6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-09-25 17:20:48 +00:00
Code Issues Projects Releases Wiki Activity

implement enough of the memset inference algorithm to recognize and insert

Browse Source 
memsets.  This is still missing one important validity check, but this is enough
to compile stuff like this:

void test0(std::vector<char> &X) {
  for (std::vector<char>::iterator I = X.begin(), E = X.end(); I != E; ++I)
    *I = 0;
}

void test1(std::vector<int> &X) {
  for (long i = 0, e = X.size(); i != e; ++i)
    X[i] = 0x01010101;
}

With:
 $ clang t.cpp -S -o - -O2 -emit-llvm | opt -loop-idiom | opt -O3 | llc 

to:

__Z5test0RSt6vectorIcSaIcEE:            ## @_Z5test0RSt6vectorIcSaIcEE
## BB#0:                                ## %entry
	subq	$8, %rsp
	movq	(%rdi), %rax
	movq	8(%rdi), %rsi
	cmpq	%rsi, %rax
	je	LBB0_2
## BB#1:                                ## %bb.nph
	subq	%rax, %rsi
	movq	%rax, %rdi
	callq	___bzero
LBB0_2:                                 ## %for.end
	addq	$8, %rsp
	ret
...
__Z5test1RSt6vectorIiSaIiEE:            ## @_Z5test1RSt6vectorIiSaIiEE
## BB#0:                                ## %entry
	subq	$8, %rsp
	movq	(%rdi), %rax
	movq	8(%rdi), %rdx
	subq	%rax, %rdx
	cmpq	$4, %rdx
	jb	LBB1_2
## BB#1:                                ## %for.body.preheader
	andq	$-4, %rdx
	movl	$1, %esi
	movq	%rax, %rdi
	callq	_memset
LBB1_2:                                 ## %for.end
	addq	$8, %rsp
	ret



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122573 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Chris Lattner
2010-12-26 23:42:51 +00:00
parent 61db1f56d0
commit a92ff91a96
4 changed files with 126 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
test/Transforms/LoopIdiom/basic.ll Normal file
View File

@@ -0,0 +1,44 @@
; RUN: opt -loop-idiom < %s -S | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
target triple = "x86_64-apple-darwin10.0.0"
define void @test1(i8* %Base, i64 %Size) nounwind ssp {
bb.nph: ; preds = %entry
br label %for.body
for.body: ; preds = %bb.nph, %for.body
%indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
%I.0.014 = getelementptr i8* %Base, i64 %indvar
store i8 0, i8* %I.0.014, align 1
%indvar.next = add i64 %indvar, 1
%exitcond = icmp eq i64 %indvar.next, %Size
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
; CHECK: @test1
; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base, i8 0, i64 %Size, i32 1, i1 false)
; CHECK-NOT: store
}
define void @test2(i32* %Base, i64 %Size) nounwind ssp {
entry:
%cmp10 = icmp eq i64 %Size, 0
br i1 %cmp10, label %for.end, label %for.body
for.body: ; preds = %entry, %for.body
%i.011 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
%add.ptr.i = getelementptr i32* %Base, i64 %i.011
store i32 16843009, i32* %add.ptr.i, align 4
%inc = add nsw i64 %i.011, 1
%exitcond = icmp eq i64 %inc, %Size
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
; CHECK: @test2
; CHECK: br i1 %cmp10,
; CHECK: %tmp = mul i64 %Size, 4
; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base1, i8 1, i64 %tmp, i32 4, i1 false)
; CHECK-NOT: store
}