llvm/test/CodeGen/X86/sink-blockfreq.ll

46 lines
1.5 KiB
LLVM
Raw Normal View History

Don't delete empty preheaders in CodeGenPrepare if it would create a critical edge Presently, CodeGenPrepare deletes all nearly empty (only phi and branch) basic blocks. This pass can delete loop preheaders which frequently creates critical edges. A preheader can be a convenient place to spill registers to the stack. If the entrance to a loop body is a critical edge, then spills may occur in the loop body rather than immediately before it. This patch protects loop preheaders from deletion in CodeGenPrepare even if they are nearly empty. Since the patch alters the CFG, it affects a large number of test cases. In most cases, the changes are merely cosmetic (basic blocks have different names or instruction orders change slightly). I am somewhat concerned about the test/CodeGen/Mips/brdelayslot.ll test case. If the loop preheader is not deleted, then the MIPS backend does not take advantage of a branch delay slot. Consequently, I would like some close review by a MIPS expert. The patch also partially subsumes D16893 from George Burgess IV. George correctly notes that CodeGenPrepare does not actually preserve the dominator tree. I think the dominator tree was usually not valid when CodeGenPrepare ran, but I am using LoopInfo to mark preheaders, so the dominator tree is now always valid before CodeGenPrepare. Author: Tom Jablin (tjablin) Reviewers: hfinkel george.burgess.iv vkalintiris dsanders kbarton cycheng http://reviews.llvm.org/D16984 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@265397 91177308-0d34-0410-b5e6-96231b3b80d8
2016-04-05 14:06:20 +00:00
; RUN: llc -disable-preheader-prot=true -disable-machine-licm -machine-sink-bfi=true -mtriple=x86_64-apple-darwin < %s | FileCheck %s -check-prefix=MSINK_BFI
; RUN: llc -disable-preheader-prot=true -disable-machine-licm -machine-sink-bfi=false -mtriple=x86_64-apple-darwin < %s | FileCheck %s -check-prefix=MSINK_NOBFI
; Test that by changing BlockFrequencyInfo we change the order in which
; machine-sink looks for sucessor blocks. By not using BFI, both G and B
; have the same loop depth and no instructions is sinked - B is selected but
; can't be used as to avoid breaking a non profitable critical edge. By using
; BFI, "mul" is sinked into the less frequent block G.
define i32 @sink_freqinfo(i32 %a, i32 %b) nounwind uwtable ssp {
; MSINK_BFI-LABEL: sink_freqinfo
; MSINK_BFI: jl
; MSINK_BFI-NEXT: ## BB#
; MSINK_BFI-NEXT: imull
; MSINK_NOBFI-LABEL: sink_freqinfo
; MSINK_NOBFI: imull
; MSINK_NOBFI: jl
entry:
br label %B
B:
%ee = phi i32 [ 0, %entry ], [ %inc, %F ]
%xx = sub i32 %a, %ee
%cond0 = icmp slt i32 %xx, 0
br i1 %cond0, label %F, label %exit, !prof !0
F:
%inc = add nsw i32 %xx, 2
%aa = mul nsw i32 %b, %inc
%exitcond = icmp slt i32 %inc, %a
br i1 %exitcond, label %B, label %G, !prof !1
G:
%ii = add nsw i32 %aa, %a
%ll = add i32 %b, 45
%exitcond2 = icmp sge i32 %ii, %b
br i1 %exitcond2, label %G, label %exit, !prof !2
exit:
ret i32 0
}
IR: Make metadata typeless in assembly Now that `Metadata` is typeless, reflect that in the assembly. These are the matching assembly changes for the metadata/value split in r223802. - Only use the `metadata` type when referencing metadata from a call intrinsic -- i.e., only when it's used as a `Value`. - Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode` when referencing it from call intrinsics. So, assembly like this: define @foo(i32 %v) { call void @llvm.foo(metadata !{i32 %v}, metadata !0) call void @llvm.foo(metadata !{i32 7}, metadata !0) call void @llvm.foo(metadata !1, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{metadata !3}, metadata !0) ret void, !bar !2 } !0 = metadata !{metadata !2} !1 = metadata !{i32* @global} !2 = metadata !{metadata !3} !3 = metadata !{} turns into this: define @foo(i32 %v) { call void @llvm.foo(metadata i32 %v, metadata !0) call void @llvm.foo(metadata i32 7, metadata !0) call void @llvm.foo(metadata i32* @global, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{!3}, metadata !0) ret void, !bar !2 } !0 = !{!2} !1 = !{i32* @global} !2 = !{!3} !3 = !{} I wrote an upgrade script that handled almost all of the tests in llvm and many of the tests in cfe (even handling many `CHECK` lines). I've attached it (or will attach it in a moment if you're speedy) to PR21532 to help everyone update their out-of-tree testcases. This is part of PR21532. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@224257 91177308-0d34-0410-b5e6-96231b3b80d8
2014-12-15 19:07:53 +00:00
!0 = !{!"branch_weights", i32 4, i32 1}
!1 = !{!"branch_weights", i32 128, i32 1}
!2 = !{!"branch_weights", i32 1, i32 1}