rubydragon/metagraphoptimization.jl
1
0
Fork 0
Code Issues 6 Pull Requests Actions Packages Projects Releases Wiki Activity

Start adding device and machine info

Browse Source
This commit is contained in:
Anton Reinhard 2023-09-17 23:06:14 +02:00
parent bd6c54c1ae
commit f8a591991c
5 changed files with 306 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
Project.toml
View File

@ -4,11 +4,16 @@ authors = ["Anton Reinhard <anton.reinhard@proton.me>"]
version = "0.1.0"
[deps]
AMDGPU = "21141c5a-9bdb-4563-92ae-f87d6854732e"
AccurateArithmetic = "22286c92-06ac-501d-9306-4abd417d9753"
CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
DataStructures = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
JuliaFormatter = "98e50ef6-434e-11e9-1051-2b60c6c9e899"
KernelAbstractions = "63c18a36-062a-441e-b654-da1e3ab1ce7c"
NumaAllocators = "21436f30-1b4a-4f08-87af-e26101bb5379"
Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
UUIDs = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
oneAPI = "8f75cd03-7ff8-4ecb-9b8f-daf728133b1b"
[extras]
Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"

75
docs/src/flowchart.drawio Normal file
View File

@ -0,0 +1,75 @@
<mxfile host="Electron" modified="2023-09-17T13:34:45.840Z" agent="Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) draw.io/21.6.1 Chrome/114.0.5735.134 Electron/25.6.0 Safari/537.36" etag="e0c8qLevhaP_q_R2fyC9" version="21.6.1" type="device">
<diagram name="Page-1" id="Vy0cA1nkMPfy-3cC5ahA">
<mxGraphModel dx="1185" dy="707" grid="1" gridSize="10" guides="1" tooltips="1" connect="1" arrows="1" fold="1" page="1" pageScale="1" pageWidth="500" pageHeight="900" math="0" shadow="0">
<root>
<mxCell id="0" />
<mxCell id="1" parent="0" />
<mxCell id="yG8qeggDCLqQ8GwY7ugi-5" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;shadow=1;" edge="1" parent="1" source="yG8qeggDCLqQ8GwY7ugi-1" target="yG8qeggDCLqQ8GwY7ugi-2">
<mxGeometry relative="1" as="geometry" />
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-1" value="Process Generator Script" style="rounded=1;whiteSpace=wrap;html=1;shadow=1;" vertex="1" parent="1">
<mxGeometry x="180" y="120" width="120" height="60" as="geometry" />
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-11" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;shadow=1;" edge="1" parent="1" source="yG8qeggDCLqQ8GwY7ugi-2" target="yG8qeggDCLqQ8GwY7ugi-3">
<mxGeometry relative="1" as="geometry" />
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-2" value="Process Parser" style="rounded=1;whiteSpace=wrap;html=1;shadow=1;" vertex="1" parent="1">
<mxGeometry x="180" y="220" width="120" height="60" as="geometry" />
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-8" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=1;exitY=0.25;exitDx=0;exitDy=0;entryX=0;entryY=0.25;entryDx=0;entryDy=0;shadow=1;" edge="1" parent="1" source="yG8qeggDCLqQ8GwY7ugi-3" target="yG8qeggDCLqQ8GwY7ugi-6">
<mxGeometry relative="1" as="geometry" />
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-14" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;shadow=1;" edge="1" parent="1" source="yG8qeggDCLqQ8GwY7ugi-3" target="yG8qeggDCLqQ8GwY7ugi-12">
