[llvm] f2ade65 - [CSSPGO] Even flow distribution
via llvm-commits
llvm-commits at lists.llvm.org
Wed Mar 2 13:12:24 PST 2022
Author: spupyrev
Date: 2022-03-02T13:12:05-08:00
New Revision: f2ade65fb2a63679d48178608286753616809bc0
URL: https://github.com/llvm/llvm-project/commit/f2ade65fb2a63679d48178608286753616809bc0
DIFF: https://github.com/llvm/llvm-project/commit/f2ade65fb2a63679d48178608286753616809bc0.diff
LOG: [CSSPGO] Even flow distribution
Differential Revision: https://reviews.llvm.org/D118640
Added:
llvm/test/Transforms/SampleProfile/Inputs/profile-inference-even-count-distribution.prof
llvm/test/Transforms/SampleProfile/profile-inference-even-count-distribution.ll
Modified:
llvm/lib/Transforms/Utils/SampleProfileInference.cpp
llvm/test/Transforms/SampleProfile/csspgo-import-list.ll
llvm/test/Transforms/SampleProfile/profile-context-tracker.ll
Removed:
################################################################################
diff --git a/llvm/lib/Transforms/Utils/SampleProfileInference.cpp b/llvm/lib/Transforms/Utils/SampleProfileInference.cpp
index 961adf2570a73..8fbebb6d4ddee 100644
--- a/llvm/lib/Transforms/Utils/SampleProfileInference.cpp
+++ b/llvm/lib/Transforms/Utils/SampleProfileInference.cpp
@@ -15,15 +15,27 @@
#include "llvm/Transforms/Utils/SampleProfileInference.h"
#include "llvm/ADT/BitVector.h"
+#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include <queue>
#include <set>
+#include <stack>
using namespace llvm;
#define DEBUG_TYPE "sample-profile-inference"
namespace {
+static cl::opt<bool> SampleProfileEvenCountDistribution(
+ "sample-profile-even-count-distribution", cl::init(true), cl::Hidden,
+ cl::ZeroOrMore,
+ cl::desc("Try to evenly distribute counts when there are multiple equally "
+ "likely options."));
+
+static cl::opt<unsigned> SampleProfileMaxDfsCalls(
+ "sample-profile-max-dfs-calls", cl::init(10), cl::Hidden, cl::ZeroOrMore,
+ cl::desc("Maximum number of dfs iterations for even count distribution."));
+
/// A value indicating an infinite flow/capacity/weight of a block/edge.
/// Not using numeric_limits<int64_t>::max(), as the values can be summed up
/// during the execution.
@@ -52,16 +64,16 @@ class MinCostMaxFlow {
Nodes = std::vector<Node>(NodeCount);
Edges = std::vector<std::vector<Edge>>(NodeCount, std::vector<Edge>());
+ if (SampleProfileEvenCountDistribution)
+ AugmentingEdges =
+ std::vector<std::vector<Edge *>>(NodeCount, std::vector<Edge *>());
}
// Run the algorithm.
int64_t run() {
- // Find an augmenting path and update the flow along the path
- size_t AugmentationIters = 0;
- while (findAugmentingPath()) {
- augmentFlowAlongPath();
- AugmentationIters++;
- }
+ // Iteratively find an augmentation path/dag in the network and send the
+ // flow along its edges
+ size_t AugmentationIters = applyFlowAugmentation();
// Compute the total flow and its cost
int64_t TotalCost = 0;
@@ -79,6 +91,7 @@ class MinCostMaxFlow {
<< " iterations with " << TotalFlow << " total flow"
<< " of " << TotalCost << " cost\n");
(void)TotalFlow;
+ (void)AugmentationIters;
return TotalCost;
}
@@ -148,6 +161,55 @@ class MinCostMaxFlow {
static constexpr int64_t AuxCostUnlikely = ((int64_t)1) << 30;
private:
+ /// Iteratively find an augmentation path/dag in the network and send the
+ /// flow along its edges. The method returns the number of applied iterations.
+ size_t applyFlowAugmentation() {
+ size_t AugmentationIters = 0;
+ while (findAugmentingPath()) {
+ uint64_t PathCapacity = computeAugmentingPathCapacity();
+ while (PathCapacity > 0) {
+ bool Progress = false;
+ if (SampleProfileEvenCountDistribution) {
+ // Identify node/edge candidates for augmentation
+ identifyShortestEdges(PathCapacity);
+
+ // Find an augmenting DAG
+ auto AugmentingOrder = findAugmentingDAG();
+
+ // Apply the DAG augmentation
+ Progress = augmentFlowAlongDAG(AugmentingOrder);
+ PathCapacity = computeAugmentingPathCapacity();
+ }
+
+ if (!Progress) {
+ augmentFlowAlongPath(PathCapacity);
+ PathCapacity = 0;
+ }
+
+ AugmentationIters++;
+ }
+ }
+ return AugmentationIters;
+ }
+
+ /// Compute the capacity of the cannonical augmenting path. If the path is
+ /// saturated (that is, no flow can be sent along the path), then return 0.
