diff --git a/lib/Control/Distributed/MPI/Packing.hs b/lib/Control/Distributed/MPI/Packing.hs
--- a/lib/Control/Distributed/MPI/Packing.hs
+++ b/lib/Control/Distributed/MPI/Packing.hs
@@ -73,6 +73,8 @@
 
     -- ** Collective (non-blocking)
   , ibarrier
+  , ibcastRecv
+  , ibcastSend
   ) where
 
 import Prelude hiding (init)
@@ -229,8 +231,11 @@
      -> IO ()
 send sendobj sendrank sendtag comm =
   do sendbuf <- serialize sendobj
-     req <- MPI.isend sendbuf sendrank sendtag comm
-     whileM_ (not <$> MPI.test_ req) yield
+     -- Use 'unsafeUseAsCStringLen' to ensure 'sendbuf' is not freed
+     -- too early
+     B.unsafeUseAsCStringLen sendbuf $ \_ ->
+       do req <- MPI.isend sendbuf sendrank sendtag comm
+          whileM_ (not <$> MPI.test_ req) yield
 
 -- | Send and receive objects simultaneously.
 sendrecv :: (CanSerialize a, CanSerialize b)
@@ -326,11 +331,13 @@
   do rank <- MPI.commRank comm
      mpiAssert (rank /= root) "bcastRecv: expected rank /= root"
      lenbuf <- mallocForeignPtr @CLong
-     MPI.bcast (lenbuf, 1::Int) root comm
+     lenreq <- MPI.ibcast (lenbuf, 1::Int) root comm
+     whileM_ (not <$> MPI.test_ lenreq) yield
      len <- withForeignPtr lenbuf peek
      ptr <- mallocBytes (fromIntegral len)
      recvbuf <- B.unsafePackMallocCStringLen (ptr, fromIntegral len)
-     MPI.bcast recvbuf root comm               
+     req <- MPI.ibcast recvbuf root comm               
+     whileM_ (not <$> MPI.test_ req) yield
      recvobj <- deserialize recvbuf
      return recvobj
 
@@ -348,17 +355,42 @@
      sendbuf <- serialize sendobj
      lenbuf <- mallocForeignPtr @CLong
      withForeignPtr lenbuf $ \ptr -> poke ptr (fromIntegral (B.length sendbuf))
-     MPI.bcast (lenbuf, 1::Int) root comm
-     MPI.bcast sendbuf root comm
+     lenreq <- MPI.ibcast (lenbuf, 1::Int) root comm
+     whileM_ (not <$> MPI.test_ lenreq) yield
+     req <- MPI.ibcast sendbuf root comm
+     whileM_ (not <$> MPI.test_ req) yield
 
+ibcastRecv :: CanSerialize a
+           => Rank
+           -> Comm
+           -> IO (Request a)
+ibcastRecv root comm =
+  do result <- newEmptyMVar
+     _ <- forkIO $
+       do recvobj <- bcastRecv root comm
+          putMVar result (Status root MPI.anyTag, recvobj)
+     return (Request result)
+
+ibcastSend :: CanSerialize a
+           => a
+           -> Rank
+           -> Comm
+           -> IO (Request ())
+ibcastSend sendobj root comm =
+  do result <- newEmptyMVar
+     _ <- forkIO $
+       do bcastSend sendobj root comm
+          putMVar result (Status root MPI.anyTag, ())
+     return (Request result)
+
 -- | Begin a barrier. Call 'test' or 'wait' to finish the
 -- communication.
 ibarrier :: Comm
          -> IO (Request ())
 ibarrier comm =
   do result <- newEmptyMVar
-     req <- MPI.ibarrier comm
      _ <- forkIO $
-       do whileM_ (not <$> MPI.test_ req) yield
+       do req <- MPI.ibarrier comm
+          whileM_ (not <$> MPI.test_ req) yield
           putMVar result (Status MPI.anySource MPI.anyTag, ())
      return (Request result)
diff --git a/lib/Control/Distributed/MPI/Store.hs b/lib/Control/Distributed/MPI/Store.hs
--- a/lib/Control/Distributed/MPI/Store.hs
+++ b/lib/Control/Distributed/MPI/Store.hs
@@ -73,6 +73,8 @@
 
     -- ** Collective (non-blocking)
   , ibarrier
+  , ibcastRecv
+  , ibcastSend
   ) where
 
 import Prelude hiding (init)
@@ -227,8 +229,11 @@
      -> IO ()
 send sendobj sendrank sendtag comm =
   do sendbuf <- serialize sendobj
-     req <- MPI.isend sendbuf sendrank sendtag comm
-     whileM_ (not <$> MPI.test_ req) yield
+     -- Use 'unsafeUseAsCStringLen' to ensure 'sendbuf' is not freed
+     -- too early
+     B.unsafeUseAsCStringLen sendbuf $ \_ ->
+       do req <- MPI.isend sendbuf sendrank sendtag comm
+          whileM_ (not <$> MPI.test_ req) yield
 
