mirror of
https://github.com/golang/go
synced 2024-11-11 21:20:21 -07:00
cmd/compile: add some generic composite type optimizations
Propagate values through some wide Zero/Move operations. Among
other things this allows us to optimize some kinds of array
initialization. For example, the following code no longer
requires a temporary be allocated on the stack. Instead it
writes the values directly into the return value.
func f(i uint32) [4]uint32 {
return [4]uint32{i, i+1, i+2, i+3}
}
The return value is unnecessarily cleared but removing that is
probably a task for dead store analysis (I think it needs to
be able to match multiple Store ops to wide Zero ops).
In order to reliably remove stack variables that are rendered
unnecessary by these new rules I've added a new generic version
of the unread autos elimination pass.
These rules are triggered more than 5000 times when building and
testing the standard library.
Updates #15925 (fixes for arrays of up to 4 elements).
Updates #24386 (fixes for up to 4 kept elements).
Updates #24416.
compilebench results:
name old time/op new time/op delta
Template 353ms ± 5% 359ms ± 3% ~ (p=0.143 n=10+10)
Unicode 219ms ± 1% 217ms ± 4% ~ (p=0.740 n=7+10)
GoTypes 1.26s ± 1% 1.26s ± 2% ~ (p=0.549 n=9+10)
Compiler 6.00s ± 1% 6.08s ± 1% +1.42% (p=0.000 n=9+8)
SSA 15.3s ± 2% 15.6s ± 1% +2.43% (p=0.000 n=10+10)
Flate 237ms ± 2% 240ms ± 2% +1.31% (p=0.015 n=10+10)
GoParser 285ms ± 1% 285ms ± 1% ~ (p=0.878 n=8+8)
Reflect 797ms ± 3% 807ms ± 2% ~ (p=0.065 n=9+10)
Tar 334ms ± 0% 335ms ± 4% ~ (p=0.460 n=8+10)
XML 419ms ± 0% 423ms ± 1% +0.91% (p=0.001 n=7+9)
StdCmd 46.0s ± 0% 46.4s ± 0% +0.85% (p=0.000 n=9+9)
name old user-time/op new user-time/op delta
Template 337ms ± 3% 346ms ± 5% ~ (p=0.053 n=9+10)
Unicode 205ms ±10% 205ms ± 8% ~ (p=1.000 n=10+10)
GoTypes 1.22s ± 2% 1.21s ± 3% ~ (p=0.436 n=10+10)
Compiler 5.85s ± 1% 5.93s ± 0% +1.46% (p=0.000 n=10+8)
SSA 14.9s ± 1% 15.3s ± 1% +2.62% (p=0.000 n=10+10)
Flate 229ms ± 4% 228ms ± 6% ~ (p=0.796 n=10+10)
GoParser 271ms ± 3% 275ms ± 4% ~ (p=0.165 n=10+10)
Reflect 779ms ± 5% 775ms ± 2% ~ (p=0.971 n=10+10)
Tar 317ms ± 4% 319ms ± 5% ~ (p=0.853 n=10+10)
XML 404ms ± 4% 409ms ± 5% ~ (p=0.436 n=10+10)
name old alloc/op new alloc/op delta
Template 34.9MB ± 0% 35.0MB ± 0% +0.26% (p=0.000 n=10+10)
Unicode 29.3MB ± 0% 29.3MB ± 0% +0.02% (p=0.000 n=10+10)
GoTypes 115MB ± 0% 115MB ± 0% +0.30% (p=0.000 n=10+10)
Compiler 519MB ± 0% 521MB ± 0% +0.30% (p=0.000 n=10+10)
SSA 1.55GB ± 0% 1.57GB ± 0% +1.34% (p=0.000 n=10+9)
Flate 24.1MB ± 0% 24.2MB ± 0% +0.10% (p=0.000 n=10+10)
GoParser 28.1MB ± 0% 28.1MB ± 0% +0.07% (p=0.000 n=10+10)
Reflect 78.7MB ± 0% 78.7MB ± 0% +0.03% (p=0.000 n=8+10)
Tar 34.4MB ± 0% 34.5MB ± 0% +0.12% (p=0.000 n=10+10)
XML 43.2MB ± 0% 43.2MB ± 0% +0.13% (p=0.000 n=10+10)
name old allocs/op new allocs/op delta
Template 330k ± 0% 330k ± 0% -0.01% (p=0.017 n=10+10)
Unicode 337k ± 0% 337k ± 0% +0.01% (p=0.000 n=9+10)
GoTypes 1.15M ± 0% 1.15M ± 0% +0.03% (p=0.000 n=10+10)
Compiler 4.77M ± 0% 4.77M ± 0% +0.03% (p=0.000 n=9+10)