+ uint64_t computeAugmentingPathCapacity() {
+ uint64_t PathCapacity = INF;
+ uint64_t Now = Target;
+ while (Now != Source) {
+ uint64_t Pred = Nodes[Now].ParentNode;
+ auto &Edge = Edges[Pred][Nodes[Now].ParentEdgeIndex];
+
+ assert(Edge.Capacity >= Edge.Flow && "incorrect edge flow");
+ uint64_t EdgeCapacity = uint64_t(Edge.Capacity - Edge.Flow);
+ PathCapacity = std::min(PathCapacity, EdgeCapacity);
+
+ Now = Pred;
+ }
+ return PathCapacity;
+ }
+
/// Check for existence of an augmenting path with a positive capacity.
bool findAugmentingPath() {
// Initialize data structures
@@ -180,7 +242,7 @@ class MinCostMaxFlow {
// from Source to Target; it follows from inequalities
// Dist[Source, Target] >= Dist[Source, V] + Dist[V, Target]
// >= Dist[Source, V]
- if (Nodes[Target].Distance == 0)
+ if (!SampleProfileEvenCountDistribution && Nodes[Target].Distance == 0)
break;
if (Nodes[Src].Distance > Nodes[Target].Distance)
continue;
@@ -210,21 +272,9 @@ class MinCostMaxFlow {
}
/// Update the current flow along the augmenting path.
- void augmentFlowAlongPath() {
- // Find path capacity
- int64_t PathCapacity = INF;
- uint64_t Now = Target;
- while (Now != Source) {
- uint64_t Pred = Nodes[Now].ParentNode;
- auto &Edge = Edges[Pred][Nodes[Now].ParentEdgeIndex];
- PathCapacity = std::min(PathCapacity, Edge.Capacity - Edge.Flow);
- Now = Pred;
- }
-
+ void augmentFlowAlongPath(uint64_t PathCapacity) {
assert(PathCapacity > 0 && "found an incorrect augmenting path");
-
- // Update the flow along the path
- Now = Target;
+ uint64_t Now = Target;
while (Now != Source) {
uint64_t Pred = Nodes[Now].ParentNode;
auto &Edge = Edges[Pred][Nodes[Now].ParentEdgeIndex];
@@ -237,6 +287,220 @@ class MinCostMaxFlow {
}
}
+ /// Find an Augmenting DAG order using a modified version of DFS in which we
+ /// can visit a node multiple times. In the DFS search, when scanning each
+ /// edge out of a node, continue search at Edge.Dst endpoint if it has not
+ /// been discovered yet and its NumCalls < MaxDfsCalls. The algorithm
+ /// runs in O(MaxDfsCalls * |Edges| + |Nodes|) time.
+ /// It returns an Augmenting Order (Taken nodes in decreasing Finish time)
+ /// that starts with Source and ends with Target.
+ std::vector<uint64_t> findAugmentingDAG() {
+ // We use a stack based implemenation of DFS to avoid recursion.
+ // Defining DFS data structures:
+ // A pair (NodeIdx, EdgeIdx) at the top of the Stack denotes that
+ // - we are currently visiting Nodes[NodeIdx] and
+ // - the next edge to scan is Edges[NodeIdx][EdgeIdx]
+ typedef std::pair<uint64_t, uint64_t> StackItemType;
+ std::stack<StackItemType> Stack;
+ std::vector<uint64_t> AugmentingOrder;
+
+ // Phase 0: Initialize Node attributes and Time for DFS run
+ for (auto &Node : Nodes) {
+ Node.Discovery = 0;
+ Node.Finish = 0;
+ Node.NumCalls = 0;
+ Node.Taken = false;
+ }
+ uint64_t Time = 0;
+ // Mark Target as Taken
+ // Taken attribute will be propagated backwards from Target towards Source
+ Nodes[Target].Taken = true;
+
+ // Phase 1: Start DFS traversal from Source
+ Stack.emplace(Source, 0);
+ Nodes[Source].Discovery = ++Time;
+ while (!Stack.empty()) {
+ auto NodeIdx = Stack.top().first;
+ auto EdgeIdx = Stack.top().second;
+
+ // If we haven't scanned all edges out of NodeIdx, continue scanning
+ if (EdgeIdx < Edges[NodeIdx].size()) {
+ auto &Edge = Edges[NodeIdx][EdgeIdx];
+ auto &Dst = Nodes[Edge.Dst];
+ Stack.top().second++;
+
+ if (Edge.OnShortestPath) {
+ // If we haven't seen Edge.Dst so far, continue DFS search there
+ if (Dst.Discovery == 0 && Dst.NumCalls < SampleProfileMaxDfsCalls) {
+ Dst.Discovery = ++Time;
+ Stack.emplace(Edge.Dst, 0);
+ Dst.NumCalls++;
+ } else if (Dst.Taken && Dst.Finish != 0) {
