cmd/compile: optimize make+copy pattern to avoid memclr

match:
 m = make([]T, x); copy(m, s)
for pointer free T and x==len(s) rewrite to:
 m = mallocgc(x*elemsize(T), nil, false); memmove(&m, &s, x*elemsize(T))
otherwise rewrite to:
 m = makeslicecopy([]T, x, s)

This avoids memclear and shading of pointers in the newly created slice
before the copy.

With this CL "s" is only be allowed to bev a variable and not a more
complex expression. This restriction could be lifted in future versions
of this optimization when it can be proven that "s" is not referencing "m".

Triggers 450 times during make.bash..
Reduces go binary size by ~8 kbyte.

name                           old time/op  new time/op  delta
MakeSliceCopy/mallocmove/Byte  71.1ns ± 1%  65.8ns ± 0%  -7.49%  (p=0.000 n=10+9)
MakeSliceCopy/mallocmove/Int   71.2ns ± 1%  66.0ns ± 0%  -7.27%  (p=0.000 n=10+8)
MakeSliceCopy/mallocmove/Ptr    104ns ± 4%    99ns ± 1%  -5.13%  (p=0.000 n=10+10)
MakeSliceCopy/makecopy/Byte    70.3ns ± 0%  68.0ns ± 0%  -3.22%  (p=0.000 n=10+9)
MakeSliceCopy/makecopy/Int     70.3ns ± 0%  68.5ns ± 1%  -2.59%  (p=0.000 n=9+10)
MakeSliceCopy/makecopy/Ptr      102ns ± 0%    99ns ± 1%  -2.97%  (p=0.000 n=9+9)
MakeSliceCopy/nilappend/Byte   75.4ns ± 0%  74.9ns ± 2%  -0.63%  (p=0.015 n=9+9)
MakeSliceCopy/nilappend/Int    75.6ns ± 0%  76.4ns ± 3%    ~     (p=0.245 n=9+10)
MakeSliceCopy/nilappend/Ptr     107ns ± 0%   108ns ± 1%  +0.93%  (p=0.005 n=9+10)

Fixes #26252

Change-Id: Iec553dd1fef6ded16197216a472351c8799a8e71
Reviewed-on: https://go-review.googlesource.com/c/go/+/146719
Reviewed-by: Keith Randall <[email protected]>
Run-TryBot: Martin Möhrmann <[email protected]>
TryBot-Result: Gobot Gobot <[email protected]>

Author: martisch

src/cmd/compile/internal/gc/builtin.go

@@ -15,6 +15,7 @@ package runtime
 import "unsafe"
 
 func newobject(typ *byte) *any
+func mallocgc(size uintptr, typ *byte, needszero bool) unsafe.Pointer
 func panicdivide()
 func panicshift()
 func panicmakeslicelen()
@@ -174,6 +175,7 @@ func block()
 
 func makeslice(typ *byte, len int, cap int) unsafe.Pointer
 func makeslice64(typ *byte, len int64, cap int64) unsafe.Pointer
+func makeslicecopy(typ *byte, tolen int, fromlen int, from unsafe.Pointer) unsafe.Pointer
 func growslice(typ *byte, old []any, cap int) (ary []any)
 func memmove(to *any, frm *any, length uintptr)
 func memclrNoHeapPointers(ptr unsafe.Pointer, n uintptr)

