:
; CHECK: # %bb.0:
; CHECK-NEXT: pushq %rax
; CHECK-NEXT: testb $1, %dl
; CHECK-NEXT: cmovel %esi, %edi
; CHECK-NEXT: callq bar
; CHECK-NEXT: popq %rax
; CHECK-NEXT: retq
%c = trunc i64 %a to i32
%d = trunc i64 %b to i32
%e = select i1 %p, i32 %c, i32 %d
%f = zext i32 %e to i64
call void @bar(i64 %f)
ret void
}
; CodeGen shouldn't try to do a setne after an expanded 8-bit conditional
; move without recomputing EFLAGS, because the expansion of the conditional
; move with control flow may clobber EFLAGS (e.g., with xor, to set the
; register to zero).
; The test is a little awkward; the important part is that there's a test before the
; setne.
; PR4814
@g_3 = external global i8
@g_96 = external global i8
@g_100 = external global i8
@_2E_str = external constant [15 x i8], align 1
define i1 @test4() nounwind {
; CHECK-LABEL: test4:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movsbl {{.*}}(%rip), %edx
; CHECK-NEXT: movzbl %dl, %ecx
; CHECK-NEXT: shrl $7, %ecx
; CHECK-NEXT: xorl $1, %ecx
; CHECK-NEXT: # kill: def $cl killed $cl killed $ecx
; CHECK-NEXT: sarl %cl, %edx
; CHECK-NEXT: movb {{.*}}(%rip), %al
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: je .LBB3_2
; CHECK-NEXT: # %bb.1: # %bb.i.i.i
; CHECK-NEXT: movb {{.*}}(%rip), %cl
; CHECK-NEXT: .LBB3_2: # %func_4.exit.i
; CHECK-NEXT: pushq %rbx
; CHECK-NEXT: testb %dl, %dl
; CHECK-NEXT: setne %bl
; CHECK-NEXT: movl %eax, %ecx
; CHECK-NEXT: je .LBB3_4
; CHECK-NEXT: # %bb.3: # %func_4.exit.i
; CHECK-NEXT: xorl %ecx, %ecx
; CHECK-NEXT: .LBB3_4: # %func_4.exit.i
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: je .LBB3_7
; CHECK-NEXT: # %bb.5: # %func_4.exit.i
; CHECK-NEXT: testb %bl, %bl
; CHECK-NEXT: jne .LBB3_7
; CHECK-NEXT: # %bb.6: # %bb.i.i
; CHECK-NEXT: movb {{.*}}(%rip), %cl
; CHECK-NEXT: xorl %ebx, %ebx
; CHECK-NEXT: movl %eax, %ecx
; CHECK-NEXT: .LBB3_7: # %func_1.exit
; CHECK-NEXT: movb %cl, {{.*}}(%rip)
; CHECK-NEXT: movzbl %cl, %esi
; CHECK-NEXT: movl $_2E_str, %edi
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: callq printf
; CHECK-NEXT: movl %ebx, %eax
; CHECK-NEXT: popq %rbx
; CHECK-NEXT: retq
entry:
%0 = load i8, i8* @g_3, align 1
%1 = sext i8 %0 to i32
%.lobit.i = lshr i8 %0, 7
%tmp.i = zext i8 %.lobit.i to i32
%tmp.not.i = xor i32 %tmp.i, 1
%iftmp.17.0.i.i = ashr i32 %1, %tmp.not.i
%retval56.i.i = trunc i32 %iftmp.17.0.i.i to i8
%2 = icmp eq i8 %retval56.i.i, 0
%g_96.promoted.i = load i8, i8* @g_96
%3 = icmp eq i8 %g_96.promoted.i, 0
br i1 %3, label %func_4.exit.i, label %bb.i.i.i
bb.i.i.i:
%4 = load volatile i8, i8* @g_100, align 1
br label %func_4.exit.i
func_4.exit.i:
%.not.i = xor i1 %2, true
%brmerge.i = or i1 %3, %.not.i
%.mux.i = select i1 %2, i8 %g_96.promoted.i, i8 0
br i1 %brmerge.i, label %func_1.exit, label %bb.i.i
bb.i.i:
%5 = load volatile i8, i8* @g_100, align 1
br label %func_1.exit
func_1.exit:
%g_96.tmp.0.i = phi i8 [ %g_96.promoted.i, %bb.i.i ], [ %.mux.i, %func_4.exit.i ]
%ret = phi i1 [ 0, %bb.i.i ], [ %.not.i, %func_4.exit.i ]
store i8 %g_96.tmp.0.i, i8* @g_96
%6 = zext i8 %g_96.tmp.0.i to i32
%7 = tail call i32 (i8*, ...) @printf(i8* noalias getelementptr ([15 x i8], [15 x i8]* @_2E_str, i64 0, i64 0), i32 %6) nounwind
ret i1 %ret
}
declare i32 @printf(i8* nocapture, ...) nounwind
; Should compile to setcc | -2.
; rdar://6668608
define i32 @test5(i32* nocapture %P) nounwind readonly {
; CHECK-LABEL: test5:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: cmpl $41, (%rdi)
; CHECK-NEXT: setg %al
; CHECK-NEXT: orl $-2, %eax
; CHECK-NEXT: retq
entry:
%0 = load i32, i32* %P, align 4
%1 = icmp sgt i32 %0, 41
%iftmp.0.0 = select i1 %1, i32 -1, i32 -2
ret i32 %iftmp.0.0
}
define i32 @test6(i32* nocapture %P) nounwind readonly {
; CHECK-LABEL: test6:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: cmpl $42, (%rdi)
; CHECK-NEXT: setl %al
; CHECK-NEXT: leal 4(%rax,%rax,8), %eax
; CHECK-NEXT: retq
entry:
%0 = load i32, i32* %P, align 4
%1 = icmp sgt i32 %0, 41
%iftmp.0.0 = select i1 %1, i32 4, i32 13
ret i32 %iftmp.0.0
}
; Don't try to use a 16-bit conditional move to do an 8-bit select,
; because it isn't worth it. Just use a branch instead.
define i8 @test7(i1 inreg %c, i8 inreg %a, i8 inreg %b) nounwind {
; CHECK-LABEL: test7:
; CHECK: # %bb.0:
; CHECK-NEXT: testb $1, %dil
; CHECK-NEXT: jne .LBB6_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: movl %edx, %esi
; CHECK-NEXT: .LBB6_2:
; CHECK-NEXT: movl %esi, %eax
; CHECK-NEXT: retq
%d = select i1 %c, i8 %a, i8 %b
ret i8 %d
}
define i32 @smin(i32 %x) {
; CHECK-LABEL: smin:
; CHECK: # %bb.0:
; CHECK-NEXT: notl %edi
; CHECK-NEXT: testl %edi, %edi
; CHECK-NEXT: movl $-1, %eax
; CHECK-NEXT: cmovsl %edi, %eax
; CHECK-NEXT: retq
%not_x = xor i32 %x, -1
%1 = icmp slt i32 %not_x, -1
%sel = select i1 %1, i32 %not_x, i32 -1
ret i32 %sel
}