+ // Else, if Edge.Dst already have a path to Target, so that NodeIdx
+ Nodes[NodeIdx].Taken = true;
+ }
+ }
+ } else {
+ // If we are done scanning all edge out of NodeIdx
+ Stack.pop();
+ // If we haven't found a path from NodeIdx to Target, forget about it
+ if (!Nodes[NodeIdx].Taken) {
+ Nodes[NodeIdx].Discovery = 0;
+ } else {
+ // If we have found a path from NodeIdx to Target, then finish NodeIdx
+ // and propagate Taken flag to DFS parent unless at the Source
+ Nodes[NodeIdx].Finish = ++Time;
+ // NodeIdx == Source if and only if the stack is empty
+ if (NodeIdx != Source) {
+ assert(!Stack.empty() && "empty stack while running dfs");
+ Nodes[Stack.top().first].Taken = true;
+ }
+ AugmentingOrder.push_back(NodeIdx);
+ }
+ }
+ }
+ // Nodes are collected decreasing Finish time, so the order is reversed
+ std::reverse(AugmentingOrder.begin(), AugmentingOrder.end());
+
+ // Phase 2: Extract all forward (DAG) edges and fill in AugmentingEdges
+ for (size_t Src : AugmentingOrder) {
+ AugmentingEdges[Src].clear();
+ for (auto &Edge : Edges[Src]) {
+ uint64_t Dst = Edge.Dst;
+ if (Edge.OnShortestPath && Nodes[Src].Taken && Nodes[Dst].Taken &&
+ Nodes[Dst].Finish < Nodes[Src].Finish) {
+ AugmentingEdges[Src].push_back(&Edge);
+ }
+ }
+ assert((Src == Target || !AugmentingEdges[Src].empty()) &&
+ "incorrectly constructed augmenting edges");
+ }
+
+ return AugmentingOrder;
+ }
+
+ /// Update the current flow along the given (acyclic) subgraph specified by
+ /// the vertex order, AugmentingOrder. The objective is to send as much flow
+ /// as possible while evenly distributing flow among successors of each node.
+ /// After the update at least one edge is saturated.
+ bool augmentFlowAlongDAG(const std::vector<uint64_t> &AugmentingOrder) {
+ // Phase 0: Initialization
+ for (uint64_t Src : AugmentingOrder) {
+ Nodes[Src].FracFlow = 0;
+ Nodes[Src].IntFlow = 0;
+ for (auto &Edge : AugmentingEdges[Src]) {
+ Edge->AugmentedFlow = 0;
+ }
+ }
+
+ // Phase 1: Send a unit of fractional flow along the DAG
+ uint64_t MaxFlowAmount = INF;
+ Nodes[Source].FracFlow = 1.0;
+ for (uint64_t Src : AugmentingOrder) {
+ assert((Src == Target || Nodes[Src].FracFlow > 0.0) &&
+ "incorrectly computed fractional flow");
+ // Distribute flow evenly among successors of Src
+ uint64_t Degree = AugmentingEdges[Src].size();
+ for (auto &Edge : AugmentingEdges[Src]) {
+ double EdgeFlow = Nodes[Src].FracFlow / Degree;
+ Nodes[Edge->Dst].FracFlow += EdgeFlow;
+ if (Edge->Capacity == INF)
+ continue;
+ uint64_t MaxIntFlow = double(Edge->Capacity - Edge->Flow) / EdgeFlow;
+ MaxFlowAmount = std::min(MaxFlowAmount, MaxIntFlow);
+ }
+ }
+ // Stop early if we cannot send any (integral) flow from Source to Target
+ if (MaxFlowAmount == 0)
+ return false;
+
+ // Phase 2: Send an integral flow of MaxFlowAmount
+ Nodes[Source].IntFlow = MaxFlowAmount;
+ for (uint64_t Src : AugmentingOrder) {
+ if (Src == Target)
+ break;
+ // Distribute flow evenly among successors of Src, rounding up to make
+ // sure all flow is sent
+ uint64_t Degree = AugmentingEdges[Src].size();
+ // We are guaranteeed that Node[Src].IntFlow <= SuccFlow * Degree
+ uint64_t SuccFlow = (Nodes[Src].IntFlow + Degree - 1) / Degree;
+ for (auto &Edge : AugmentingEdges[Src]) {
+ uint64_t Dst = Edge->Dst;
+ uint64_t EdgeFlow = std::min(Nodes[Src].IntFlow, SuccFlow);
+ EdgeFlow = std::min(EdgeFlow, uint64_t(Edge->Capacity - Edge->Flow));
+ Nodes[Dst].IntFlow += EdgeFlow;
+ Nodes[Src].IntFlow -= EdgeFlow;
+ Edge->AugmentedFlow += EdgeFlow;
+ }
+ }
+ assert(Nodes[Target].IntFlow <= MaxFlowAmount);
+ Nodes[Target].IntFlow = 0;
+
+ // Phase 3: Send excess flow back traversing the nodes backwards.