<mxGeometry relative="1" as="geometry" />
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-3" value="Optimizer" style="rounded=1;whiteSpace=wrap;html=1;shadow=1;" vertex="1" parent="1">
<mxGeometry x="180" y="320" width="120" height="60" as="geometry" />
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-9" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=1;entryY=0.75;entryDx=0;entryDy=0;exitX=0;exitY=0.75;exitDx=0;exitDy=0;shadow=1;" edge="1" parent="1" source="yG8qeggDCLqQ8GwY7ugi-6" target="yG8qeggDCLqQ8GwY7ugi-3">
<mxGeometry relative="1" as="geometry" />
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-6" value="Fast Cost Estimator&lt;br&gt;(Global Metrics)" style="rounded=1;whiteSpace=wrap;html=1;shadow=1;" vertex="1" parent="1">
<mxGeometry x="340" y="320" width="120" height="60" as="geometry" />
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-15" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;shadow=1;" edge="1" parent="1" source="yG8qeggDCLqQ8GwY7ugi-12" target="yG8qeggDCLqQ8GwY7ugi-13">
<mxGeometry relative="1" as="geometry">
<Array as="points">
<mxPoint x="80" y="450" />
</Array>
</mxGeometry>
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-12" value="Scheduler" style="rounded=1;whiteSpace=wrap;html=1;shadow=1;" vertex="1" parent="1">
<mxGeometry x="180" y="420" width="120" height="60" as="geometry" />
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-16" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0;entryY=0.5;entryDx=0;entryDy=0;shadow=1;" edge="1" parent="1" source="yG8qeggDCLqQ8GwY7ugi-13" target="yG8qeggDCLqQ8GwY7ugi-3">
<mxGeometry relative="1" as="geometry">
<mxPoint x="120" y="380" as="targetPoint" />
<Array as="points">
<mxPoint x="80" y="350" />
</Array>
</mxGeometry>
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-19" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=0.5;exitY=1;exitDx=0;exitDy=0;shadow=1;" edge="1" parent="1" source="yG8qeggDCLqQ8GwY7ugi-12" target="yG8qeggDCLqQ8GwY7ugi-18">
<mxGeometry relative="1" as="geometry">
<Array as="points">
<mxPoint x="240" y="500" />
<mxPoint x="240" y="500" />
</Array>
</mxGeometry>
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-13" value="Accurate Cost Estimator&lt;br&gt;(Machine Specific)" style="rounded=1;whiteSpace=wrap;html=1;shadow=1;" vertex="1" parent="1">
<mxGeometry x="20" y="370" width="120" height="60" as="geometry" />
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-21" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;shadow=1;" edge="1" parent="1" source="yG8qeggDCLqQ8GwY7ugi-18" target="yG8qeggDCLqQ8GwY7ugi-20">
<mxGeometry relative="1" as="geometry" />
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-18" value="Code Generator" style="rounded=1;whiteSpace=wrap;html=1;shadow=1;" vertex="1" parent="1">
<mxGeometry x="180" y="520" width="120" height="60" as="geometry" />
</mxCell>
<mxCell id="yG8qeggDCLqQ8GwY7ugi-20" value="Executor" style="rounded=1;whiteSpace=wrap;html=1;shadow=1;" vertex="1" parent="1">
<mxGeometry x="180" y="620" width="120" height="60" as="geometry" />
</mxCell>
</root>
</mxGraphModel>
</diagram>
</mxfile>