SSA 12.5M ± 0% 12.6M ± 0% +1.16% (p=0.000 n=10+10)
Flate 221k ± 0% 221k ± 0% +0.05% (p=0.000 n=9+10)
GoParser 275k ± 0% 275k ± 0% +0.01% (p=0.014 n=10+9)
Reflect 944k ± 0% 944k ± 0% -0.02% (p=0.000 n=10+10)
Tar 324k ± 0% 323k ± 0% -0.12% (p=0.000 n=10+10)
XML 384k ± 0% 384k ± 0% -0.01% (p=0.001 n=10+10)
name old object-bytes new object-bytes delta
Template 476kB ± 0% 476kB ± 0% -0.04% (p=0.000 n=10+10)
Unicode 218kB ± 0% 218kB ± 0% ~ (all equal)
GoTypes 1.58MB ± 0% 1.58MB ± 0% -0.04% (p=0.000 n=10+10)
Compiler 6.25MB ± 0% 6.24MB ± 0% -0.09% (p=0.000 n=10+10)
SSA 15.9MB ± 0% 16.1MB ± 0% +1.22% (p=0.000 n=10+10)
Flate 304kB ± 0% 304kB ± 0% -0.13% (p=0.000 n=10+10)
GoParser 370kB ± 0% 370kB ± 0% -0.00% (p=0.000 n=10+10)
Reflect 1.27MB ± 0% 1.27MB ± 0% -0.12% (p=0.000 n=10+10)
Tar 421kB ± 0% 419kB ± 0% -0.64% (p=0.000 n=10+10)
XML 518kB ± 0% 517kB ± 0% -0.12% (p=0.000 n=10+10)
name old export-bytes new export-bytes delta
Template 16.7kB ± 0% 16.7kB ± 0% ~ (all equal)
Unicode 6.52kB ± 0% 6.52kB ± 0% ~ (all equal)
GoTypes 29.2kB ± 0% 29.2kB ± 0% ~ (all equal)
Compiler 88.0kB ± 0% 88.0kB ± 0% ~ (all equal)
SSA 109kB ± 0% 109kB ± 0% ~ (all equal)
Flate 4.49kB ± 0% 4.49kB ± 0% ~ (all equal)
GoParser 8.10kB ± 0% 8.10kB ± 0% ~ (all equal)
Reflect 7.71kB ± 0% 7.71kB ± 0% ~ (all equal)
Tar 9.15kB ± 0% 9.15kB ± 0% ~ (all equal)
XML 12.3kB ± 0% 12.3kB ± 0% ~ (all equal)
name old text-bytes new text-bytes delta
HelloSize 676kB ± 0% 672kB ± 0% -0.59% (p=0.000 n=10+10)
CmdGoSize 7.26MB ± 0% 7.24MB ± 0% -0.18% (p=0.000 n=10+10)
name old data-bytes new data-bytes delta
HelloSize 10.2kB ± 0% 10.2kB ± 0% ~ (all equal)
CmdGoSize 248kB ± 0% 248kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 125kB ± 0% 125kB ± 0% ~ (all equal)
CmdGoSize 145kB ± 0% 145kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.46MB ± 0% 1.45MB ± 0% -0.31% (p=0.000 n=10+10)
CmdGoSize 14.7MB ± 0% 14.7MB ± 0% -0.17% (p=0.000 n=10+10)
Change-Id: Ic72b0c189dd542f391e1c9ab88a76e9148dc4285
Reviewed-on: https://go-review.googlesource.com/106495
Run-TryBot: Michael Munday <mike.munday@ibm.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
This commit is contained in:
Michael Munday
parent
098ca846c7
commit
f31a18ded4
@ -371,6 +371,7 @@ var passes = [...]pass{
|
||||
{name: "decompose builtin", fn: decomposeBuiltIn, required: true},
|
||||
{name: "softfloat", fn: softfloat, required: true},
|
||||
{name: "late opt", fn: opt, required: true}, // TODO: split required rules and optimizing rules
|
||||
{name: "dead auto elim", fn: elimDeadAutosGeneric},
|
||||
{name: "generic deadcode", fn: deadcode},
|
||||
{name: "check bce", fn: checkbce},
|
||||
{name: "branchelim", fn: branchelim},
|
||||
|
||||
@ -133,6 +133,153 @@ func dse(f *Func) {
|
||||
}
|
||||
}
|
||||
|
||||
// elimDeadAutosGeneric deletes autos that are never accessed. To acheive this
|
||||
// we track the operations that the address of each auto reaches and if it only
|
||||
// reaches stores then we delete all the stores. The other operations will then
|
||||
// be eliminated by the dead code elimination pass.
