From 0203254b709614fa732c114aa25916f61b8b3275 Mon Sep 17 00:00:00 2001 From: Niels Thiele Date: Sun, 22 Jun 2025 12:31:21 +0200 Subject: Implemented Single GPU Support & outline of host-level allocation policies (#342) * renamed performance counter to distinguish different resource types * added GPU, modelled similar to CPU * added GPUs to machine model * list of GPUs instead of single instance * renamed memory speed to bandwidth * enabled parsing of GPU resources * split powermodel into cpu and GPU powermodel * added gpu parsing tests * added idea of host level scheduling * added tests for multi gpu parsing * renamed powermodel to cpupowermodel * clarified naming of cpu and gpu components * added resource type to flow suplier and edge * added resourcetype * added GPU components and resource type to fragments * added GPU to workload and updated resource usage retrieval * implemented first version of multi resource * added name to workload * renamed perfomance counters * removed commented out code * removed deprecated comments * included demand and supply into calculations * resolving rebase mismatches * moved resource type from flowedge class to common package * added available resources to machinees * cleaner separation if workload is started of simmachine or vm * Replaced exception with dedicated enum * Only looping over resources that are actually used * using hashmaps to handle resourcetype instead of arrays for readability * fixed condition * tracking finished workloads per resource type * removed resource type from flowedge * made supply and demand distribution resource specific * added power model for GPU * removed unused test setup * removed depracated comments * removed unused parameter * added ID for GPU * added GPUs and GPU performance counters (naively) * implemented capturing of GPU statistics * added reminders for future implementations * renamed properties for better identification * added capturing GPU statistics * implemented first tests for GPUs * unified access to performance counters * added interface for general compute resource handling * implemented multi resource support in simmachine * added individual edge to VM per resource * extended compute resource interface * implemented multi-resource support in PSU * implemented generic retrieval of computeresources * implemented mult-resource suppport in vm * made method use more resource specific * implemented simple GPU tests * rolled back frquency and demand use * made naming independent of used resource * using workloads resources instead of VMs to determine available resource * implemented determination of used resources in workload * removed logging statements * implemented reading from workload * fixed naming for host-level allocation * fixed next deadline calculation * fixed forwarding supply * reduced memory footprint * made GPU powermodel nullable * maded Gpu powermodel configurable in topology * implemented tests for basic gpu scheduler * added gpu properties * implemented weights, filter and simple cpu-gpu scheduler * spotless apply * spotless apply pt. 2 * fixed capitalization * spotless kotlin run * implemented coloumn export * todo update * removed code comments * Merged PerformanceCounter classes into one & removed interface * removed GPU specific powermodel * Rebase master: kept both versions of TopologyFactories * renamed CpuPowermodel to resource independent Powermodel Moved it from Cpu package to power package * implementated default of getResourceType & removed overrides if possible * split getResourceType into Consumer and Supplier * added power as resource type * reduced supply demand from arrayList to single value * combining GPUs into one large GPU, until full multi-gpu support * merged distribution policy enum with corresponding factory * added comment * post-rebase fixes * aligned naming * Added GPU metrics to task output * Updates power resource type to uppercase. Standardizes the `ResourceType.Power` enum to `ResourceType.POWER` for consistency with other resource types and improved readability. * Removes deprecated test assertions Removes commented-out assertions in GPU tests. These assertions are no longer needed and clutter the test code. * Renames MaxMinFairnessStrategy to Policy Renames MaxMinFairnessStrategy to MaxMinFairnessPolicy for clarity and consistency with naming conventions. This change affects the factory and distributor to use the updated name. * applies spotless * nulls GPUs as it is not used --- .../org/opendc/simulator/compute/SimMachineTest.kt | 41 +++++++++++----------- 1 file changed, 20 insertions(+), 21 deletions(-) (limited to 'opendc-simulator/opendc-simulator-compute/src/test') diff --git a/opendc-simulator/opendc-simulator-compute/src/test/kotlin/org/opendc/simulator/compute/SimMachineTest.kt b/opendc-simulator/opendc-simulator-compute/src/test/kotlin/org/opendc/simulator/compute/SimMachineTest.kt index 173c60e7..eb3d3377 100644 --- a/opendc-simulator/opendc-simulator-compute/src/test/kotlin/org/opendc/simulator/compute/SimMachineTest.kt +++ b/opendc-simulator/opendc-simulator-compute/src/test/kotlin/org/opendc/simulator/compute/SimMachineTest.kt @@ -22,32 +22,31 @@ package org.opendc.simulator.compute -import org.junit.jupiter.api.BeforeEach -import org.opendc.simulator.compute.models.CpuModel import org.opendc.simulator.compute.models.MachineModel -import org.opendc.simulator.compute.models.MemoryUnit /** * Test suite for the [SimBareMetalMachine] class. */ + class SimMachineTest { private lateinit var machineModel: MachineModel - - @BeforeEach - fun setUp() { - machineModel = - MachineModel( - CpuModel( - 0, - 2, - 1000.0, - "Intel", - "Xeon", - "amd64", - ), - MemoryUnit("Crucial", "MTA18ASF4G72AZ-3G2B1", 3200.0, 32_000 * 4), - ) - } +// +// @BeforeEach +// fun setUp() { +// machineModel = +// MachineModel( +// CpuModel( +// 0, +// 2, +// 1000.0, +// "Intel", +// "Xeon", +// "amd64", +// ), +// MemoryUnit("Crucial", "MTA18ASF4G72AZ-3G2B1", 3200.0, 32_000 * 4), +// null +// ) +// } // @Test // fun testFlopsWorkload() = @@ -104,10 +103,10 @@ class SimMachineTest { // val cpuNode = machineModel.cpu // val machineModel = // MachineModel( -// List(cpuNode.coreCount * 2) { +// List(cpuNode.cpuCoreCount * 2) { // CpuModel( // it, -// cpuNode.coreCount, +// cpuNode.cpuCoreCount, // 1000.0, // ) // }, -- cgit v1.2.3