F# Alea没有正确地处理内存
以下F#代码在第三次调用时崩溃，出现无内存异常。要么我遗漏了什么，要么Alea由于某种原因没有正确释放内存。我在F#Interactive和Compiled两个版本中都尝试过。我也尝试过手动调用dispose，但不起作用。知道为什么吗F# Alea没有正确地处理内存,f#,aleagpu,F#,Aleagpu,以下F#代码在第三次调用时崩溃，出现无内存异常。要么我遗漏了什么，要么Alea由于某种原因没有正确释放内存。我在F#Interactive和Compiled两个版本中都尝试过。我也尝试过手动调用dispose，但不起作用。知道为什么吗 let squareGPU (inputs:float[]) = use dInputs = worker.Malloc(inputs) use dOutputs = worker.Malloc(inputs.Length)
let squareGPU (inputs:float[]) =
use dInputs = worker.Malloc(inputs)
use dOutputs = worker.Malloc(inputs.Length)
let blockSize = 256
let numSm = worker.Device.Attributes.MULTIPROCESSOR_COUNT
let gridSize = Math.Min(16 * numSm, divup inputs.Length blockSize)
let lp = new LaunchParam(gridSize, blockSize)
worker.Launch <@ squareKernel @> lp dOutputs.Ptr dInputs.Ptr inputs.Length
dOutputs.Gather()
let x = squareGPU [|0.0..0.001..100000.0|]
printfn "1"
let y = squareGPU [|0.0..0.001..100000.0|]
printfn "2"
let z = squareGPU [|0.0..0.001..100000.0|]
printfn "3"
let squareGPU（输入：浮点[]）=
使用dInputs=worker.Malloc（输入）
使用dOutputs=worker.Malloc（inputs.Length）
让blockSize=256
让numSm=worker.Device.Attributes.MULTIPROCESSOR\u计数
让gridSize=Math.Min（16*numm，分段输入。长度块大小）
设lp=新启动参数（gridSize、blockSize）
worker.Launch lp dOutputs.Ptr dinput.Ptr inputs.Length
dOutputs.Gather（）
设x=squareGPU[| 0.0..0.001..100000.0 |]
printfn“1”
设y=squareGPU[| 0.0..0.001..100000.0 |]
printfn“2”
设z=squareGPU[| 0.0..0.001..100000.0 |]
打印fn“3”
系统。OutOfMemoryExceptionlet x1 = [|0.0..0.001..30000.0|]
printfn "1"
let x2 = [|0.0..0.001..30000.0|]
printfn "2"
let x3 = [|0.0..0.001..30000.0|]
printfn "3"
let x4 = [|0.0..0.001..30000.0|]
printfn "4"
let x5 = [|0.0..0.001..30000.0|]
printfn "5"
let x6 = [|0.0..0.001..30000.0|]
printfn "6"
Microsoft (R) F# Interactive version 12.0.30815.0
Copyright (c) Microsoft Corporation. All Rights Reserved.
For help type #help;;
>
1
2
System.OutOfMemoryException: Exception of type 'System.OutOfMemoryException' was thrown.