|
||||
func elimDeadAutosGeneric(f *Func) {
|
||||
addr := make(map[*Value]GCNode) // values that the address of the auto reaches
|
||||
elim := make(map[*Value]GCNode) // values that could be eliminated if the auto is
|
||||
used := make(map[GCNode]bool) // used autos that must be kept
|
||||
|
||||
// visit the value and report whether any of the maps are updated
|
||||
visit := func(v *Value) (changed bool) {
|
||||
args := v.Args
|
||||
switch v.Op {
|
||||
case OpAddr:
|
||||
// Propagate the address if it points to an auto.
|
||||
n, ok := v.Aux.(GCNode)
|
||||
if !ok || n.StorageClass() != ClassAuto {
|
||||
return
|
||||
}
|
||||
if addr[v] == nil {
|
||||
addr[v] = n
|
||||
changed = true
|
||||
}
|
||||
return
|
||||
case OpVarDef, OpVarKill:
|
||||
// v should be eliminated if we eliminate the auto.
|
||||
n, ok := v.Aux.(GCNode)
|
||||
if !ok || n.StorageClass() != ClassAuto {
|
||||
return
|
||||
}
|
||||
if elim[v] == nil {
|
||||
elim[v] = n
|
||||
changed = true
|
||||
}
|
||||
return
|
||||
case OpVarLive:
|
||||
// Don't delete the auto if it needs to be kept alive.
|
||||
n, ok := v.Aux.(GCNode)
|
||||
if !ok || n.StorageClass() != ClassAuto {
|
||||
return
|
||||
}
|
||||
if !used[n] {
|
||||
used[n] = true
|
||||
changed = true
|
||||
}
|
||||
return
|
||||
case OpStore, OpMove, OpZero:
|
||||
// v should be elimated if we eliminate the auto.
|
||||
n, ok := addr[args[0]]
|
||||
if ok && elim[v] == nil {
|
||||
elim[v] = n
|
||||
changed = true
|
||||
}
|
||||
// Other args might hold pointers to autos.
|
||||
args = args[1:]
|
||||
}
|
||||
|
||||
// The code below assumes that we have handled all the ops
|
||||
// with sym effects already. Sanity check that here.
|
||||
// Ignore Args since they can't be autos.
|
||||
if v.Op.SymEffect() != SymNone && v.Op != OpArg {
|
||||
panic("unhandled op with sym effect")
|
||||
}
|
||||
|
||||
if v.Uses == 0 || len(args) == 0 {
|
||||
return
|
||||
}
|
||||
|
||||
// If the address of the auto reaches a memory or control
|
||||
// operation not covered above then we probably need to keep it.
|
||||
if v.Type.IsMemory() || v.Type.IsFlags() || (v.Op != OpPhi && v.MemoryArg() != nil) {
|
||||
for _, a := range args {
|
||||
if n, ok := addr[a]; ok {
|
||||
if !used[n] {
|
||||
used[n] = true
|
||||
changed = true
|
||||
}
|
||||
}
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
// Propagate any auto addresses through v.
|
||||
node := GCNode(nil)
|
||||
for _, a := range args {
|
||||
if n, ok := addr[a]; ok && !used[n] {
|
||||
if node == nil {
|
||||
node = n
|
||||
} else if node != n {
|
||||
// Most of the time we only see one pointer
|
||||
// reaching an op, but some ops can take
|
||||
// multiple pointers (e.g. NeqPtr, Phi etc.).
