New primops for byte range copies ByteArray# <-> Addr#

We have primops for copying ranges of bytes between ByteArray#s:
 * ByteArray# -> MutableByteArray#
 * MutableByteArray# -> MutableByteArray#
This extends it with three further cases:
 * Addr# -> MutableByteArray#
 * ByteArray# -> Addr#
 * MutableByteArray# -> Addr#
One use case for these is copying between ForeignPtr-based
representations and in-heap arrays (like Text, UArray etc).

The implementation is essentially the same as for the existing
primops, and shares the memcpy stuff in the code generators.

Defficiencies / future directions: none of these primops (existing
or the new ones) let one take advantage of knowing that ByteArray#s
are word-aligned in memory. Though it is unclear that any of the
code generators would make use of this information unless the size
to copy is also known at compile time.

Signed-off-by: Austin Seipp <austin@well-typed.com>

2 files changed, 70 insertions, 0 deletions

diff --git a/compiler/codeGen/StgCmmPrim.hs b/compiler/codeGen/StgCmmPrim.hs
index bb58024a4e..8560f7cf1c 100644
--- a/compiler/codeGen/StgCmmPrim.hs
+++ b/compiler/codeGen/StgCmmPrim.hs
@@ -529,6 +529,12 @@ emitPrimOp _      [] CopyByteArrayOp [src,src_off,dst,dst_off,n] =
     doCopyByteArrayOp src src_off dst dst_off n
 emitPrimOp _      [] CopyMutableByteArrayOp [src,src_off,dst,dst_off,n] =
     doCopyMutableByteArrayOp src src_off dst dst_off n
+emitPrimOp _      [] CopyByteArrayToAddrOp [src,src_off,dst,n] =
+    doCopyByteArrayToAddrOp src src_off dst n
+emitPrimOp _      [] CopyMutableByteArrayToAddrOp [src,src_off,dst,n] =
+    doCopyMutableByteArrayToAddrOp src src_off dst n
+emitPrimOp _      [] CopyAddrToByteArrayOp [src,dst,dst_off,n] =
+    doCopyAddrToByteArrayOp src dst dst_off n
 emitPrimOp _      [] SetByteArrayOp [ba,off,len,c] =
     doSetByteArrayOp ba off len c
 
@@ -1358,6 +1364,34 @@ emitCopyByteArray copy src src_off dst dst_off n = do
     src_p <- assignTempE $ cmmOffsetExpr dflags (cmmOffsetB dflags src (arrWordsHdrSize dflags)) src_off
     copy src dst dst_p src_p n
 
+-- | Takes a source 'ByteArray#', an offset in the source array, a
+-- destination 'Addr#', and the number of bytes to copy.  Copies the given
+-- number of bytes from the source array to the destination memory region.
+doCopyByteArrayToAddrOp :: CmmExpr -> CmmExpr -> CmmExpr -> CmmExpr -> FCode ()
+doCopyByteArrayToAddrOp src src_off dst_p bytes = do
+    -- Use memcpy (we are allowed to assume the arrays aren't overlapping)
+    dflags <- getDynFlags
+    src_p <- assignTempE $ cmmOffsetExpr dflags (cmmOffsetB dflags src (arrWordsHdrSize dflags)) src_off
+    emitMemcpyCall dst_p src_p bytes (mkIntExpr dflags 1)
+
+-- | Takes a source 'MutableByteArray#', an offset in the source array, a
+-- destination 'Addr#', and the number of bytes to copy.  Copies the given
+-- number of bytes from the source array to the destination memory region.
+doCopyMutableByteArrayToAddrOp :: CmmExpr -> CmmExpr -> CmmExpr -> CmmExpr
+                               -> FCode ()
+doCopyMutableByteArrayToAddrOp = doCopyByteArrayToAddrOp
+
+-- | Takes a source 'Addr#', a destination 'MutableByteArray#', an offset into
+-- the destination array, and the number of bytes to copy.  Copies the given
+-- number of bytes from the source memory region to the destination array.
+doCopyAddrToByteArrayOp :: CmmExpr -> CmmExpr -> CmmExpr -> CmmExpr -> FCode ()
+doCopyAddrToByteArrayOp src_p dst dst_off bytes = do
+    -- Use memcpy (we are allowed to assume the arrays aren't overlapping)
+    dflags <- getDynFlags
+    dst_p <- assignTempE $ cmmOffsetExpr dflags (cmmOffsetB dflags dst (arrWordsHdrSize dflags)) dst_off
+    emitMemcpyCall dst_p src_p bytes (mkIntExpr dflags 1)
+
+
 -- ----------------------------------------------------------------------------
 -- Setting byte arrays
 
diff --git a/compiler/prelude/primops.txt.pp b/compiler/prelude/primops.txt.pp
index a59dfd624d..71dea22c4f 100644
--- a/compiler/prelude/primops.txt.pp
+++ b/compiler/prelude/primops.txt.pp
@@ -1110,6 +1110,42 @@ primop  CopyMutableByteArrayOp "copyMutableByteArray#" GenPrimOp
   code_size = { primOpCodeSizeForeignCall + 4 }
   can_fail = True
 
+primop  CopyByteArrayToAddrOp "copyByteArrayToAddr#" GenPrimOp
+  ByteArray# -> Int# -> Addr# -> Int# -> State# RealWorld -> State# RealWorld
+  {Copy a range of the ByteArray# to the memory range starting at the Addr#.
+   The ByteArray# and the memory region at Addr# must fully contain the
+   specified ranges, but this is not checked. The Addr# must not point into the
+   ByteArray# (e.g. if the ByteArray# were pinned), but this is not checked
+   either.}
+  with
+  has_side_effects = True
+  code_size = { primOpCodeSizeForeignCall + 4}
+  can_fail = True
+
+primop  CopyMutableByteArrayToAddrOp "copyMutableByteArrayToAddr#" GenPrimOp
+  MutableByteArray# RealWorld -> Int# -> Addr# -> Int# -> State# RealWorld -> State# RealWorld
+  {Copy a range of the MutableByteArray# to the memory range starting at the
+   Addr#. The MutableByteArray# and the memory region at Addr# must fully
+   contain the specified ranges, but this is not checked. The Addr# must not
+   point into the MutableByteArray# (e.g. if the MutableByteArray# were
+   pinned), but this is not checked either.}
+  with
+  has_side_effects = True
+  code_size = { primOpCodeSizeForeignCall + 4}
+  can_fail = True
+
+primop  CopyAddrToByteArrayOp "copyAddrToByteArray#" GenPrimOp
+  Addr# -> MutableByteArray# s -> Int# -> Int# -> State# RealWorld -> State# RealWorld
+  {Copy a memory range starting at the Addr# to the specified range in the
+   MutableByteArray#. The memory region at Addr# and the ByteArray# must fully
+   contain the specified ranges, but this is not checked. The Addr# must not
+   point into the MutableByteArray# (e.g. if the MutableByteArray# were pinned),
+   but this is not checked either.}
+  with
+  has_side_effects = True
+  code_size = { primOpCodeSizeForeignCall + 4}
+  can_fail = True
+
 primop  SetByteArrayOp "setByteArray#" GenPrimOp
   MutableByteArray# s -> Int# -> Int# -> Int# -> State# s -> State# s
   {Set the range of the MutableByteArray# to the specified character.}