mirror of
https://github.com/RPCSX/llvm.git
synced 2024-11-27 05:30:49 +00:00
9d0b704e3e
Here is the original commit message: This commit updates malloc optimizations to operate on malloc calls that have constant int size arguments. Update CreateMalloc so that its callers specify the size to allocate: MallocInst-autoupgrade users use non-TargetData-computed allocation sizes. Optimization uses use TargetData to compute the allocation size. Now that malloc calls can have constant sizes, update isArrayMallocHelper() to use TargetData to determine the size of the malloced type and the size of malloced arrays. Extend getMallocType() to support malloc calls that have non-bitcast uses. Update OptimizeGlobalAddressOfMalloc() to optimize malloc calls that have non-bitcast uses. The bitcast use of a malloc call has to be treated specially here because the uses of the bitcast need to be replaced and the bitcast needs to be erased (just like the malloc call) for OptimizeGlobalAddressOfMalloc() to work correctly. Update PerformHeapAllocSRoA() to optimize malloc calls that have non-bitcast uses. The bitcast use of the malloc is not handled specially here because ReplaceUsesOfMallocWithGlobal replaces through the bitcast use. Update OptimizeOnceStoredGlobal() to not care about the malloc calls' bitcast use. Update all globalopt malloc tests to not rely on autoupgraded-MallocInsts, but instead use explicit malloc calls with correct allocation sizes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@86311 91177308-0d34-0410-b5e6-96231b3b80d8
44 lines
1.8 KiB
LLVM
44 lines
1.8 KiB
LLVM
; RUN: opt < %s -globalopt -S | grep {tmp.f1 = phi i32. }
|
|
; RUN: opt < %s -globalopt -S | grep {tmp.f0 = phi i32. }
|
|
target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
|
|
|
|
%struct.foo = type { i32, i32 }
|
|
@X = internal global %struct.foo* null ; <%struct.foo**> [#uses=2]
|
|
|
|
define void @bar(i32 %Size) nounwind noinline {
|
|
entry:
|
|
%malloccall = tail call i8* @malloc(i64 8000000) ; <i8*> [#uses=1]
|
|
%tmp = bitcast i8* %malloccall to [1000000 x %struct.foo]* ; <[1000000 x %struct.foo]*> [#uses=1]
|
|
%.sub = getelementptr [1000000 x %struct.foo]* %tmp, i32 0, i32 0 ; <%struct.foo*> [#uses=1]
|
|
store %struct.foo* %.sub, %struct.foo** @X, align 4
|
|
ret void
|
|
}
|
|
|
|
declare noalias i8* @malloc(i64)
|
|
|
|
define i32 @baz() nounwind readonly noinline {
|
|
bb1.thread:
|
|
%tmpLD1 = load %struct.foo** @X, align 4 ; <%struct.foo*> [#uses=1]
|
|
br label %bb1
|
|
|
|
bb1: ; preds = %bb1, %bb1.thread
|
|
%tmp = phi %struct.foo* [%tmpLD1, %bb1.thread ], [ %tmpLD2, %bb1 ] ; <i32> [#uses=2]
|
|
%i.0.reg2mem.0 = phi i32 [ 0, %bb1.thread ], [ %indvar.next, %bb1 ] ; <i32> [#uses=2]
|
|
%sum.0.reg2mem.0 = phi i32 [ 0, %bb1.thread ], [ %tmp3, %bb1 ] ; <i32> [#uses=1]
|
|
%tmp1 = getelementptr %struct.foo* %tmp, i32 %i.0.reg2mem.0, i32 0 ; <i32*> [#uses=1]
|
|
%tmp2 = load i32* %tmp1, align 4 ; <i32> [#uses=1]
|
|
%tmp6 = add i32 %tmp2, %sum.0.reg2mem.0 ; <i32> [#uses=2]
|
|
%tmp4 = getelementptr %struct.foo* %tmp, i32 %i.0.reg2mem.0, i32 1 ; <i32*> [#uses=1]
|
|
%tmp5 = load i32 * %tmp4
|
|
%tmp3 = add i32 %tmp5, %tmp6
|
|
%indvar.next = add i32 %i.0.reg2mem.0, 1 ; <i32> [#uses=2]
|
|
|
|
%tmpLD2 = load %struct.foo** @X, align 4 ; <%struct.foo*> [#uses=1]
|
|
|
|
%exitcond = icmp eq i32 %indvar.next, 1200 ; <i1> [#uses=1]
|
|
br i1 %exitcond, label %bb2, label %bb1
|
|
|
|
bb2: ; preds = %bb1
|
|
ret i32 %tmp3
|
|
}
|