+ // Because of rounding, not all flow can be sent along the edges of Src.
+ // Hence, sending the remaining flow back to maintain flow conservation
+ for (size_t Idx = AugmentingOrder.size() - 1; Idx > 0; Idx--) {
+ uint64_t Src = AugmentingOrder[Idx - 1];
+ // Try to send excess flow back along each edge.
+ // Make sure we only send back flow we just augmented (AugmentedFlow).
+ for (auto &Edge : AugmentingEdges[Src]) {
+ uint64_t Dst = Edge->Dst;
+ if (Nodes[Dst].IntFlow == 0)
+ continue;
+ uint64_t EdgeFlow = std::min(Nodes[Dst].IntFlow, Edge->AugmentedFlow);
+ Nodes[Dst].IntFlow -= EdgeFlow;
+ Nodes[Src].IntFlow += EdgeFlow;
+ Edge->AugmentedFlow -= EdgeFlow;
+ }
+ }
+
+ // Phase 4: Update flow values along all edges
+ bool HasSaturatedEdges = false;
+ for (uint64_t Src : AugmentingOrder) {
+ // Verify that we have sent all the excess flow from the node
+ assert(Src == Source || Nodes[Src].IntFlow == 0);
+ for (auto &Edge : AugmentingEdges[Src]) {
+ assert(uint64_t(Edge->Capacity - Edge->Flow) >= Edge->AugmentedFlow);
+ // Update flow values along the edge and its reverse copy
+ auto &RevEdge = Edges[Edge->Dst][Edge->RevEdgeIndex];
+ Edge->Flow += Edge->AugmentedFlow;
+ RevEdge.Flow -= Edge->AugmentedFlow;
+ if (Edge->Capacity == Edge->Flow && Edge->AugmentedFlow > 0)
+ HasSaturatedEdges = true;
+ }
+ }
+
+ // The augmentation is successful iff at least one edge becomes saturated
+ return HasSaturatedEdges;
+ }
+
+ /// Identify candidate (shortest) edges for augmentation.
+ void identifyShortestEdges(uint64_t PathCapacity) {
+ assert(PathCapacity > 0 && "found an incorrect augmenting DAG");
+ // To make sure the augmentation DAG contains only edges with large residual
+ // capacity, we prune all edges whose capacity is below a fraction of
+ // the capacity of the augmented path.
+ // (All edges of the path itself are always in the DAG)
+ uint64_t MinCapacity = std::max(PathCapacity / 2, uint64_t(1));
+
+ // Decide which edges are on a shortest path from Source to Target
+ for (size_t Src = 0; Src < Nodes.size(); Src++) {
+ // An edge cannot be augmenting if the endpoint has large distance
+ if (Nodes[Src].Distance > Nodes[Target].Distance)
+ continue;
+
+ for (auto &Edge : Edges[Src]) {
+ uint64_t Dst = Edge.Dst;
+ Edge.OnShortestPath =
+ Src != Target && Dst != Source &&
+ Nodes[Dst].Distance <= Nodes[Target].Distance &&
+ Nodes[Dst].Distance == Nodes[Src].Distance + Edge.Cost &&
+ Edge.Capacity > Edge.Flow &&
+ uint64_t(Edge.Capacity - Edge.Flow) >= MinCapacity;
+ }
+ }
+ }
+
/// A node in a flow network.
struct Node {
/// The cost of the cheapest path from the source to the current node.
@@ -247,7 +511,20 @@ class MinCostMaxFlow {
uint64_t ParentEdgeIndex;
/// An indicator of whether the current node is in a queue.
bool Taken;
+
+ /// Data fields utilized in DAG-augmentation:
+ /// Fractional flow.
+ double FracFlow;
+ /// Integral flow.
+ uint64_t IntFlow;
+ /// Discovery time.
+ uint64_t Discovery;
+ /// Finish time.
+ uint64_t Finish;
+ /// NumCalls.
+ uint64_t NumCalls;
};
+
/// An edge in a flow network.
struct Edge {
/// The cost of the edge.
