diff --git a/flate/deflate.go b/flate/deflate.go
index 96c5b8bec6..86f4fd0371 100644
--- a/flate/deflate.go
+++ b/flate/deflate.go
@@ -132,8 +132,7 @@ func (d *compressor) fillDeflate(b []byte) int {
 	s := d.state
 	if s.index >= 2*windowSize-(minMatchLength+maxMatchLength) {
 		// shift the window by windowSize
-		//copy(d.window[:], d.window[windowSize:2*windowSize])
-		*(*[windowSize]byte)(d.window) = *(*[windowSize]byte)(d.window[windowSize:])
+		copy(d.window[:], d.window[windowSize:2*windowSize])
 		s.index -= windowSize
 		d.windowEnd -= windowSize
 		if d.blockStart >= windowSize {
diff --git a/flate/fast_encoder.go b/flate/fast_encoder.go
index 152229afd5..95d3ef996e 100644
--- a/flate/fast_encoder.go
+++ b/flate/fast_encoder.go
@@ -90,8 +90,7 @@ func (e *fastGen) addBlock(src []byte) int32 {
 			}
 			// Move down
 			offset := int32(len(e.hist)) - maxMatchOffset
-			// copy(e.hist[0:maxMatchOffset], e.hist[offset:])
-			*(*[maxMatchOffset]byte)(e.hist) = *(*[maxMatchOffset]byte)(e.hist[offset:])
+			copy(e.hist[0:maxMatchOffset], e.hist[offset:])
 			e.cur += offset
 			e.hist = e.hist[:maxMatchOffset]
 		}
diff --git a/flate/huffman_bit_writer.go b/flate/huffman_bit_writer.go
index 34b091af09..2bccd8e8eb 100644
--- a/flate/huffman_bit_writer.go
+++ b/flate/huffman_bit_writer.go
@@ -791,11 +791,9 @@ func (w *huffmanBitWriter) fillTokens() {
 // and offsetEncoding.
 // The number of literal and offset tokens is returned.
 func (w *huffmanBitWriter) indexTokens(t *tokens, filled bool) (numLiterals, numOffsets int) {
-	//copy(w.literalFreq[:], t.litHist[:])
-	*(*[256]uint16)(w.literalFreq[:]) = t.litHist
-	//copy(w.literalFreq[256:], t.extraHist[:])
-	*(*[32]uint16)(w.literalFreq[256:]) = t.extraHist
-	w.offsetFreq = t.offHist
+	copy(w.literalFreq[:], t.litHist[:])
+	copy(w.literalFreq[256:], t.extraHist[:])
+	copy(w.offsetFreq[:], t.offHist[:offsetCodeCount])
 
 	if t.n == 0 {
 		return
diff --git a/huff0/decompress.go b/huff0/decompress.go
index 42a237eac4..c0c48bd707 100644
--- a/huff0/decompress.go
+++ b/huff0/decompress.go
@@ -763,20 +763,17 @@ func (d *Decoder) decompress4X8bit(dst, src []byte) ([]byte, error) {
 				d.bufs.Put(buf)
 				return nil, errors.New("corruption detected: stream overrun 1")
 			}
+			copy(out, buf[0][:])
+			copy(out[dstEvery:], buf[1][:])
+			copy(out[dstEvery*2:], buf[2][:])
+			copy(out[dstEvery*3:], buf[3][:])
+			out = out[bufoff:]
+			decoded += bufoff * 4
 			// There must at least be 3 buffers left.
-			if len(out)-bufoff < dstEvery*3 {
+			if len(out) < dstEvery*3 {
 				d.bufs.Put(buf)
 				return nil, errors.New("corruption detected: stream overrun 2")
 			}
-			//copy(out, buf[0][:])
-			//copy(out[dstEvery:], buf[1][:])
-			//copy(out[dstEvery*2:], buf[2][:])
-			*(*[bufoff]byte)(out) = buf[0]
-			*(*[bufoff]byte)(out[dstEvery:]) = buf[1]
-			*(*[bufoff]byte)(out[dstEvery*2:]) = buf[2]
-			*(*[bufoff]byte)(out[dstEvery*3:]) = buf[3]
-			out = out[bufoff:]
-			decoded += bufoff * 4
 		}
 	}
 	if off > 0 {
@@ -1000,22 +997,17 @@ func (d *Decoder) decompress4X8bitExactly(dst, src []byte) ([]byte, error) {
 				d.bufs.Put(buf)
 				return nil, errors.New("corruption detected: stream overrun 1")
 			}
+			copy(out, buf[0][:])
+			copy(out[dstEvery:], buf[1][:])
+			copy(out[dstEvery*2:], buf[2][:])
+			copy(out[dstEvery*3:], buf[3][:])
+			out = out[bufoff:]
+			decoded += bufoff * 4
 			// There must at least be 3 buffers left.
-			if len(out)-bufoff < dstEvery*3 {
+			if len(out) < dstEvery*3 {
 				d.bufs.Put(buf)
 				return nil, errors.New("corruption detected: stream overrun 2")
 			}
-
-			//copy(out, buf[0][:])
-			//copy(out[dstEvery:], buf[1][:])
-			//copy(out[dstEvery*2:], buf[2][:])
-			// copy(out[dstEvery*3:], buf[3][:])
-			*(*[bufoff]byte)(out) = buf[0]
-			*(*[bufoff]byte)(out[dstEvery:]) = buf[1]
-			*(*[bufoff]byte)(out[dstEvery*2:]) = buf[2]
-			*(*[bufoff]byte)(out[dstEvery*3:]) = buf[3]
-			out = out[bufoff:]
-			decoded += bufoff * 4
 		}
 	}
 	if off > 0 {
diff --git a/huff0/decompress_generic.go b/huff0/decompress_generic.go
index 908c17de63..4f6f37cb2c 100644
--- a/huff0/decompress_generic.go
+++ b/huff0/decompress_generic.go
@@ -122,21 +122,17 @@ func (d *Decoder) Decompress4X(dst, src []byte) ([]byte, error) {
 				d.bufs.Put(buf)
 				return nil, errors.New("corruption detected: stream overrun 1")
 			}
+			copy(out, buf[0][:])
+			copy(out[dstEvery:], buf[1][:])
+			copy(out[dstEvery*2:], buf[2][:])
+			copy(out[dstEvery*3:], buf[3][:])
+			out = out[bufoff:]
+			decoded += bufoff * 4
 			// There must at least be 3 buffers left.
-			if len(out)-bufoff < dstEvery*3 {
+			if len(out) < dstEvery*3 {
 				d.bufs.Put(buf)
 				return nil, errors.New("corruption detected: stream overrun 2")
 			}
-			//copy(out, buf[0][:])
-			//copy(out[dstEvery:], buf[1][:])
-			//copy(out[dstEvery*2:], buf[2][:])
-			//copy(out[dstEvery*3:], buf[3][:])
-			*(*[bufoff]byte)(out) = buf[0]
-			*(*[bufoff]byte)(out[dstEvery:]) = buf[1]
-			*(*[bufoff]byte)(out[dstEvery*2:]) = buf[2]
-			*(*[bufoff]byte)(out[dstEvery*3:]) = buf[3]
-			out = out[bufoff:]
-			decoded += bufoff * 4
 		}
 	}
 	if off > 0 {
diff --git a/s2c b/s2c
deleted file mode 100755
index 93b2942154..0000000000
Binary files a/s2c and /dev/null differ
diff --git a/zstd/enc_dfast.go b/zstd/enc_dfast.go
index 7d425109ad..a5158fc8fc 100644
--- a/zstd/enc_dfast.go
+++ b/zstd/enc_dfast.go
@@ -1099,8 +1099,7 @@ func (e *doubleFastEncoderDict) Reset(d *dict, singleBlock bool) {
 	}
 
