Index: lib/ProfileData/InstrProfReader.cpp
===================================================================
--- lib/ProfileData/InstrProfReader.cpp
+++ lib/ProfileData/InstrProfReader.cpp
@@ -733,7 +733,7 @@
 }
 
 Error IndexedInstrProfReader::readNextRecord(NamedInstrProfRecord &Record) {
-  static unsigned RecordIndex = 0;
+  thread_local static unsigned RecordIndex = 0;
 
   ArrayRef<NamedInstrProfRecord> Data;
 
Index: test/tools/llvm-profdata/Inputs/multiple-profdata-merge.proftext
===================================================================
--- test/tools/llvm-profdata/Inputs/multiple-profdata-merge.proftext
+++ test/tools/llvm-profdata/Inputs/multiple-profdata-merge.proftext
@@ -0,0 +1,106 @@
+# IR level Instrumentation Flag
+:ir
+foo
+# Func Hash:
+36982789018
+# Num Counters:
+4
+# Counter Values:
+700000
+700000
+0
+0
+
+foo
+# Func Hash:
+59188585735
+# Num Counters:
+6
+# Counter Values:
+400000
+400000
+0
+0
+0
+0
+
+foo
+# Func Hash:
+27904764724
+# Num Counters:
+3
+# Counter Values:
+200000
+200000
+0
+
+foo
+# Func Hash:
+60466382370
+# Num Counters:
+6
+# Counter Values:
+0
+100000
+0
+0
+0
+0
+
+bar
+# Func Hash:
+12884901887
+# Num Counters:
+1
+# Counter Values:
+0
+
+foo2
+# Func Hash:
+12884901887
+# Num Counters:
+1
+# Counter Values:
+0
+
+foo3
+# Func Hash:
+12884901887
+# Num Counters:
+1
+# Counter Values:
+0
+
+foo4
+# Func Hash:
+12884901887
+# Num Counters:
+1
+# Counter Values:
+0
+
+foo5
+# Func Hash:
+12884901887
+# Num Counters:
+1
+# Counter Values:
+0
+
+foo1
+# Func Hash:
+12884901887
+# Num Counters:
+1
+# Counter Values:
+100000
+
+main
+# Func Hash:
+29212902728
+# Num Counters:
+2
+# Counter Values:
+1400000
+14
+
Index: test/tools/llvm-profdata/multiple-profdata-merge.test
===================================================================
--- test/tools/llvm-profdata/multiple-profdata-merge.test
+++ test/tools/llvm-profdata/multiple-profdata-merge.test
@@ -0,0 +1,11 @@
+Test multi-thread merge of multiple profdata files.
+
+RUN: llvm-profdata merge %p/Inputs/multiple-profdata-merge.proftext -o %t
+RUN: llvm-profdata merge -j 4 %t %t %t %t -o %t_2
+RUN: llvm-profdata show %t_2 | FileCheck %s
+
+; CHECK:Total functions: 11
+; CHECK:Maximum function count: 5600000
+; CHECK:Maximum internal block count: 2800000
+
+
Index: tools/llvm-profdata/llvm-profdata.cpp
===================================================================
--- tools/llvm-profdata/llvm-profdata.cpp
+++ tools/llvm-profdata/llvm-profdata.cpp
@@ -227,10 +227,18 @@
     ThreadPool Pool(NumThreads);
 
     // Load the inputs in parallel (N/NumThreads serial steps).
-    unsigned Ctx = 0;
-    for (const auto &Input : Inputs) {
-      Pool.async(loadInput, Input, Contexts[Ctx].get());
-      Ctx = (Ctx + 1) % NumThreads;
+    unsigned ChunkSize = Inputs.size() / NumThreads;
+    unsigned ChunkRemainder = Inputs.size() % NumThreads;
+    for (unsigned Ctx = 0; Ctx < NumThreads; Ctx++) {
+      Pool.async(
+          [&](unsigned Ctx) {
+            for (unsigned I = 0; I < ChunkSize; I++)
+              loadInput(Inputs[Ctx * ChunkSize + I], Contexts[Ctx].get());
+            if (Ctx < ChunkRemainder)
+              loadInput(Inputs[NumThreads * ChunkSize + Ctx],
+                        Contexts[Ctx].get());
+          },
+          Ctx);
     }
     Pool.wait();