maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[PowerPC]add testcase for ppcctrloops pass shortloop check 

llvm-svn: 357560
This commit is contained in:
Chen Zheng 2019-04-03 03:11:34 +00:00
parent 5e349afccb
commit 4178c15330
1 changed files with 51 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
llvm/test/CodeGen/PowerPC/ctrloop-shortLoops.ll
View File

@ -1,10 +1,15 @@
; RUN: llc < %s -mtriple=powerpc64le-unknown-linux-gnu -verify-machineinstrs -mcpu=pwr8 | FileCheck %s
; RUN: llc < %s -mtriple=powerpc64le-unknown-linux-gnu -verify-machineinstrs -mcpu=a2q | FileCheck %s
; RUN: llc < %s -mtriple=powerpc64le-unknown-linux-gnu -verify-machineinstrs -mcpu=pwr8 | FileCheck %s --check-prefixes=CHECK,CHECK-PWR8
; RUN: llc < %s -mtriple=powerpc64le-unknown-linux-gnu -verify-machineinstrs -mcpu=a2q | FileCheck %s --check-prefixes=CHECK,CHECK-A2Q
; Verify that we do NOT generate the mtctr instruction for loop trip counts < 4
; The latency of the mtctr is only justified if there are more than 4 comparisons that are removed as a result.
@a = common local_unnamed_addr global i32 0, align 4
@b = common local_unnamed_addr global i32 0, align 4
@c = common local_unnamed_addr global i32 0, align 4
@d = common local_unnamed_addr global i32 0, align 4
@e = common local_unnamed_addr global i32 0, align 4
@f = common local_unnamed_addr global i32 0, align 4
@arr = common local_unnamed_addr global [5 x i32] zeroinitializer, align 4
; Function Attrs: norecurse nounwind readonly
@ -113,3 +118,47 @@ for.end: ; preds = %if.end
ret i32 %conv
}
; On core a2q, IssueWidth is 1. On core pwr8, IssueWidth is 8.
; a2q should use mtctr, but pwr8 should not use mtctr.
define signext i32 @testTripCount5() {
; CHECK-LABEL: testTripCount5:
; CHECK-PWR8: mtctr
; CHECK-A2Q: mtctr
entry:
%.prea = load i32, i32* @a, align 4
%.preb = load i32, i32* @b, align 4
%.prec = load i32, i32* @c, align 4
%.pred = load i32, i32* @d, align 4
%.pree = load i32, i32* @e, align 4
%.pref = load i32, i32* @f, align 4
br label %for.body
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ 2, %entry ], [ %indvars.iv.next, %for.body ]
%0 = phi i32 [ %.prea, %entry ], [ %6, %for.body ]
%1 = phi i32 [ %.preb, %entry ], [ %7, %for.body ]
%2 = phi i32 [ %.prec, %entry ], [ %8, %for.body ]
%3 = phi i32 [ %.pred, %entry ], [ %9, %for.body ]
%4 = phi i32 [ %.pree, %entry ], [ %10, %for.body ]
%5 = phi i32 [ %.pref, %entry ], [ %11, %for.body ]
%6 = add i32 %0, 1
%7 = add i32 %1, 1
%8 = add i32 %2, 1
%9 = add i32 %3, 1
%10 = add i32 %4, 1
%11 = add i32 %5, 1
%indvars.iv.next = add nsw i64 %indvars.iv, -1
%tobool = icmp eq i64 %indvars.iv, 0
br i1 %tobool, label %for.end, label %for.body
for.end: ; preds = %for.body
store i32 %6, i32* @a, align 4
store i32 %7, i32* @b, align 4
store i32 %8, i32* @c, align 4
store i32 %9, i32* @d, align 4
store i32 %10, i32* @e, align 4
store i32 %11, i32* @f, align 4
ret i32 0
}