at System.Collections.Generic.List`1.set_Capacity(Int32 value)
at System.Collections.Generic.List`1.EnsureCapacity(Int32 min)
at System.Collections.Generic.List`1.Add(T item)
at Microsoft.FSharp.Collections.SeqModule.ToArray[T](IEnumerable`1 source)
at <StartupCode$FSI_0002>.$FSI_0002.main@() in C:\Users\Xiang\Documents\Inbox\ConsoleApplication6\Script1.fsx:line 32
Stopped due to error
>
let foo() =
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "1"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "2"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "3"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "4"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "5"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "6"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "7"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "8"
> foo();;
1
2
3
4
5
6
7
8
val it : unit = ()
>
或者，您可以尝试使用64位进程。GC在一个单独的后台线程中工作，因此，如果您经常新建大型数组，它将很容易抛出内存不足异常 在这个大数组的情况下，我建议您使用“就地修改”样式，这样会更稳定。我创建了一个测试来显示：（注意，由于数组非常大，您最好转到项目属性页，在Build选项卡中，取消选中“preferred32-bit”，以确保它作为64位进程运行）
开放系统
打开Alea.CUDA
打开Alea.CUDA.Utilities
打开NUnit.Framework
[]
let squareKernel（输出：deviceptr）（输入：deviceptr）（n:int）=
让start=blockIdx.x*blockDim.x+threadIdx.x
让stride=gridDim.x*blockDim.x
让可变的i=开始
而我
输出。[我]对aleagpu一无所知，我觉得奇怪的是，你会调用dOutputs.Gather（）
，而不是dinput.Gather（）
。我假设这是在调用Malloc（）
之后进行的清理。不，Gather（）
只是将数据从GPU复制到主机内存。你是对的。我最初在交互模式下测试它的方法是在没有任何let绑定的情况下反复调用squareGPU[|0.0..0.001..100000.0]。由于某些原因，当您在同一行上重复执行该操作时，它不会触发GC。即使在没有任何函数调用的情况下执行[|0.0..0.001..30000.0 |]，也会导致内存阻塞。我想知道这是怎么回事？嗯，那么我不知道是怎么回事，你可以看到，我运行了8次，效果很好。你介意发布没有主机内存问题的测试吗？你的例子对我来说很有用，当变量超出范围时，确实可以适当地释放内存。如果您在F#Interactive中执行[|0.0..0.001..30000.0 |][|0.0..0.001..30000.0 |]时打开任务管理器，您将看到我的意思，而不是在函数内部。内存使用率应该会上升，但不会因为它从未超出范围而被释放。正如您在下面的文章中所说，GC在一个单独的线程中工作。谢谢你的课。我希望我有代表，这样我就可以投票给你了。
let foo() =
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "1"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "2"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "3"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "4"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "5"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "6"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "7"
let x = squareGPU [|0.0..0.001..30000.0|]
printfn "8"
> foo();;
1
2
3
4
5
6
7
8
val it : unit = ()
>
open System
open Alea.CUDA
open Alea.CUDA.Utilities
open NUnit.Framework
[<ReflectedDefinition>]
let squareKernel (outputs:deviceptr<float>) (inputs:deviceptr<float>) (n:int) =
let start = blockIdx.x * blockDim.x + threadIdx.x
let stride = gridDim.x * blockDim.x
let mutable i = start
while i < n do
outputs.[i] <- inputs.[i] * inputs.[i]
i <- i + stride
let squareGPUInplaceUpdate (worker:Worker) (lp:LaunchParam) (hData:float[]) (dData:DeviceMemory<float>) =
// instead of malloc a new device memory, you just reuse the device memory dData
// and scatter new data to it.
dData.Scatter(hData)
worker.Launch <@ squareKernel @> lp dData.Ptr dData.Ptr hData.Length
// actually, there should be a counterpart of data.Scatter(hData) like data.Gather(hData)
// but unfortunately, that is missing, but there is a workaround of using worker.Gather.
worker.Gather(dData.Ptr, hData)
let squareGPUManyTimes (iters:int) =
let worker = Worker.Default
// actually during the many iters, you just malloc 2 host array (for data and expected value)
// and you malloc a device array. You keep reusing them, since they are big array.
// if you new the huge array very frequentely, GC is under pressure. and since GC works
// as a separate thread, so you will get System.OutOfMemoryException from time to time.
let hData = [|0.0..0.001..100000.0|]
let n = hData.Length
let expected = Array.zeroCreate n
use dData = worker.Malloc<float>(n)
let rng = Random()
let update () =
// in-place updating the data
for i = 0 to n - 1 do
hData.[i] <- rng.NextDouble()
expected.[i] <- hData.[i] * hData.[i]
let lp =
let blockSize = 256
let numSm = worker.Device.Attributes.MULTIPROCESSOR_COUNT
let gridSize = Math.Min(16 * numSm, divup n blockSize)
new LaunchParam(gridSize, blockSize)
for i = 1 to iters do
update()
squareGPUInplaceUpdate worker lp hData dData
Assert.AreEqual(expected, hData)
printfn "iter %d passed..." i
[<Test>]
let test() =
squareGPUManyTimes 5