@@ -260,6 +537,12 @@ class MinCostMaxFlow {
uint64_t Dst;
/// The index of the reverse edge between Dst and the current node.
uint64_t RevEdgeIndex;
+
+ /// Data fields utilized in DAG-augmentation:
+ /// Whether the edge is currently on a shortest path from Source to Target.
+ bool OnShortestPath;
+ /// Extra flow along the edge.
+ uint64_t AugmentedFlow;
};
/// The set of network nodes.
@@ -270,6 +553,8 @@ class MinCostMaxFlow {
uint64_t Source;
/// Target (sink) node of the flow.
uint64_t Target;
+ /// Augmenting edges.
+ std::vector<std::vector<Edge *>> AugmentingEdges;
};
/// A post-processing adjustment of control flow. It applies two steps by
@@ -511,7 +796,7 @@ class FlowAdjuster {
std::vector<FlowBlock *> &KnownDstBlocks,
std::vector<FlowBlock *> &UnknownBlocks) {
// Run BFS from SrcBlock and make sure all paths are going through unknown
- // blocks and end at a non-unknown DstBlock
+ // blocks and end at a known DstBlock
auto Visited = BitVector(NumBlocks(), false);
std::queue<uint64_t> Queue;
diff --git a/llvm/test/Transforms/SampleProfile/Inputs/profile-inference-even-count-distribution.prof b/llvm/test/Transforms/SampleProfile/Inputs/profile-inference-even-count-distribution.prof
new file mode 100644
index 0000000000000..7b9012c0f8dd9
--- /dev/null
+++ b/llvm/test/Transforms/SampleProfile/Inputs/profile-inference-even-count-distribution.prof
@@ -0,0 +1,16 @@
+foo1:37078302:0
+ 1: 1000
+ 2: 0
+ 3: 0
+ 4: 1000
+ !CFGChecksum: 157181141624
+
+foo2:37078302:0
+ 3: 1000
+ !CFGChecksum: 208782362068
+
+foo3:37078302:0
+ 1: 1000
+ 4: 1000
+ 6: 1000
+ !CFGChecksum: 189901498683
diff --git a/llvm/test/Transforms/SampleProfile/csspgo-import-list.ll b/llvm/test/Transforms/SampleProfile/csspgo-import-list.ll
index b797b0031cf9c..0202177da3e0e 100644
--- a/llvm/test/Transforms/SampleProfile/csspgo-import-list.ll
+++ b/llvm/test/Transforms/SampleProfile/csspgo-import-list.ll
@@ -1,19 +1,19 @@
; Make sure Import GUID list for ThinLTO properly set for CSSPGO
-; RUN: opt < %s -passes='thinlto-pre-link<O2>' -pgo-kind=pgo-sample-use-pipeline -sample-profile-file=%S/Inputs/csspgo-import-list.prof -S | FileCheck %s
+; RUN: opt < %s -passes='thinlto-pre-link<O2>' -pgo-kind=pgo-sample-use-pipeline -sample-profile-file=%S/Inputs/csspgo-import-list.prof -sample-profile-even-count-distribution=0 -S | FileCheck %s
; RUN: llvm-profdata merge --sample --extbinary %S/Inputs/csspgo-import-list.prof -o %t.prof
-; RUN: opt < %s -passes='thinlto-pre-link<O2>' -pgo-kind=pgo-sample-use-pipeline -sample-profile-file=%t.prof -S | FileCheck %s
+; RUN: opt < %s -passes='thinlto-pre-link<O2>' -pgo-kind=pgo-sample-use-pipeline -sample-profile-file=%t.prof -sample-profile-even-count-distribution=0 -S | FileCheck %s
; RUN: llvm-profdata show --sample -show-sec-info-only %t.prof | FileCheck %s --check-prefix=CHECK-ORDERED
; RUN: llvm-profdata merge --sample --extbinary --use-md5 %S/Inputs/csspgo-import-list.prof -o %t.md5
-; RUN: opt < %s -passes='thinlto-pre-link<O2>' -pgo-kind=pgo-sample-use-pipeline -sample-profile-file=%t.md5 -S | FileCheck %s
+; RUN: opt < %s -passes='thinlto-pre-link<O2>' -pgo-kind=pgo-sample-use-pipeline -sample-profile-file=%t.md5 -sample-profile-even-count-distribution=0 -S | FileCheck %s
; RUN: llvm-profdata show --sample -show-sec-info-only %t.md5 | FileCheck %s --check-prefix=CHECK-ORDERED
;; Validate that with replay in effect, we import call sites even if they are below the threshold
;; Baseline import decisions
-; RUN: opt < %s -passes='thinlto-pre-link<O2>' -pgo-kind=pgo-sample-use-pipeline -sample-profile-file=%S/Inputs/csspgo-import-list.prof -profile-summary-hot-count=10000 -S | FileCheck %s --check-prefix=THRESHOLD
+; RUN: opt < %s -passes='thinlto-pre-link<O2>' -pgo-kind=pgo-sample-use-pipeline -sample-profile-file=%S/Inputs/csspgo-import-list.prof -profile-summary-hot-count=10000 -sample-profile-even-count-distribution=0 -S | FileCheck %s --check-prefix=THRESHOLD
;; With replay
-; RUN: opt < %s -passes='thinlto-pre-link<O2>' -pgo-kind=pgo-sample-use-pipeline -sample-profile-file=%S/Inputs/csspgo-import-list.prof -sample-profile-inline-replay=%S/Inputs/csspgo-import-list-replay.txt -sample-profile-inline-replay-scope=Module -profile-summary-hot-count=10000 -S | FileCheck %s --check-prefix=THRESHOLD-REPLAY
+; RUN: opt < %s -passes='thinlto-pre-link<O2>' -pgo-kind=pgo-sample-use-pipeline -sample-profile-file=%S/Inputs/csspgo-import-list.prof -sample-profile-inline-replay=%S/Inputs/csspgo-import-list-replay.txt -sample-profile-inline-replay-scope=Module -profile-summary-hot-count=10000 -sample-profile-even-count-distribution=0 -S | FileCheck %s --check-prefix=THRESHOLD-REPLAY
;; With replay but no profile information for call to _Z5funcAi. We import _Z5funcAi because it's explicitly in the replay but don't go further to its callee (_Z3fibi) because we lack samples
-; RUN: opt < %s -passes='thinlto-pre-link<O2>' -pgo-kind=pgo-sample-use-pipeline -sample-profile-file=%S/Inputs/csspgo-import-list-no-funca.prof -sample-profile-inline-replay=%S/Inputs/csspgo-import-list-replay.txt -sample-profile-inline-replay-scope=Module -profile-summary-hot-count=10000 -S | FileCheck %s --check-prefix=THRESHOLD-REPLAY-NO-FUNCA
+; RUN: opt < %s -passes='thinlto-pre-link<O2>' -pgo-kind=pgo-sample-use-pipeline -sample-profile-file=%S/Inputs/csspgo-import-list-no-funca.prof -sample-profile-inline-replay=%S/Inputs/csspgo-import-list-replay.txt -sample-profile-inline-replay-scope=Module -profile-summary-hot-count=10000 -sample-profile-even-count-distribution=0 -S | FileCheck %s --check-prefix=THRESHOLD-REPLAY-NO-FUNCA
declare i32 @_Z5funcBi(i32 %x)
declare i32 @_Z5funcAi(i32 %x)
diff --git a/llvm/test/Transforms/SampleProfile/profile-context-tracker.ll b/llvm/test/Transforms/SampleProfile/profile-context-tracker.ll
index 323f662afcdde..d49e2dc9b5f0e 100644
--- a/llvm/test/Transforms/SampleProfile/profile-context-tracker.ll
+++ b/llvm/test/Transforms/SampleProfile/profile-context-tracker.ll
@@ -8,10 +8,10 @@
; main:3 @ _Z5funcAi
; main:3 @ _Z5funcAi:1 @ _Z8funcLeafi
; _Z5funcBi:1 @ _Z8funcLeafi
-; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/profile-context-tracker.prof -sample-profile-inline-size -sample-profile-prioritized-inline=0 -profile-sample-accurate -S | FileCheck %s --check-prefix=INLINE-ALL
-; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t -sample-profile-inline-size -sample-profile-prioritized-inline=0 -profile-sample-accurate -S | FileCheck %s --check-prefix=INLINE-ALL
-; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/profile-context-tracker.prof -sample-profile-inline-size -sample-profile-cold-inline-threshold=200 -profile-sample-accurate -S | FileCheck %s --check-prefix=INLINE-ALL
-; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t -sample-profile-inline-size -sample-profile-cold-inline-threshold=200 -profile-sample-accurate -S | FileCheck %s --check-prefix=INLINE-ALL
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/profile-context-tracker.prof -sample-profile-inline-size -sample-profile-prioritized-inline=0 -profile-sample-accurate -sample-profile-even-count-distribution=0 -S | FileCheck %s --check-prefix=INLINE-ALL
