nnicolosi/Raptor
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

better throughput scheduling with steady state cost model (WIP)

Browse Source
This commit is contained in:
NiccoloN
2026-10-23 11:27:06 +02:00
parent 48e9fb3795
commit fd493ae6e8
51 changed files with 3581 additions and 247 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/PIM/SpatialSchedulingTargetTest.cpp
+50
View File
@@ -19,6 +19,8 @@
#include "src/Accelerators/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredCommunicationScheduling.hpp"
#include "src/Accelerators/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryPlanning.hpp"
#include "src/Accelerators/PIM/Compiler/PimScheduleDiagnostic.hpp"
#include "src/Accelerators/PIM/Compiler/PimInstructionTiming.hpp"
#include "src/Accelerators/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredTransferPlanning.hpp"
#include "src/Accelerators/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/ScheduledComputeMaterialization.hpp"
#include "src/Accelerators/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredCommunicationRealization.hpp"
@@ -1030,6 +1032,54 @@ static void checkPublicationMemoryTraffic(mlir::func::FuncOp function,
assert(mlir::succeeded(communication));
auto boundaries = buildDeferredBoundaryPlan(*shared, *communication, registers);
assert(mlir::succeeded(boundaries));
std::string before, after;
llvm::raw_string_ostream beforeStream(before), afterStream(after);
function.print(beforeStream);
onnx_mlir::PimInstructionTiming timed;
static_cast<SchedulingTarget &>(timed) = target;
timed.peerPermissionThenSourceRead = true;
timed.signalIssueNs = 1;
timed.controlMessageBytes = 1;
timed.sharedMemoryRequestLatencyNs.assign(4, 3);
timed.sharedMemoryResponseLatencyNs.assign(4, 5);
timed.interProcessorLatencyNs.assign(16, 2);
for (size_t core = 0; core < 4; ++core)
timed.interProcessorLatencyNs[core * 4 + core] = 0;
auto report = getPeriodicScheduleReport(graph, *materialized, *shared, *boundaries, timed);
assert(report.getString("status") == "estimated");
assert(report.getBoolean("diagnostic_only") == true);
assert(report.getInteger("boundary_write_bytes") == expected.writeBytes);
assert(report.getInteger("boundary_read_bytes") == expected.readBytes);
timed.sharedMemoryReadReturnsPayload = false;
auto noResponse = getPeriodicScheduleReport(graph, *materialized, *shared, *boundaries, timed);
assert(noResponse.getString("status") == "estimated");
assert(*noResponse.getNumber("interval_estimate_ns") <= *report.getNumber("interval_estimate_ns"));
bool checkedRunOwnership = false;
for (size_t i = 0; i < shared->scheduled.size(); ++i)
if (!materialized->materializedSchedules[i].runs.empty()) {
auto &cores = shared->scheduled[i].cores;
assert(cores.size() == 1);
cores.push_back((cores.front() + 1) % target.processorCount);
auto invalidRun = getPeriodicScheduleReport(graph, *materialized, *shared, *boundaries, timed);
assert(invalidRun.getString("status") == "unavailable");
assert(invalidRun.getString("reason") == "compact compute runs require one physical core");
cores.pop_back();
checkedRunOwnership = true;
break;
}
assert(checkedRunOwnership);
onnx_mlir::PimInstructionTiming incomplete = timed;
incomplete.sharedMemoryRequestLatencyNs.clear();
auto unavailable = getPeriodicScheduleReport(graph, *materialized,
*shared, *boundaries, incomplete);
assert(unavailable.getString("status") == "unavailable");
incomplete = timed;
incomplete.peerPermissionThenSourceRead = false;
unavailable = getPeriodicScheduleReport(graph, *materialized,
*shared, *boundaries, incomplete);
assert(unavailable.getString("status") == "unavailable");
function.print(afterStream);
assert(before == after && "periodic diagnostics must not mutate scheduled IR");
size_t stores = 0, signals = 0, readyWaits = 0, freeWaits = 0, releases = 0;
llvm::DenseSet<int64_t> published;
for (const auto &boundary : boundaries->boundaries)