forked from OSchip/llvm-project
[MemCpyOpt] Add additional call slot capture tests (NFC)
This commit is contained in:
Nikita Popov
parent
787f86e68c
commit
c2e77c9122
|
|
@ -1,5 +1,5 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
||||
; RUN: opt < %s -basic-aa -memcpyopt -S -verify-memoryssa | FileCheck %s
|
||||
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature
|
||||
; RUN: opt < %s -basic-aa -globals-aa -memcpyopt -S -verify-memoryssa | FileCheck %s
|
||||
|
||||
target datalayout = "e"
|
||||
|
||||
|
|
@ -11,7 +11,7 @@ declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture)
|
|||
; Check that the transformation isn't applied if the called function can
|
||||
; capture the pointer argument (i.e. the nocapture attribute isn't present)
|
||||
define void @test() {
|
||||
; CHECK-LABEL: @test(
|
||||
; CHECK-LABEL: define {{[^@]+}}@test() {
|
||||
; CHECK-NEXT: [[PTR1:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: [[PTR2:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: call void @foo(i8* [[PTR2]])
|
||||
|
|
@ -30,7 +30,7 @@ define void @test() {
|
|||
; Same as previous test, but with a bitcasted argument.
|
||||
; TODO: Call slot optimization should not be applied here.
|
||||
define void @test_bitcast() {
|
||||
; CHECK-LABEL: @test_bitcast(
|
||||
; CHECK-LABEL: define {{[^@]+}}@test_bitcast() {
|
||||
; CHECK-NEXT: [[PTR1:%.*]] = alloca [2 x i8], align 1
|
||||
; CHECK-NEXT: [[PTR2:%.*]] = alloca [2 x i8], align 1
|
||||
; CHECK-NEXT: [[PTR1_CAST:%.*]] = bitcast [2 x i8]* [[PTR1]] to i8*
|
||||
|
|
@ -53,7 +53,7 @@ define void @test_bitcast() {
|
|||
; Lifetime of %ptr2 ends before the potential use of the capture in the second
|
||||
; call.
|
||||
define void @test_lifetime_end() {
|
||||
; CHECK-LABEL: @test_lifetime_end(
|
||||
; CHECK-LABEL: define {{[^@]+}}@test_lifetime_end() {
|
||||
; CHECK-NEXT: [[PTR1:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: [[PTR2:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 1, i8* [[PTR2]])
|
||||
|
|
@ -73,10 +73,32 @@ define void @test_lifetime_end() {
|
|||
ret void
|
||||
}
|
||||
|
||||
; Lifetime of %ptr2 does not end, because of size mismatch.
|
||||
define void @test_lifetime_not_end() {
|
||||
; CHECK-LABEL: define {{[^@]+}}@test_lifetime_not_end() {
|
||||
; CHECK-NEXT: [[PTR1:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: [[PTR2:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 1, i8* [[PTR2]])
|
||||
; CHECK-NEXT: call void @foo(i8* [[PTR2]])
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[PTR1]], i8* [[PTR2]], i32 1, i1 false)
|
||||
; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 0, i8* [[PTR2]])
|
||||
; CHECK-NEXT: call void @foo(i8* [[PTR1]])
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
%ptr1 = alloca i8
|
||||
%ptr2 = alloca i8
|
||||
call void @llvm.lifetime.start.p0i8(i64 1, i8* %ptr2)
|
||||
call void @foo(i8* %ptr2)
|
||||
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr1, i8* %ptr2, i32 1, i1 false)
|
||||
call void @llvm.lifetime.end.p0i8(i64 0, i8* %ptr2)
|
||||
call void @foo(i8* %ptr1)
|
||||
ret void
|
||||
}
|
||||
|
||||
; Lifetime of %ptr2 ends before any potential use of the capture because we
|
||||
; return from the function.
|
||||
define void @test_function_end() {
|
||||
; CHECK-LABEL: @test_function_end(
|
||||
; CHECK-LABEL: define {{[^@]+}}@test_function_end() {
|
||||
; CHECK-NEXT: [[PTR1:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: [[PTR2:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: call void @foo(i8* [[PTR2]])
|
||||
|
|
@ -89,3 +111,110 @@ define void @test_function_end() {
|
|||
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr1, i8* %ptr2, i32 1, i1 false)
|
||||
ret void
|
||||
}
|
||||
|
||||
; A potential use of the capture occurs in a later block, can't be optimized.
