maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/code_placement_loop_rotatio...

123 lines
2.2 KiB
LLVM
Raw Normal View History

Enhance loop rotation with existence of profile data in MachineBlockPlacement pass. Currently, in MachineBlockPlacement pass the loop is rotated to let the best exit to be the last BB in the loop chain, to maximize the fall-through from the loop to outside. With profile data, we can determine the cost in terms of missed fall through opportunities when rotating a loop chain and select the best rotation. Basically, there are three kinds of cost to consider for each rotation: 1. The possibly missed fall through edge (if it exists) from BB out of the loop to the loop header. 2. The possibly missed fall through edges (if they exist) from the loop exits to BB out of the loop. 3. The missed fall through edge (if it exists) from the last BB to the first BB in the loop chain. Therefore, the cost for a given rotation is the sum of costs listed above. We select the best rotation with the smallest cost. This is only for PGO mode when we have more precise edge frequencies. Differential revision: http://reviews.llvm.org/D10717 llvm-svn: 250754
2015-10-20 07:16:40 +08:00
; RUN: llc -mcpu=corei7 -mtriple=x86_64-linux < %s | FileCheck %s -check-prefix=CHECK
; RUN: llc -mcpu=corei7 -mtriple=x86_64-linux -precise-rotation-cost < %s | FileCheck %s -check-prefix=CHECK-PROFILE
define void @foo() {
; Test a nested loop case when profile data is not available.
;
; CHECK-LABEL: foo:
; CHECK: callq b
; CHECK: callq c
; CHECK: callq d
; CHECK: callq e
; CHECK: callq f
; CHECK: callq g
; CHECK: callq h
entry:
br label %header
header:
call void @b()
%call = call zeroext i1 @a()
br i1 %call, label %if.then, label %if.else, !prof !2
if.then:
br label %header2
header2:
call void @c()
%call1 = call zeroext i1 @a()
br i1 %call1, label %if.then2, label %if.else2, !prof !2
if.then2:
call void @d()
br label %if.end2
if.else2:
call void @e()
br label %if.end2
if.end2:
call void @f()
%call2 = call zeroext i1 @a()
br i1 %call2, label %header2, label %if.end
if.else:
call void @g()
br label %if.end
if.end:
call void @h()
%call3 = call zeroext i1 @a()
br i1 %call3, label %header, label %end
end:
ret void
}
define void @bar() !prof !1 {
; Test a nested loop case when profile data is available.
;
; CHECK-PROFILE-LABEL: bar:
; CHECK-PROFILE: callq e
; CHECK-PROFILE: callq f
; CHECK-PROFILE: callq c
; CHECK-PROFILE: callq d
; CHECK-PROFILE: callq h
; CHECK-PROFILE: callq b
; CHECK-PROFILE: callq g
entry:
br label %header
header:
call void @b()
%call = call zeroext i1 @a()
br i1 %call, label %if.then, label %if.else, !prof !2
if.then:
br label %header2
header2:
call void @c()
%call1 = call zeroext i1 @a()
br i1 %call1, label %if.then2, label %if.else2, !prof !2
if.then2:
call void @d()
br label %if.end2
if.else2:
call void @e()
br label %if.end2
if.end2:
call void @f()
%call2 = call zeroext i1 @a()
br i1 %call2, label %header2, label %if.end
if.else:
call void @g()
br label %if.end
if.end:
call void @h()
%call3 = call zeroext i1 @a()
br i1 %call3, label %header, label %end
end:
ret void
}
declare zeroext i1 @a()
declare void @b()
declare void @c()
declare void @d()
declare void @e()
declare void @f()
declare void @g()
declare void @h()
!1 = !{!"function_entry_count", i64 1}
!2 = !{!"branch_weights", i32 16, i32 16}