russell@unturf.com
a629bd0bbf
New defects (all PASS): - exim-0001: same_hosts() MX-segment O(H²) → AVL set O(H log H), 10.5x at H=20 - minecraft-0001: DependencySorter.isCyclic no visited set O(E^D) → O(E), 342,000x at D=24 - minecraft-0002: PistonStructureResolver toPush ArrayList O(N²) → HashSet O(N) - minecraft-0003: RedstoneWireEvaluator Deque.contains O(N²) → HashSet O(N) - minecraft-0004: MoveThroughVillageGoal visited List O(N²) → HashSet O(N) - mpich-0001: group_lpid_to_rank O(N²) → HashMap O(N), 313x at N=1000 - ompi-0001: group_overlap process-name scan O(N×M) → HashMap O(N+M), 2048x - pcl-0001: RegionGrowing::getSegmentFromPoint O(C×S) → point_labels[] O(1), 50000x CLEAN confirmed: esbuild, express, koa, ktor, lucene, mpich-recvq, ompi-startup, prosody, roda, rust/rustc-wave2, signal-server, solana, wiredtiger, wireguard-tools, linux-kernel (pointer to linux/)
261 lines
10 KiB
Java
261 lines
10 KiB
Java
package unit;
|
||
import java.util.*;
|
||
|
||
/**
|
||
* MpichGroupTest — CWE-407 benchmark for mpich-0001
|
||
*
|
||
* mpich-0001: pmap_lpid_to_rank O(N) linear scan in group set operations
|
||
* SLOW: O(N×M) — pmap_lpid_to_rank linear scan inside outer loop over group1
|
||
* FAST: O(N+M) — HashMap reverse lookup built once from group2, O(1) per query
|
||
*
|
||
* Affected functions (all call pmap_lpid_to_rank inside a loop):
|
||
* - MPIR_Group_difference_impl group_impl.c:330
|
||
* - MPIR_Group_intersection_impl group_impl.c:368
|
||
* - MPIR_Group_union_impl group_impl.c:414
|
||
* - MPIR_Group_translate_ranks_impl group_impl.c:93
|
||
* - MPIR_Group_compare_impl group_impl.c:55
|
||
*
|
||
* The defect is acknowledged by a code comment in grouputil.c:475:
|
||
* "Use linear search for now.
|
||
* Optimization: build hash map in MPIR_Group_create_map and do O(1) hash lookup"
|
||
* and by a TODO in grouputil.c:226:
|
||
* "TODO: build hash to accelerate MPIR_Group_lpid_to_rank"
|
||
*/
|
||
public class MpichGroupTest {
|
||
|
||
// -------------------------------------------------------------------------
|
||
// Benchmark harness
|
||
// -------------------------------------------------------------------------
|
||
|
||
static void bench(String label, Runnable slow, Runnable fast, long sOps, long fOps) {
|
||
// warmup
|
||
slow.run(); fast.run();
|
||
long t0 = System.nanoTime(); slow.run(); long sMs = (System.nanoTime() - t0) / 1_000_000;
|
||
long t1 = System.nanoTime(); fast.run(); long fMs = (System.nanoTime() - t1) / 1_000_000;
|
||
System.out.printf(" %-60s slow:%5dms (%,d ops) fast:%5dms (%,d ops) speedup:%.0fx%n",
|
||
label, sMs, sOps, fMs, fOps, fOps > 0 ? (double) sOps / fOps : 0);
|
||
}
|
||
|
||
// =========================================================================
|
||
// Model
|
||
//
|
||
// An MPI group is modeled as an array of lpids (logical process IDs).
|
||
// map-format groups arise when ranks are not a simple arithmetic progression
|
||
// (MPI_Group_incl with arbitrary rank lists, MPI_Comm_split with gaps, etc.)
|
||
//
|
||
// MPIR_Group_lpid_to_rank scans the map[] array linearly:
|
||
// for (rank = 0; rank < size; rank++)
|
||
// if (map[rank] == lpid) return rank;
|
||
// return MPI_UNDEFINED;
|
||
//
|
||
// This is called from MPIR_Group_difference_impl inside:
|
||
// for (i = 0; i < group1->size; i++)
|
||
// if (MPI_UNDEFINED == MPIR_Group_lpid_to_rank(group2, lpid)) ...
|
||
//
|
||
// Total: O(N × M) comparisons.