|
||||
define void @test_terminator() {
|
||||
; CHECK-LABEL: define {{[^@]+}}@test_terminator() {
|
||||
; CHECK-NEXT: [[PTR1:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: [[PTR2:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: call void @foo(i8* [[PTR2]])
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[PTR1]], i8* [[PTR2]], i32 1, i1 false)
|
||||
; CHECK-NEXT: br label [[NEXT:%.*]]
|
||||
; CHECK: next:
|
||||
; CHECK-NEXT: call void @foo(i8* [[PTR1]])
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
%ptr1 = alloca i8
|
||||
%ptr2 = alloca i8
|
||||
call void @foo(i8* %ptr2)
|
||||
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr1, i8* %ptr2, i32 1, i1 false)
|
||||
br label %next
|
||||
|
||||
next:
|
||||
call void @foo(i8* %ptr1)
|
||||
ret void
|
||||
}
|
||||
|
||||
; This case can be optimized, but would require a scan across multiple blocks
|
||||
; and is currently not performed.
|
||||
define void @test_terminator2() {
|
||||
; CHECK-LABEL: define {{[^@]+}}@test_terminator2() {
|
||||
; CHECK-NEXT: [[PTR1:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: [[PTR2:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: call void @foo(i8* [[PTR2]])
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[PTR1]], i8* [[PTR2]], i32 1, i1 false)
|
||||
; CHECK-NEXT: br label [[NEXT:%.*]]
|
||||
; CHECK: next:
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
%ptr1 = alloca i8
|
||||
%ptr2 = alloca i8
|
||||
call void @foo(i8* %ptr2)
|
||||
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr1, i8* %ptr2, i32 1, i1 false)
|
||||
br label %next
|
||||
|
||||
next:
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @capture(i8*)
|
||||
|
||||
; This case should not be optimized, because dest is captured before the call.
|
||||
define void @test_dest_captured_before_alloca() {
|
||||
; CHECK-LABEL: define {{[^@]+}}@test_dest_captured_before_alloca() {
|
||||
; CHECK-NEXT: [[PTR1:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: [[PTR2:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: call void @capture(i8* [[PTR1]])
|
||||
; CHECK-NEXT: call void @foo(i8* [[PTR2]]) #[[ATTR2:[0-9]+]]
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[PTR1]], i8* [[PTR2]], i32 1, i1 false)
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
%ptr1 = alloca i8
|
||||
%ptr2 = alloca i8
|
||||
call void @capture(i8* %ptr1)
|
||||
call void @foo(i8* %ptr2) argmemonly
|
||||
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr1, i8* %ptr2, i32 1, i1 false)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
||||
@g = internal global i8 0
|
||||
|
||||
; This case should not be optimized, because @g is captured before the call
|
||||
; (being a global) and @icmp_g might depend on its identity.
|
||||
define void @test_dest_captured_before_global() {
|
||||
; CHECK-LABEL: define {{[^@]+}}@test_dest_captured_before_global() {
|
||||
; CHECK-NEXT: [[PTR:%.*]] = alloca i8, align 1
|
||||
; CHECK-NEXT: call void @icmp_g(i8* [[PTR]])
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* @g, i8* [[PTR]], i32 1, i1 false)
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
%ptr = alloca i8
|
||||
call void @icmp_g(i8* %ptr)
|
||||
call void @llvm.memcpy.p0i8.p0i8.i32(i8* @g, i8* %ptr, i32 1, i1 false)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @icmp_g(i8* %p) {
|
||||
; CHECK-LABEL: define {{[^@]+}}@icmp_g
|
||||
; CHECK-SAME: (i8* [[P:%.*]]) {
|
||||
; CHECK-NEXT: [[C:%.*]] = icmp eq i8* [[P]], @g
|
||||
; CHECK-NEXT: br i1 [[C]], label [[IF:%.*]], label [[ELSE:%.*]]
|
||||
; CHECK: if:
|
||||
; CHECK-NEXT: store i8 1, i8* [[P]], align 1
|
||||
; CHECK-NEXT: ret void
|
||||
; CHECK: else:
|
||||
; CHECK-NEXT: store i8 2, i8* [[P]], align 1
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
%c = icmp eq i8* %p, @g
|
||||
br i1 %c, label %if, label %else
|
||||
|
||||
if:
|
||||
store i8 1, i8* %p
|
||||
ret void
|
||||
|
||||
else:
|
||||
store i8 2, i8* %p
|
||||
ret void
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue