e6bf48d110
As of revea222be0d, LLVMs assembler will actually try to honour the "fill value" part of p2align directives. X86 printed these as 0x90, which isn't actually what it wanted: we want multi-byte nops for .text padding. Compiling via a textual assembly file produces single-byte nop padding sinceea222be0dbut the built-in assembler will produce multi-byte nops. This divergent behaviour is undesirable. To fix: don't set the byte padding field for x86, which allows the assembler to pick multi-byte nops. Test that we get the same multi-byte padding when compiled via textual assembly or directly to object file. Added same-align-bytes-with-llasm-llobj.ll to that effect, updated numerous other tests to not contain check-lines for the explicit padding.
259 lines
6.9 KiB
LLVM
259 lines
6.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
;RUN: llc < %s -mtriple=i686-- -mattr=-slow-incdec | FileCheck %s -check-prefixes=CHECK,SLOW
|
|
;RUN: llc < %s -mtriple=i686-- -mattr=+slow-incdec | FileCheck %s -check-prefixes=CHECK,FAST
|
|
|
|
define void @foo(i32 inreg %dns) minsize {
|
|
; CHECK-LABEL: foo:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xorl %ecx, %ecx
|
|
; CHECK-NEXT: decl %ecx
|
|
; CHECK-NEXT: .LBB0_1: # %for.body
|
|
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: movzwl %cx, %edx
|
|
; CHECK-NEXT: decl %ecx
|
|
; CHECK-NEXT: cmpl %eax, %edx
|
|
; CHECK-NEXT: jl .LBB0_1
|
|
; CHECK-NEXT: # %bb.2: # %for.end
|
|
; CHECK-NEXT: retl
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%i.05 = phi i16 [ %dec, %for.body ], [ 0, %entry ]
|
|
%dec = add i16 %i.05, -1
|
|
%conv = zext i16 %dec to i32
|
|
%cmp = icmp slt i32 %conv, %dns
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
define void @bar(i32 inreg %dns) minsize {
|
|
; CHECK-LABEL: bar:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xorl %ecx, %ecx
|
|
; CHECK-NEXT: incl %ecx
|
|
; CHECK-NEXT: .LBB1_1: # %for.body
|
|
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: movzwl %cx, %edx
|
|
; CHECK-NEXT: incl %ecx
|
|
; CHECK-NEXT: cmpl %eax, %edx
|
|
; CHECK-NEXT: jl .LBB1_1
|
|
; CHECK-NEXT: # %bb.2: # %for.end
|
|
; CHECK-NEXT: retl
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%i.05 = phi i16 [ %inc, %for.body ], [ 0, %entry ]
|
|
%inc = add i16 %i.05, 1
|
|
%conv = zext i16 %inc to i32
|
|
%cmp = icmp slt i32 %conv, %dns
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
define void @foo_optsize(i32 inreg %dns) optsize {
|
|
; CHECK-LABEL: foo_optsize:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xorl %ecx, %ecx
|
|
; CHECK-NEXT: decl %ecx
|
|
; CHECK-NEXT: .LBB2_1: # %for.body
|
|
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: movzwl %cx, %edx
|
|
; CHECK-NEXT: decl %ecx
|
|
; CHECK-NEXT: cmpl %eax, %edx
|
|
; CHECK-NEXT: jl .LBB2_1
|
|
; CHECK-NEXT: # %bb.2: # %for.end
|
|
; CHECK-NEXT: retl
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%i.05 = phi i16 [ %dec, %for.body ], [ 0, %entry ]
|
|
%dec = add i16 %i.05, -1
|
|
%conv = zext i16 %dec to i32
|
|
%cmp = icmp slt i32 %conv, %dns
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
define void @bar_optsize(i32 inreg %dns) optsize {
|
|
; CHECK-LABEL: bar_optsize:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xorl %ecx, %ecx
|
|
; CHECK-NEXT: incl %ecx
|
|
; CHECK-NEXT: .LBB3_1: # %for.body
|
|
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: movzwl %cx, %edx
|
|
; CHECK-NEXT: incl %ecx
|
|
; CHECK-NEXT: cmpl %eax, %edx
|
|
; CHECK-NEXT: jl .LBB3_1
|
|
; CHECK-NEXT: # %bb.2: # %for.end
|
|
; CHECK-NEXT: retl
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%i.05 = phi i16 [ %inc, %for.body ], [ 0, %entry ]
|
|
%inc = add i16 %i.05, 1
|
|
%conv = zext i16 %inc to i32
|
|
%cmp = icmp slt i32 %conv, %dns
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
define void @foo_pgso(i32 inreg %dns) !prof !14 {
|
|
; CHECK-LABEL: foo_pgso:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xorl %ecx, %ecx
|
|
; CHECK-NEXT: decl %ecx