|
||
// =========================================================================
|
||
|
||
/** Simulate the current slow MPIR_Group_lpid_to_rank: linear scan */
|
||
static int lpid_to_rank_slow(long[] map, long lpid) {
|
||
for (int rank = 0; rank < map.length; rank++) {
|
||
if (map[rank] == lpid) return rank;
|
||
}
|
||
return -1; // MPI_UNDEFINED
|
||
}
|
||
|
||
/** Simulate the fast version: O(1) HashMap lookup */
|
||
static int lpid_to_rank_fast(Map<Long, Integer> reverseMap, long lpid) {
|
||
return reverseMap.getOrDefault(lpid, -1);
|
||
}
|
||
|
||
// -------------------------------------------------------------------------
|
||
// SLOW: MPIR_Group_difference_impl current behavior — O(N × M)
|
||
// For each lpid in group1, scan all of group2 linearly.
|
||
// -------------------------------------------------------------------------
|
||
|
||
static long groupDifferenceSlow(long[] group1, long[] group2) {
|
||
long ops = 0;
|
||
long[] result = new long[group1.length];
|
||
int nnew = 0;
|
||
for (long lpid : group1) {
|
||
// pmap_lpid_to_rank: linear scan
|
||
boolean found = false;
|
||
for (int r = 0; r < group2.length; r++) {
|
||
ops++;
|
||
if (group2[r] == lpid) { found = true; break; }
|
||
}
|
||
if (!found) result[nnew++] = lpid;
|
||
}
|
||
return ops;
|
||
}
|
||
|
||
// -------------------------------------------------------------------------
|
||
// FAST: MPIR_Group_difference_impl with hash — O(N + M)
|
||
// Build reverse hash of group2 once, then O(1) per group1 element.
|
||
// -------------------------------------------------------------------------
|
||
|
||
static long groupDifferenceFast(long[] group1, long[] group2) {
|
||
long ops = 0;
|
||
// Build hash: O(M)
|
||
Set<Long> group2Set = new HashSet<>(group2.length * 2);
|
||
for (long lpid : group2) {
|
||
group2Set.add(lpid);
|
||
ops++;
|
||
}
|
||
// O(N) lookups
|
||
long[] result = new long[group1.length];
|
||
int nnew = 0;
|
||
for (long lpid : group1) {
|
||
ops++;
|
||
if (!group2Set.contains(lpid)) result[nnew++] = lpid;
|
||
}
|
||
return ops;
|
||
}
|
||
|
||
// -------------------------------------------------------------------------
|
||
// SLOW: MPIR_Group_translate_ranks_impl — O(n_ranks × M)
|
||
// For each of n_ranks ranks in group1, scan all of group2 for the lpid.
|
||
// -------------------------------------------------------------------------
|
||
|
||
static long translateRanksSlow(long[] group1, int[] ranksToTranslate, long[] group2) {
|
||
long ops = 0;
|
||
int[] result = new int[ranksToTranslate.length];
|
||
for (int i = 0; i < ranksToTranslate.length; i++) {
|
||
long lpid = group1[ranksToTranslate[i]];
|
||
// linear scan of group2
|
||
result[i] = -1;
|
||
for (int r = 0; r < group2.length; r++) {
|
||
ops++;
|
||
if (group2[r] == lpid) { result[i] = r; break; }
|
||
}
|
||
}
|
||
return ops;
|
||
}
|
||
|
||
// -------------------------------------------------------------------------
|
||
// FAST: MPIR_Group_translate_ranks_impl with hash — O(n_ranks + M)
|
||
// -------------------------------------------------------------------------
|
||
|
||
static long translateRanksFast(long[] group1, int[] ranksToTranslate, long[] group2) {
|
||
long ops = 0;
|
||
// Build reverse map of group2: lpid -> rank
|
||
Map<Long, Integer> revMap = new HashMap<>(group2.length * 2);
|
||
for (int r = 0; r < group2.length; r++) {
|
||
revMap.put(group2[r], r);
|
||
ops++;
|
||
}
|
||
int[] result = new int[ranksToTranslate.length];
|
||
for (int i = 0; i < ranksToTranslate.length; i++) {
|
||
long lpid = group1[ranksToTranslate[i]];
|
||
ops++;
|
||
result[i] = revMap.getOrDefault(lpid, -1);
|
||
}
|
||
return ops;
|
||
}
|
||
|
||
// =========================================================================
|
||
// Test cases
|
||