 	if allDirty || dirtyShardCnt > dLongTableShardCnt/2 {
-		//copy(e.longTable[:], e.dictLongTable)
-		e.longTable = *(*[dFastLongTableSize]tableEntry)(e.dictLongTable)
+		copy(e.longTable[:], e.dictLongTable)
 		for i := range e.longTableShardDirty {
 			e.longTableShardDirty[i] = false
 		}
@@ -1111,9 +1110,7 @@ func (e *doubleFastEncoderDict) Reset(d *dict, singleBlock bool) {
 			continue
 		}
 
-		// copy(e.longTable[i*dLongTableShardSize:(i+1)*dLongTableShardSize], e.dictLongTable[i*dLongTableShardSize:(i+1)*dLongTableShardSize])
-		*(*[dLongTableShardSize]tableEntry)(e.longTable[i*dLongTableShardSize:]) = *(*[dLongTableShardSize]tableEntry)(e.dictLongTable[i*dLongTableShardSize:])
-
+		copy(e.longTable[i*dLongTableShardSize:(i+1)*dLongTableShardSize], e.dictLongTable[i*dLongTableShardSize:(i+1)*dLongTableShardSize])
 		e.longTableShardDirty[i] = false
 	}
 }
diff --git a/zstd/enc_fast.go b/zstd/enc_fast.go
index 315b1a8f2f..6bae3bb449 100644
--- a/zstd/enc_fast.go
+++ b/zstd/enc_fast.go
@@ -869,8 +869,7 @@ func (e *fastEncoderDict) Reset(d *dict, singleBlock bool) {
 	const shardCnt = tableShardCnt
 	const shardSize = tableShardSize
 	if e.allDirty || dirtyShardCnt > shardCnt*4/6 {
-		//copy(e.table[:], e.dictTable)
-		e.table = *(*[tableSize]tableEntry)(e.dictTable)
+		copy(e.table[:], e.dictTable)
 		for i := range e.tableShardDirty {
 			e.tableShardDirty[i] = false
 		}
@@ -882,8 +881,7 @@ func (e *fastEncoderDict) Reset(d *dict, singleBlock bool) {
 			continue
 		}
 
-		//copy(e.table[i*shardSize:(i+1)*shardSize], e.dictTable[i*shardSize:(i+1)*shardSize])
-		*(*[shardSize]tableEntry)(e.table[i*shardSize:]) = *(*[shardSize]tableEntry)(e.dictTable[i*shardSize:])
+		copy(e.table[i*shardSize:(i+1)*shardSize], e.dictTable[i*shardSize:(i+1)*shardSize])
 		e.tableShardDirty[i] = false
 	}
 	e.allDirty = false