 -- | Send and receive objects simultaneously.
 sendrecv :: (CanSerialize a, CanSerialize b)
@@ -324,11 +329,13 @@
   do rank <- MPI.commRank comm
      mpiAssert (rank /= root) "bcastRecv: expected rank /= root"
      lenbuf <- mallocForeignPtr @CLong
-     MPI.bcast (lenbuf, 1::Int) root comm
+     lenreq <- MPI.ibcast (lenbuf, 1::Int) root comm
+     whileM_ (not <$> MPI.test_ lenreq) yield
      len <- withForeignPtr lenbuf peek
      ptr <- mallocBytes (fromIntegral len)
      recvbuf <- B.unsafePackMallocCStringLen (ptr, fromIntegral len)
-     MPI.bcast recvbuf root comm               
+     req <- MPI.ibcast recvbuf root comm               
+     whileM_ (not <$> MPI.test_ req) yield
      recvobj <- deserialize recvbuf
      return recvobj
 
@@ -346,17 +353,42 @@
      sendbuf <- serialize sendobj
      lenbuf <- mallocForeignPtr @CLong
      withForeignPtr lenbuf $ \ptr -> poke ptr (fromIntegral (B.length sendbuf))
-     MPI.bcast (lenbuf, 1::Int) root comm
-     MPI.bcast sendbuf root comm
+     lenreq <- MPI.ibcast (lenbuf, 1::Int) root comm
+     whileM_ (not <$> MPI.test_ lenreq) yield
+     req <- MPI.ibcast sendbuf root comm
+     whileM_ (not <$> MPI.test_ req) yield
 
+ibcastRecv :: CanSerialize a
+           => Rank
+           -> Comm
+           -> IO (Request a)
+ibcastRecv root comm =
+  do result <- newEmptyMVar
+     _ <- forkIO $
+       do recvobj <- bcastRecv root comm
+          putMVar result (Status root MPI.anyTag, recvobj)
+     return (Request result)
+
+ibcastSend :: CanSerialize a
+           => a
+           -> Rank
+           -> Comm
+           -> IO (Request ())
+ibcastSend sendobj root comm =
+  do result <- newEmptyMVar
+     _ <- forkIO $
+       do bcastSend sendobj root comm
+          putMVar result (Status root MPI.anyTag, ())
+     return (Request result)
+
 -- | Begin a barrier. Call 'test' or 'wait' to finish the
 -- communication.
 ibarrier :: Comm
          -> IO (Request ())
 ibarrier comm =
   do result <- newEmptyMVar
-     req <- MPI.ibarrier comm
      _ <- forkIO $
-       do whileM_ (not <$> MPI.test_ req) yield
+       do req <- MPI.ibarrier comm
+          whileM_ (not <$> MPI.test_ req) yield
           putMVar result (Status MPI.anySource MPI.anyTag, ())
      return (Request result)
diff --git a/mpi-hs.cabal b/mpi-hs.cabal
--- a/mpi-hs.cabal
+++ b/mpi-hs.cabal
@@ -4,10 +4,10 @@
 --
 -- see: https://github.com/sol/hpack
 --
--- hash: 5c902ab43e71de0472124cd5087d38762a8c74caf1bf2af33a04eb72da015285
+-- hash: 78a9591a1cd036f2ecd9afed2b5c9b1a094791c057255536650d00de3174f23c
 
 name:           mpi-hs
-version:        0.4.0.0
+version:        0.4.1.0
 synopsis:       MPI bindings for Haskell
 description:    MPI (the [Message Passing Interface](https://www.mpi-forum.org)) is
                 widely used standard for distributed-memory programming on HPC (High
diff --git a/package.yaml b/package.yaml
--- a/package.yaml
+++ b/package.yaml
@@ -1,5 +1,5 @@
 name: mpi-hs
-version: '0.4.0.0'
+version: '0.4.1.0'
 github: "eschnett/mpi-hs"
 license: Apache-2.0
 author: "Erik Schnetter <schnetter@gmail.com>"
diff --git a/tests/packing/Main.hs b/tests/packing/Main.hs
--- a/tests/packing/Main.hs
+++ b/tests/packing/Main.hs
@@ -152,4 +152,15 @@
   [ testCase "barrier" $
     do req <- MPI.ibarrier MPI.commWorld
        MPI.wait_ req
+  , testCase "bcast" $
+    do rank <- MPI.commRank MPI.commWorld
+       let sendmsg :: String = "Hello, World!"
+       recvmsg :: String <-
+         if rank == MPI.rootRank
+         then do req <- MPI.ibcastSend sendmsg MPI.rootRank MPI.commWorld
+                 MPI.wait_ req
+                 return sendmsg
+         else do req <- MPI.ibcastRecv MPI.rootRank MPI.commWorld
+                 MPI.wait_ req
+       recvmsg == sendmsg @? ""
   ]
diff --git a/tests/store/Main.hs b/tests/store/Main.hs
--- a/tests/store/Main.hs
+++ b/tests/store/Main.hs
@@ -152,4 +152,15 @@
   [ testCase "barrier" $
     do req <- MPI.ibarrier MPI.commWorld
        MPI.wait_ req
+  , testCase "bcast" $
+    do rank <- MPI.commRank MPI.commWorld
+       let sendmsg :: String = "Hello, World!"
+       recvmsg :: String <-
+         if rank == MPI.rootRank
+         then do req <- MPI.ibcastSend sendmsg MPI.rootRank MPI.commWorld
+                 MPI.wait_ req
+                 return sendmsg
+         else do req <- MPI.ibcastRecv MPI.rootRank MPI.commWorld
+                 MPI.wait_ req
+       recvmsg == sendmsg @? ""
   ]