e3a3e3c9e9
This patch enables redundant sign- and zero-extension elimination in PowerPC MI Peephole pass.
If the input value of a sign- or zero-extension is known to be already sign- or zero-extended, the operation is redundant and can be eliminated.
One common case is sign-extensions for a method parameter or for a method return value; they must be sign- or zero-extended as defined in PPC ELF ABI.
For example of the following simple code, two extsw instructions are generated before the invocation of int_func and before the return. With this patch, both extsw are eliminated.
void int_func(int);
void ii_test(int a) {
if (a & 1) return int_func(a);
}
Such redundant sign- or zero-extensions are quite common in many programs; e.g. I observed about 60,000 occurrences of the elimination while compiling the LLVM+CLANG.
Differential Revision: https://reviews.llvm.org/D31319
llvm-svn: 315888
39 lines
1.6 KiB
LLVM
39 lines
1.6 KiB
LLVM
; RUN: llc < %s -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr9 -verify-machineinstrs | FileCheck %s
|
|
; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr9 -verify-machineinstrs | FileCheck %s
|
|
; RUN: llc < %s -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr8 -verify-machineinstrs | FileCheck %s
|
|
; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr8 -verify-machineinstrs | FileCheck %s
|
|
|
|
; Function Attrs: norecurse nounwind readonly
|
|
define signext i32 @limit_loop(i32 signext %iters, i32* nocapture readonly %vec, i32 signext %limit) local_unnamed_addr {
|
|
entry:
|
|
%cmp5 = icmp sgt i32 %iters, 0
|
|
br i1 %cmp5, label %for.body.preheader, label %cleanup
|
|
|
|
for.body.preheader: ; preds = %entry
|
|
%0 = sext i32 %iters to i64
|
|
br label %for.body
|
|
|
|
for.cond: ; preds = %for.body
|
|
%cmp = icmp slt i64 %indvars.iv.next, %0
|
|
br i1 %cmp, label %for.body, label %cleanup
|
|
|
|
for.body: ; preds = %for.body.preheader, %for.cond
|
|
%indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.cond ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %vec, i64 %indvars.iv
|
|
%1 = load i32, i32* %arrayidx, align 4
|
|
%cmp1 = icmp slt i32 %1, %limit
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
br i1 %cmp1, label %for.cond, label %cleanup
|
|
|
|
cleanup: ; preds = %for.body, %for.cond, %entry
|
|
%2 = phi i32 [ 0, %entry ], [ 0, %for.cond ], [ 1, %for.body ]
|
|
ret i32 %2
|
|
; CHECK-LABEL: limit_loop
|
|
; CHECK: mtctr
|
|
; CHECK-NOT: addi {{[0-9]+}}, {{[0-9]+}}, 1
|
|
; CHECK: bdzlr
|
|
; CHECK: blr
|
|
}
|
|
|
|
|