130
src/devices/detect.jl Normal file
View File

@ -0,0 +1,130 @@
using NumaAllocators
using CUDA
using ROCm
using oneAPI
"""
get_machine_info(verbose::Bool)
Return the [`Machine`](@ref) currently running on. The parameter `verbose` defaults to true when interactive.
"""
function get_machine_info(verbose::Bool = Base.is_interactive())
devices = Vector{Device}()
numaDevices = get_numa_devices(verbose)
push!(devices, numaDevices)
cudaDevices = get_cuda_devices(verbose)
push!(devices, cudaDevices)
rocmDevices = get_rocm_devices(verbose)
push!(devices, rocmDevices)
oneapiDevices = get_oneapi_devices(verbose)
push!(devices, oneapiDevices)
noDevices = length(devices)
@assert noDevices > 0 "No devices were found, but at least one NUMA node should always be available!"
return Machine(
devices,
transferRates::Matrix{Float64}(-1, noDevices, noDevices),
)
end
"""
get_numa_devices(verbose::Bool)
Return a Vector of [`NumaNode`](@ref)s available on the current machine. If `verbose` is true, print some additional information.
"""
function get_numa_devices(verbose::Bool)
devices = Vector{Device}()
noNumaNodes = highest_numa_node()
if (verbose)
println("Found $(noNumaNodes + 1) NUMA nodes")
end
for i in 0:noNumaNodes
push!(devices, NumaNode(i, 1, -1))
end
return devices
end
"""
get_cuda_devices(verbose::Bool)
Return a Vector of [`CUDAGPU`](@ref)s available on the current machine. If `verbose` is true, print some additional information.
"""
function get_cuda_devices(verbose::Bool)
devices = Vector{Device}()
if !CUDA.functional()
if verbose
println("CUDA is non-functional")
end
return devices
end
CUDADevices = CUDA.devices()
if verbose
println("Found $(length(CUDADevices)) CUDA devices")
end
for device in CUDADevices
push!(devices, CUDAGPU(device, -1))
end
return devices
end
"""
get_rocm_devices(verbose::Bool)
Return a Vector of [`ROCmGPU`](@ref)s available on the current machine. If `verbose` is true, print some additional information.
"""
function get_rocm_devices(verbose::Bool)
devices = Vector{Device}()
if !AMDGPU.functional()
if verbose
println("AMDGPU is non-functional")
end
return devices
end
AMDDevices = AMDGPU.devices()
if verbose
println("Found $(length(AMDDevices)) AMD devices")
end
for device in AMDDevices
push!(devices, ROCmGPU(device, -1))
end
return devices
end
"""
get_oneapi_devices(verbose::Bool)
Return a Vector of [`oneAPIGPU`](@ref)s available on the current machine. If `verbose` is true, print some additional information.
"""
function get_oneapi_devices(verbose::Bool)
devices = Vector{Device}()
if !oneAPI.functional()
if verbose
println("oneAPI is non-functional")
end
return devices
end
oneAPIDevices = oneAPI.devices()
if verbose
println("Found $(length(oneAPIDevices)) oneAPI devices")
end
for device in oneAPIDevices
push!(devices, oneAPIGPU(device, -1))
end
return devices
end

56
src/devices/measure.jl Normal file
View File

@ -0,0 +1,56 @@
"""
measure_devices(machine::Machine; verbose::Bool)
Measure FLOPS, RAM, cache sizes and what other properties can be extracted for the devices in the given machine.
"""
function measure_devices!(
machine::Machine;
verbose::Bool = Base.is_interactive(),
)
for device in machine.devices
measure_device!(device; verbose = verbose)
end
return nothing
end
"""
measure_transfer_rates(machine::Machine; verbose::Bool)
Measure the transfer rates between devices in the machine.
"""
function measure_transfer_rates!(
machine::Machine;
verbose::Bool = Base.is_interactive(),
)
return nothing
end
function measure_device!(device::NumaNode; verbose::Bool)
if verbose
println("Measuring Numa Node $(device.numaId)")
end
return nothing
end
function measure_device!(device::CUDAGPU; verbose::Bool)
if verbose
println("Measuring CUDA GPU $(device.device)")
end
return nothing
end
function measure_device!(device::ROCmGPU; verbose::Bool)
if verbose
println("Measuring ROCm GPU $(device.device)")
end
return nothing
end
function measure_device!(device::oneAPIGPU; verbose::Bool)
if verbose
println("Measuring oneAPI GPU $(device.device)")
end
return nothing
end

40
src/devices/type.jl Normal file
View File

@ -0,0 +1,40 @@
abstract type Device end
abstract type CPU <: Device end
mutable struct NumaNode <: CPU
numaId::UInt16
threads::UInt16
FLOPS::Float64
end
abstract type GPU <: Device end
mutable struct CUDAGPU <: GPU
device::Any # TODO: what's the cuda device type?
FLOPS::Float64
end
mutable struct ROCmGPU <: GPU
device::Any
FLOPS::Float64
end
mutable struct oneAPIGPU <: GPU
device::Any
FLOPS::Float64
end
"""
Machine
A representation of a machine to execute on. Contains information about its architecture (CPUs, GPUs, maybe more). This representation can be used to make a more accurate cost prediction of a [`DAG`](@ref) state.
See also: [`Scheduler`](@ref)
"""
struct Machine
devices::Vector{Device}
transferRates::Matrix{Float64}
end