// =========================================================================
|
||
|
||
static boolean PASS = true;
|
||
|
||
static void assertCorrect(String test, long[] group1, long[] group2) {
|
||
// Verify slow and fast produce the same result set for group difference
|
||
Set<Long> slowResult = new HashSet<>();
|
||
Set<Long> g2Set = new HashSet<>();
|
||
for (long x : group2) g2Set.add(x);
|
||
for (long lpid : group1) {
|
||
boolean found = false;
|
||
for (long x : group2) if (x == lpid) { found = true; break; }
|
||
if (!found) slowResult.add(lpid);
|
||
}
|
||
Set<Long> fastResult = new HashSet<>();
|
||
for (long lpid : group1) {
|
||
if (!g2Set.contains(lpid)) fastResult.add(lpid);
|
||
}
|
||
boolean ok = slowResult.equals(fastResult);
|
||
System.out.printf(" CORRECTNESS %-40s %s%n", test, ok ? "PASS" : "FAIL");
|
||
if (!ok) PASS = false;
|
||
}
|
||
|
||
// =========================================================================
|
||
// Main
|
||
// =========================================================================
|
||
|
||
public static void main(String[] args) {
|
||
System.out.println("=== mpich-0001: pmap_lpid_to_rank O(N) linear scan in group ops ===");
|
||
System.out.println();
|
||
|
||
// --- Correctness tests ---
|
||
System.out.println("--- Correctness ---");
|
||
|
||
// Basic difference: group1 = {0..9}, group2 = {5..14}, diff = {0..4}
|
||
long[] g1 = new long[10], g2 = new long[10];
|
||
for (int i = 0; i < 10; i++) { g1[i] = i; g2[i] = i + 5; }
|
||
assertCorrect("difference {0..9} \\ {5..14} = {0..4}", g1, g2);
|
||
|
||
// Intersection via complement: group1 = {0,2,4,6,8}, group2 = {1,2,3,4,5}
|
||
long[] ga = {0, 2, 4, 6, 8}, gb = {1, 2, 3, 4, 5};
|
||
assertCorrect("difference {even 0-8} \\ {1-5}", ga, gb);
|
||
|
||
// Disjoint groups
|
||
long[] gc = {0, 1, 2}, gd = {10, 11, 12};
|
||
assertCorrect("disjoint groups: diff = group1", gc, gd);
|
||
|
||
// Identical groups
|
||
long[] ge = {5, 3, 7, 1}, gf = {5, 3, 7, 1};
|
||
assertCorrect("identical groups: diff = empty", ge, gf);
|
||
|
||
System.out.println();
|
||
|
||
// --- Performance benchmarks ---
|
||
System.out.println("--- Performance (group_difference, group_translate_ranks) ---");
|
||
|
||
int[] sizes = {100, 500, 1000};
|
||
for (int N : sizes) {
|
||
// Create two groups with partial overlap: group1 = 0..N-1, group2 = N/2..3N/2-1
|
||
final long[] grp1 = new long[N], grp2 = new long[N];
|
||
for (int i = 0; i < N; i++) { grp1[i] = i; grp2[i] = i + N / 2; }
|
||
|
||
final long[] slowOps = {0}, fastOps = {0};
|
||
bench(
|
||
String.format("group_difference N=%d", N),
|
||
() -> slowOps[0] = groupDifferenceSlow(grp1, grp2),
|
||
() -> fastOps[0] = groupDifferenceFast(grp1, grp2),
|
||
slowOps[0], fastOps[0]
|
||
);
|
||
|
||
// translate_ranks: translate all N ranks
|
||
int[] allRanks = new int[N];
|
||
for (int i = 0; i < N; i++) allRanks[i] = i;
|
||
bench(
|
||
String.format("translate_ranks N=%d", N),
|
||
() -> slowOps[0] = translateRanksSlow(grp1, allRanks, grp2),
|
||
() -> fastOps[0] = translateRanksFast(grp1, allRanks, grp2),
|
||
slowOps[0], fastOps[0]
|
||
);
|
||
}
|
||
|
||
// Large scale
|
||
{
|
||
final int N = 4096;
|
||
final long[] grp1 = new long[N], grp2 = new long[N];
|
||
for (int i = 0; i < N; i++) {
|
||
// Non-strided (map format) with partial overlap
|
||
grp1[i] = (long) i * 3;
|
||
grp2[i] = (long) i * 3 + 1;
|
||
}
|
||
final long[] slowOps = {0}, fastOps = {0};
|
||
bench(
|
||
String.format("group_difference N=%d (non-strided)", N),
|
||
() -> slowOps[0] = groupDifferenceSlow(grp1, grp2),
|
||
() -> fastOps[0] = groupDifferenceFast(grp1, grp2),
|
||
slowOps[0], fastOps[0]
|
||
);
|
||
}
|
||
|
||
System.out.println();
|
||
System.out.println("Result: " + (PASS ? "PASS" : "FAIL"));
|
||
if (!PASS) System.exit(1);
|
||
}
|
||
}
|