|
|
; CHECK-NEXT: .LBB4_1: # %for.body
|
|
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: movzwl %cx, %edx
|
|
; CHECK-NEXT: decl %ecx
|
|
; CHECK-NEXT: cmpl %eax, %edx
|
|
; CHECK-NEXT: jl .LBB4_1
|
|
; CHECK-NEXT: # %bb.2: # %for.end
|
|
; CHECK-NEXT: retl
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%i.05 = phi i16 [ %dec, %for.body ], [ 0, %entry ]
|
|
%dec = add i16 %i.05, -1
|
|
%conv = zext i16 %dec to i32
|
|
%cmp = icmp slt i32 %conv, %dns
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
define void @bar_pgso(i32 inreg %dns) !prof !14 {
|
|
; CHECK-LABEL: bar_pgso:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xorl %ecx, %ecx
|
|
; CHECK-NEXT: incl %ecx
|
|
; CHECK-NEXT: .LBB5_1: # %for.body
|
|
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: movzwl %cx, %edx
|
|
; CHECK-NEXT: incl %ecx
|
|
; CHECK-NEXT: cmpl %eax, %edx
|
|
; CHECK-NEXT: jl .LBB5_1
|
|
; CHECK-NEXT: # %bb.2: # %for.end
|
|
; CHECK-NEXT: retl
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%i.05 = phi i16 [ %inc, %for.body ], [ 0, %entry ]
|
|
%inc = add i16 %i.05, 1
|
|
%conv = zext i16 %inc to i32
|
|
%cmp = icmp slt i32 %conv, %dns
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
define void @foo_nosize(i32 inreg %dns) {
|
|
; SLOW-LABEL: foo_nosize:
|
|
; SLOW: # %bb.0: # %entry
|
|
; SLOW-NEXT: movw $-1, %cx
|
|
; SLOW-NEXT: .p2align 4
|
|
; SLOW-NEXT: .LBB6_1: # %for.body
|
|
; SLOW-NEXT: # =>This Inner Loop Header: Depth=1
|
|
; SLOW-NEXT: movzwl %cx, %edx
|
|
; SLOW-NEXT: decl %ecx
|
|
; SLOW-NEXT: cmpl %eax, %edx
|
|
; SLOW-NEXT: jl .LBB6_1
|
|
; SLOW-NEXT: # %bb.2: # %for.end
|
|
; SLOW-NEXT: retl
|
|
;
|
|
; FAST-LABEL: foo_nosize:
|
|
; FAST: # %bb.0: # %entry
|
|
; FAST-NEXT: movw $-1, %cx
|
|
; FAST-NEXT: .p2align 4
|
|
; FAST-NEXT: .LBB6_1: # %for.body
|
|
; FAST-NEXT: # =>This Inner Loop Header: Depth=1
|
|
; FAST-NEXT: movzwl %cx, %edx
|
|
; FAST-NEXT: addl $-1, %ecx
|
|
; FAST-NEXT: cmpl %eax, %edx
|
|
; FAST-NEXT: jl .LBB6_1
|
|
; FAST-NEXT: # %bb.2: # %for.end
|
|
; FAST-NEXT: retl
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%i.05 = phi i16 [ %dec, %for.body ], [ 0, %entry ]
|
|
%dec = add i16 %i.05, -1
|
|
%conv = zext i16 %dec to i32
|
|
%cmp = icmp slt i32 %conv, %dns
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
define void @bar_nosize(i32 inreg %dns) {
|
|
; SLOW-LABEL: bar_nosize:
|
|
; SLOW: # %bb.0: # %entry
|
|
; SLOW-NEXT: movw $1, %cx
|
|
; SLOW-NEXT: .p2align 4
|
|
; SLOW-NEXT: .LBB7_1: # %for.body
|
|
; SLOW-NEXT: # =>This Inner Loop Header: Depth=1
|
|
; SLOW-NEXT: movzwl %cx, %edx
|
|
; SLOW-NEXT: incl %ecx
|
|
; SLOW-NEXT: cmpl %eax, %edx
|
|
; SLOW-NEXT: jl .LBB7_1
|
|
; SLOW-NEXT: # %bb.2: # %for.end
|
|
; SLOW-NEXT: retl
|
|
;
|
|
; FAST-LABEL: bar_nosize:
|
|
; FAST: # %bb.0: # %entry
|
|
; FAST-NEXT: movw $1, %cx
|
|
; FAST-NEXT: .p2align 4
|
|
; FAST-NEXT: .LBB7_1: # %for.body
|
|
; FAST-NEXT: # =>This Inner Loop Header: Depth=1
|
|
; FAST-NEXT: movzwl %cx, %edx
|
|
; FAST-NEXT: addl $1, %ecx
|
|
; FAST-NEXT: cmpl %eax, %edx
|
|
; FAST-NEXT: jl .LBB7_1
|
|
; FAST-NEXT: # %bb.2: # %for.end
|
|
; FAST-NEXT: retl
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%i.05 = phi i16 [ %inc, %for.body ], [ 0, %entry ]
|
|
%inc = add i16 %i.05, 1
|
|
%conv = zext i16 %inc to i32
|
|
%cmp = icmp slt i32 %conv, %dns
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
!llvm.module.flags = !{!0}
|
|
!0 = !{i32 1, !"ProfileSummary", !1}
|
|
!1 = !{!2, !3, !4, !5, !6, !7, !8, !9}
|
|
!2 = !{!"ProfileFormat", !"InstrProf"}
|
|
!3 = !{!"TotalCount", i64 10000}
|
|
!4 = !{!"MaxCount", i64 10}
|
|
!5 = !{!"MaxInternalCount", i64 1}
|
|
!6 = !{!"MaxFunctionCount", i64 1000}
|
|
!7 = !{!"NumCounts", i64 3}
|
|
!8 = !{!"NumFunctions", i64 3}
|
|
!9 = !{!"DetailedSummary", !10}
|
|
!10 = !{!11, !12, !13}
|
|
!11 = !{i32 10000, i64 100, i32 1}
|
|
!12 = !{i32 999000, i64 100, i32 1}
|
|
!13 = !{i32 999999, i64 1, i32 2}
|
|
!14 = !{!"function_entry_count", i64 0}
|