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t -sample-profile-inline-size -sample-profile-prioritized-inline=0 -profile-sample-accurate -sample-profile-even-count-distribution=0 -S | FileCheck %s --check-prefix=INLINE-ALL
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/profile-context-tracker.prof -sample-profile-inline-size -sample-profile-cold-inline-threshold=200 -profile-sample-accurate -sample-profile-even-count-distribution=0 -S | FileCheck %s --check-prefix=INLINE-ALL
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t -sample-profile-inline-size -sample-profile-cold-inline-threshold=200 -profile-sample-accurate -sample-profile-even-count-distribution=0 -S | FileCheck %s --check-prefix=INLINE-ALL
;
; Test we inlined the following in top-down order and entry counts accurate reflects post-inline base profile
; _Z5funcAi:1 @ _Z8funcLeafi
@@ -145,9 +145,9 @@ entry:
; INLINE-HOT-DAG-SAME: [[LEAF_PROF]] = !{!"function_entry_count", i64 0}
; INLINE-HOT-DAG: [[FUNCB_PROF]] = !{!"function_entry_count", i64 13}
-; INLINE-NONE: [[MAIN_PROF]] = !{!"function_entry_count", i64 1}
+; INLINE-NONE: [[MAIN_PROF]] = !{!"function_entry_count", i64 13}
; INLINE-NONE: [[FUNCA_PROF]] = !{!"function_entry_count", i64 24}
-; INLINE-NONE-DAG-SAME: [[LEAF_PROF]] = !{!"function_entry_count", i64 22}
+; INLINE-NONE-DAG-SAME: [[LEAF_PROF]] = !{!"function_entry_count", i64 21}
; INLINE-NONE-DAG: [[FUNCB_PROF]] = !{!"function_entry_count", i64 32}
declare i32 @_Z3fibi(i32)
diff --git a/llvm/test/Transforms/SampleProfile/profile-inference-even-count-distribution.ll b/llvm/test/Transforms/SampleProfile/profile-inference-even-count-distribution.ll
new file mode 100644
index 0000000000000..baffbc9656df6
--- /dev/null
+++ b/llvm/test/Transforms/SampleProfile/profile-inference-even-count-distribution.ll
@@ -0,0 +1,173 @@
+; RUN: opt < %s -passes=pseudo-probe,sample-profile -sample-profile-use-profi -sample-profile-file=%S/Inputs/profile-inference-even-count-distribution.prof | opt -analyze -branch-prob -enable-new-pm=0 | FileCheck %s
+; RUN: opt < %s -passes=pseudo-probe,sample-profile -sample-profile-use-profi -sample-profile-file=%S/Inputs/profile-inference-even-count-distribution.prof | opt -analyze -block-freq -enable-new-pm=0 | FileCheck %s --check-prefix=CHECK2
+
+; The test verifies that counts are evenly distributed among branches with
+; equal weights.
+;
+; +-----------+ +-----------+
+; | b3 [0] | <-- | b1 [1000] |
+; +-----------+ +-----------+
+; | |
+; | |
+; | v
+; | +-----------+
+; | | b2 [0] |
+; | +-----------+
+; | |
+; | |
+; | v
+; | +-----------+
+; +-------------> | b4 [1000] |
+; +-----------+
+
+ at yydebug = dso_local global i32 0, align 4
+
+; Function Attrs: nounwind uwtable
+define dso_local i32 @foo1(i32 %0, i32 %1) #0 {
+b11:
+ call void @llvm.pseudoprobe(i64 7682762345278052905, i64 1, i32 0, i64 -1)
+ %cmp = icmp ne i32 %0, 0
+ br i1 %cmp, label %b12, label %b13
+; CHECK: edge b11 -> b12 probability is 0x40000000 / 0x80000000 = 50.00%
+; CHECK: edge b11 -> b13 probability is 0x40000000 / 0x80000000 = 50.00%
+; CHECK2: - b11: float = {{.*}}, int = {{.*}}, count = 1000
+
+b12:
+ call void @llvm.pseudoprobe(i64 7682762345278052905, i64 2, i32 0, i64 -1)
+ br label %b14
+; CHECK2: - b12: float = {{.*}}, int = {{.*}}, count = 500
+
+b13:
+ call void @llvm.pseudoprobe(i64 7682762345278052905, i64 3, i32 0, i64 -1)
+ br label %b14
+; CHECK2: - b13: float = {{.*}}, int = {{.*}}, count = 500
+
+b14:
+ call void @llvm.pseudoprobe(i64 7682762345278052905, i64 4, i32 0, i64 -1)
+ ret i32 %1
+; CHECK2: - b14: float = {{.*}}, int = {{.*}}, count = 1000
+}
+
+
+; The test verifies that counts are evenly distributed when the entry basic
+; block is dangling.
