mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 05:01:59 +01:00
51d7b85305
Previously, we would ignore alloca alignment when building the frame and just use the natural alignment of the allocated type. If an alloca is over-aligned for its IR type, this could lead to a frame entry with inadequate alignment for the downstream uses of the alloca. Since highly-aligned fields also tend to produce poor layouts under a naive layout algorithm, I've also switched coroutine frames to use the new optimal struct layout algorithm. In order to communicate the frame size and alignment to later passes, I needed to set align+dereferenceable attributes on the frame-pointer parameter of the resume function. This is clearly the right thing to do, but the align attribute currently seems to result in assumptions being added during inlining that the optimizer cannot easily remove.
56 lines
1.8 KiB
LLVM
56 lines
1.8 KiB
LLVM
; First example from Doc/Coroutines.rst (one block loop)
|
|
; RUN: opt < %s -O2 -enable-coroutines -preserve-alignment-assumptions-during-inlining=false -S | FileCheck %s
|
|
; RUN: opt < %s -aa-pipeline=basic-aa -passes='default<O2>' -enable-coroutines -preserve-alignment-assumptions-during-inlining=false -S | FileCheck %s
|
|
|
|
define i8* @f(i32 %n) {
|
|
entry:
|
|
%id = call token @llvm.coro.id(i32 0, i8* null, i8* null, i8* null)
|
|
%size = call i32 @llvm.coro.size.i32()
|
|
%alloc = call i8* @malloc(i32 %size)
|
|
%hdl = call noalias i8* @llvm.coro.begin(token %id, i8* %alloc)
|
|
br label %loop
|
|
loop:
|
|
%n.val = phi i32 [ %n, %entry ], [ %inc, %loop ]
|
|
%inc = add nsw i32 %n.val, 1
|
|
call void @print(i32 %n.val)
|
|
%0 = call i8 @llvm.coro.suspend(token none, i1 false)
|
|
switch i8 %0, label %suspend [i8 0, label %loop
|
|
i8 1, label %cleanup]
|
|
cleanup:
|
|
%mem = call i8* @llvm.coro.free(token %id, i8* %hdl)
|
|
call void @free(i8* %mem)
|
|
br label %suspend
|
|
suspend:
|
|
call i1 @llvm.coro.end(i8* %hdl, i1 false)
|
|
ret i8* %hdl
|
|
}
|
|
|
|
; CHECK-LABEL: @main(
|
|
define i32 @main() {
|
|
entry:
|
|
%hdl = call i8* @f(i32 4)
|
|
call void @llvm.coro.resume(i8* %hdl)
|
|
call void @llvm.coro.resume(i8* %hdl)
|
|
call void @llvm.coro.destroy(i8* %hdl)
|
|
ret i32 0
|
|
; CHECK-NEXT: entry:
|
|
; CHECK: call void @print(i32 4)
|
|
; CHECK: call void @print(i32 5)
|
|
; CHECK: call void @print(i32 6)
|
|
; CHECK: ret i32 0
|
|
}
|
|
|
|
declare i8* @malloc(i32)
|
|
declare void @free(i8*)
|
|
declare void @print(i32)
|
|
|
|
declare token @llvm.coro.id(i32, i8*, i8*, i8*)
|
|
declare i32 @llvm.coro.size.i32()
|
|
declare i8* @llvm.coro.begin(token, i8*)
|
|
declare i8 @llvm.coro.suspend(token, i1)
|
|
declare i8* @llvm.coro.free(token, i8*)
|
|
declare i1 @llvm.coro.end(i8*, i1)
|
|
|
|
declare void @llvm.coro.resume(i8*)
|
|
declare void @llvm.coro.destroy(i8*)
|