src/cmd/compile/internal/gc/builtin/runtime.go

@@ -1165,92 +1165,93 @@ func (n *Node) stmtfmt(s fmt.State, mode fmtMode) {
 }
 
 var opprec = []int{
-	OALIGNOF:     8,
-	OAPPEND:      8,
-	OBYTES2STR:   8,
-	OARRAYLIT:    8,
-	OSLICELIT:    8,
-	ORUNES2STR:   8,
-	OCALLFUNC:    8,
-	OCALLINTER:   8,
-	OCALLMETH:    8,
-	OCALL:        8,
-	OCAP:         8,
-	OCLOSE:       8,
-	OCONVIFACE:   8,
-	OCONVNOP:     8,
-	OCONV:        8,
-	OCOPY:        8,
-	ODELETE:      8,
-	OGETG:        8,
-	OLEN:         8,
-	OLITERAL:     8,
-	OMAKESLICE:   8,
-	OMAKE:        8,
-	OMAPLIT:      8,
-	ONAME:        8,
-	ONEW:         8,
-	ONONAME:      8,
-	OOFFSETOF:    8,
-	OPACK:        8,
-	OPANIC:       8,
-	OPAREN:       8,
-	OPRINTN:      8,
-	OPRINT:       8,
-	ORUNESTR:     8,
-	OSIZEOF:      8,
-	OSTR2BYTES:   8,
-	OSTR2RUNES:   8,
-	OSTRUCTLIT:   8,
-	OTARRAY:      8,
-	OTCHAN:       8,
-	OTFUNC:       8,
-	OTINTER:      8,
-	OTMAP:        8,
-	OTSTRUCT:     8,
-	OINDEXMAP:    8,
-	OINDEX:       8,
-	OSLICE:       8,
-	OSLICESTR:    8,
-	OSLICEARR:    8,
-	OSLICE3:      8,
-	OSLICE3ARR:   8,
-	OSLICEHEADER: 8,
-	ODOTINTER:    8,
-	ODOTMETH:     8,
-	ODOTPTR:      8,
-	ODOTTYPE2:    8,
-	ODOTTYPE:     8,
-	ODOT:         8,
-	OXDOT:        8,
-	OCALLPART:    8,
-	OPLUS:        7,
-	ONOT:         7,
-	OBITNOT:      7,
-	ONEG:         7,
-	OADDR:        7,
-	ODEREF:       7,
-	ORECV:        7,
-	OMUL:         6,
-	ODIV:         6,
-	OMOD:         6,
-	OLSH:         6,
-	ORSH:         6,
-	OAND:         6,
-	OANDNOT:      6,
-	OADD:         5,
-	OSUB:         5,
-	OOR:          5,
-	OXOR:         5,
-	OEQ:          4,
-	OLT:          4,
-	OLE:          4,
-	OGE:          4,
-	OGT:          4,
-	ONE:          4,
-	OSEND:        3,
-	OANDAND:      2,
-	OOROR:        1,
+	OALIGNOF:       8,
+	OAPPEND:        8,
+	OBYTES2STR:     8,
+	OARRAYLIT:      8,
+	OSLICELIT:      8,
+	ORUNES2STR:     8,
+	OCALLFUNC:      8,
+	OCALLINTER:     8,
+	OCALLMETH:      8,
+	OCALL:          8,
+	OCAP:           8,
+	OCLOSE:         8,
+	OCONVIFACE:     8,
+	OCONVNOP:       8,
+	OCONV:          8,
+	OCOPY:          8,
+	ODELETE:        8,
+	OGETG:          8,
+	OLEN:           8,
+	OLITERAL:       8,
+	OMAKESLICE:     8,
+	OMAKESLICECOPY: 8,
+	OMAKE:          8,
+	OMAPLIT:        8,
+	ONAME:          8,
+	ONEW:           8,
+	ONONAME:        8,
+	OOFFSETOF:      8,
+	OPACK:          8,
+	OPANIC:         8,
+	OPAREN:         8,
+	OPRINTN:        8,
+	OPRINT:         8,
+	ORUNESTR:       8,
+	OSIZEOF:        8,
+	OSTR2BYTES:     8,
+	OSTR2RUNES:     8,
+	OSTRUCTLIT:     8,
+	OTARRAY:        8,
+	OTCHAN:         8,
+	OTFUNC:         8,
+	OTINTER:        8,
+	OTMAP:          8,
+	OTSTRUCT:       8,
+	OINDEXMAP:      8,
+	OINDEX:         8,
+	OSLICE:         8,
+	OSLICESTR:      8,
+	OSLICEARR:      8,
+	OSLICE3:        8,
+	OSLICE3ARR:     8,
+	OSLICEHEADER:   8,
+	ODOTINTER:      8,
+	ODOTMETH:       8,
+	ODOTPTR:        8,
+	ODOTTYPE2:      8,
+	ODOTTYPE:       8,
+	ODOT:           8,
+	OXDOT:          8,
+	OCALLPART:      8,
+	OPLUS:          7,
+	ONOT:           7,
+	OBITNOT:        7,
+	ONEG:           7,
+	OADDR:          7,
+	ODEREF:         7,
+	ORECV:          7,
+	OMUL:           6,
+	ODIV:           6,
+	OMOD:           6,
+	OLSH:           6,
+	ORSH:           6,
+	OAND:           6,
+	OANDNOT:        6,
+	OADD:           5,
+	OSUB:           5,
+	OOR:            5,
+	OXOR:           5,
+	OEQ:            4,
+	OLT:            4,
+	OLE:            4,
+	OGE:            4,
+	OGT:            4,
+	ONE:            4,
+	OSEND:          3,
+	OANDAND:        2,
+	OOROR:          1,
 
 	// Statements handled by stmtfmt
 	OAS:         -1,
@@ -1572,6 +1573,9 @@ func (n *Node) exprfmt(s fmt.State, prec int, mode fmtMode) {
 		}
 		mode.Fprintf(s, "make(%v)", n.Type)
 
+	case OMAKESLICECOPY:
+		mode.Fprintf(s, "makeslicecopy(%v, %v, %v)", n.Type, n.Left, n.Right)
+
 	case OPLUS, ONEG, OADDR, OBITNOT, ODEREF, ONOT, ORECV:
 		// Unary
 		mode.Fprintf(s, "%#v", n.Op)