+;
+; +-----------+
+; | b1 [?] | -+
+; +-----------+ |
+; | |
+; | |
+; v |
+; +-----------+ |
+; | b2 [?] | |
+; +-----------+ |
+; | |
+; | |
+; v |
+; +-----------+ |
+; | b3 [1000] | <+
+; +-----------+
+
+define dso_local i32 @foo2(i32 %0, i32 %1) #0 {
+b21:
+ call void @llvm.pseudoprobe(i64 2494702099028631698, i64 1, i32 0, i64 -1)
+ %cmp = icmp ne i32 %0, 0
+ br i1 %cmp, label %b22, label %b23
+; CHECK: edge b21 -> b22 probability is 0x40000000 / 0x80000000 = 50.00%
+; CHECK: edge b21 -> b23 probability is 0x40000000 / 0x80000000 = 50.00%
+; CHECK2: - b21: float = {{.*}}, int = {{.*}}, count = 1000
+
+b22:
+ call void @llvm.pseudoprobe(i64 2494702099028631698, i64 2, i32 0, i64 -1)
+ br label %b23
+; CHECK2: - b22: float = {{.*}}, int = {{.*}}, count = 500
+
+b23:
+ call void @llvm.pseudoprobe(i64 2494702099028631698, i64 3, i32 0, i64 -1)
+ ret i32 %1
+; CHECK2: - b23: float = {{.*}}, int = {{.*}}, count = 1000
+
+}
+
+; The test verifies even count distribution in the presence of multiple sinks.
+;
+; +-----------+
+; | b1 [1000] |
+; +-----------+
+; |
+; |
+; v
+; +-----------+
+; | b2 [?] | -+
+; +-----------+ |
+; | |
+; | |
+; v |
+; +--------+ +-----------+ |
+; | b5 [?] | <-- | b3 [?] | |
+; +--------+ +-----------+ |
+; | | |
+; | | |
+; | v |
+; | +-----------+ |
+; | | b4 [1000] | <+
+; | +-----------+
+; | |
+; | |
+; | v
+; | +-----------+
+; +----------> | b6 [1000] |
+; +-----------+
+;
+
+define dso_local i32 @foo3(i32 %0, i32 %1) #0 {
+b31:
+ call void @llvm.pseudoprobe(i64 -7908226060800700466, i64 1, i32 0, i64 -1)
+ %cmp = icmp ne i32 %0, 0
+ br label %b32
+; CHECK2: - b31: float = {{.*}}, int = {{.*}}, count = 1000
+
+b32:
+ call void @llvm.pseudoprobe(i64 -7908226060800700466, i64 2, i32 0, i64 -1)
+ br i1 %cmp, label %b33, label %b34
+; CHECK: edge b32 -> b33 probability is 0x40000000 / 0x80000000 = 50.00%
+; CHECK: edge b32 -> b34 probability is 0x40000000 / 0x80000000 = 50.00%
+; CHECK2: - b32: float = {{.*}}, int = {{.*}}, count = 1000
+
+b33:
+ call void @llvm.pseudoprobe(i64 -7908226060800700466, i64 3, i32 0, i64 -1)
+ br i1 %cmp, label %b35, label %b34
+; CHECK: edge b33 -> b35 probability is 0x00000000 / 0x80000000 = 0.00%
+; CHECK: edge b33 -> b34 probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
+; CHECK2: - b33: float = {{.*}}, int = {{.*}}, count = 500
+
+b34:
+ call void @llvm.pseudoprobe(i64 -7908226060800700466, i64 4, i32 0, i64 -1)
+ br label %b36
+; CHECK2: - b34: float = {{.*}}, int = {{.*}}, count = 1000
+
+b35:
+ call void @llvm.pseudoprobe(i64 -7908226060800700466, i64 5, i32 0, i64 -1)
+ br label %b36
+; CHECK2: - b35: float = {{.*}}, int = {{.*}}, count = 0
+
+b36:
+ call void @llvm.pseudoprobe(i64 -7908226060800700466, i64 6, i32 0, i64 -1)
+ ret i32 %1
+; CHECK2: - b36: float = {{.*}}, int = {{.*}}, count = 1000
+}
+
+
+
+; Function Attrs: inaccessiblememonly nounwind willreturn
+declare void @llvm.pseudoprobe(i64, i64, i32, i64) #4
+
+attributes #0 = { noinline nounwind uwtable "use-sample-profile" }
+attributes #4 = { inaccessiblememonly nounwind willreturn }
+
+!llvm.pseudo_probe_desc = !{!7, !8, !9, !10}
+
+!7 = !{i64 7682762345278052905, i64 157181141624, !"foo1", null}
+!8 = !{i64 2494702099028631698, i64 208782362068, !"foo2", null}
+!9 = !{i64 -7908226060800700466, i64 189901498683, !"foo3", null}
+!10 = !{i64 -6882312132165544686, i64 241030178952, !"foo4", null}
More information about the llvm-commits
mailing list