[PowerPC/BlockPlacement] Allow target to provide a per-loop alignment preference

The existing code provided for specifying a global loop alignment preference.
However, the preferred loop alignment might depend on the loop itself. For
recent POWER cores, loops between 5 and 8 instructions should have 32-byte
alignment (while the others are better with 16-byte alignment) so that the
entire loop will fit in one i-cache line.

To support this, getPrefLoopAlignment has been made virtual, and can be
provided with an optional MachineLoop* so the target can inspect the loop
before answering the query. The default behavior, as before, is to return the
value set with setPrefLoopAlignment. MachineBlockPlacement now queries the
target for each loop instead of only once per function. There should be no
functional change for other targets.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225117 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Hal Finkel
2015-01-03 17:58:24 +00:00
parent a1d22cc789
commit e05b232c20
5 changed files with 92 additions and 13 deletions

View File

@ -1,15 +1,15 @@
; RUN: llc -mcpu=ppc64 < %s | FileCheck %s -check-prefix=GENERIC
; RUN: llc -mcpu=970 < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -mcpu=970 < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -mcpu=a2 < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -mcpu=e500mc < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -mcpu=e5500 < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -mcpu=pwr4 < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -mcpu=pwr5 < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -mcpu=pwr5x < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -mcpu=pwr6 < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -mcpu=pwr6x < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -mcpu=pwr7 < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -mcpu=pwr8 < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -mcpu=pwr4 < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -mcpu=pwr5 < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -mcpu=pwr5x < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -mcpu=pwr6 < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -mcpu=pwr6x < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -mcpu=pwr7 < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -mcpu=pwr8 < %s | FileCheck %s -check-prefix=PWR
target datalayout = "E-m:e-i64:64-n32:64"
target triple = "powerpc64-unknown-linux-gnu"
@ -21,10 +21,13 @@ entry:
; GENERIC-LABEL: .globl foo
; BASIC-LABEL: .globl foo
; PWR-LABEL: .globl foo
; GENERIC: .align 2
; BASIC: .align 4
; PWR: .align 4
; GENERIC: @foo
; BASIC: @foo
; PWR: @foo
}
; Function Attrs: nounwind
@ -34,12 +37,16 @@ entry:
; GENERIC-LABEL: @loop
; BASIC-LABEL: @loop
; PWR-LABEL: @loop
; GENERIC: mtctr
; BASIC: mtctr
; PWR: mtctr
; GENERIC-NOT: .align
; BASIC: .align 4
; PWR: .align 4
; GENERIC: bdnz
; BASIC: bdnz
; PWR: bdnz
vector.body: ; preds = %vector.body, %entry
%index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
@ -60,6 +67,38 @@ for.end: ; preds = %vector.body
ret void
}
; Function Attrs: nounwind
define void @sloop(i32 signext %x, i32* nocapture %a) #1 {
entry:
br label %for.body
; GENERIC-LABEL: @sloop
; BASIC-LABEL: @sloop
; PWR-LABEL: @sloop
; GENERIC: mtctr
; BASIC: mtctr
; PWR: mtctr
; GENERIC-NOT: .align
; BASIC: .align 4
; PWR: .align 5
; GENERIC: bdnz
; BASIC: bdnz
; PWR: bdnz
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4
%add = add nsw i32 %0, 4
store i32 %add, i32* %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 2048
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
attributes #0 = { nounwind readnone }
attributes #1 = { nounwind }