|
||||
// This is rare, so just propagate the first
|
||||
// value to keep things simple.
|
||||
used[n] = true
|
||||
changed = true
|
||||
}
|
||||
}
|
||||
}
|
||||
if node == nil {
|
||||
return
|
||||
}
|
||||
if addr[v] == nil {
|
||||
// The address of an auto reaches this op.
|
||||
addr[v] = node
|
||||
changed = true
|
||||
return
|
||||
}
|
||||
if addr[v] != node {
|
||||
// This doesn't happen in practice, but catch it just in case.
|
||||
used[node] = true
|
||||
changed = true
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
iterations := 0
|
||||
for {
|
||||
if iterations == 4 {
|
||||
// give up
|
||||
return
|
||||
}
|
||||
iterations++
|
||||
changed := false
|
||||
for _, b := range f.Blocks {
|
||||
for _, v := range b.Values {
|
||||
changed = visit(v) || changed
|
||||
}
|
||||
}
|
||||
if !changed {
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
// Eliminate stores to unread autos.
|
||||
for v, n := range elim {
|
||||
if used[n] {
|
||||
continue
|
||||
}
|
||||
// replace with OpCopy
|
||||
v.SetArgs1(v.MemoryArg())
|
||||
v.Aux = nil
|
||||
v.AuxInt = 0
|
||||
v.Op = OpCopy
|
||||
}
|
||||
}
|
||||
|
||||
// elimUnreadAutos deletes stores (and associated bookkeeping ops VarDef and VarKill)
|
||||
// to autos that are never read from.
|
||||
func elimUnreadAutos(f *Func) {
|
||||
|
||||
@ -537,40 +537,162 @@
|
||||
(NeqSlice x y) -> (NeqPtr (SlicePtr x) (SlicePtr y))
|
||||
|
||||
// Load of store of same address, with compatibly typed value and same size
|
||||
(Load <t1> p1 (Store {t2} p2 x _)) && isSamePtr(p1,p2) && t1.Compare(x.Type) == types.CMPeq && t1.Size() == t2.(*types.Type).Size() -> x
|
||||
(Load <t1> p1 (Store {t2} p2 x _))
|
||||
&& isSamePtr(p1, p2)
|
||||
&& t1.Compare(x.Type) == types.CMPeq
|
||||
&& t1.Size() == sizeof(t2)
|
||||
-> x
|
||||
(Load <t1> p1 (Store {t2} p2 _ (Store {t3} p3 x _)))
|
||||
&& isSamePtr(p1, p3)
|
||||
&& t1.Compare(x.Type) == types.CMPeq
|
||||
&& t1.Size() == sizeof(t2)
|
||||
&& disjoint(p3, sizeof(t3), p2, sizeof(t2))
|
||||
-> x
|
||||
(Load <t1> p1 (Store {t2} p2 _ (Store {t3} p3 _ (Store {t4} p4 x _))))
|
||||
&& isSamePtr(p1, p4)
|
||||
&& t1.Compare(x.Type) == types.CMPeq
|
||||
&& t1.Size() == sizeof(t2)
|
||||
&& disjoint(p4, sizeof(t4), p2, sizeof(t2))
|
||||
&& disjoint(p4, sizeof(t4), p3, sizeof(t3))
|
||||
-> x
|
||||
(Load <t1> p1 (Store {t2} p2 _ (Store {t3} p3 _ (Store {t4} p4 _ (Store {t5} p5 x _)))))
|
||||
&& isSamePtr(p1, p5)
|
||||
&& t1.Compare(x.Type) == types.CMPeq
|
||||
&& t1.Size() == sizeof(t2)
|
||||
&& disjoint(p5, sizeof(t5), p2, sizeof(t2))
|
||||
&& disjoint(p5, sizeof(t5), p3, sizeof(t3))
|
||||
&& disjoint(p5, sizeof(t5), p4, sizeof(t4))
|
||||
-> x
|
||||
|
||||
// Pass constants through math.Float{32,64}bits and math.Float{32,64}frombits
|
||||
(Load <t1> p1 (Store {t2} p2 (Const64 [x]) _)) && isSamePtr(p1,p2) && t2.(*types.Type).Size() == 8 && is64BitFloat(t1) -> (Const64F [x])
|
||||
(Load <t1> p1 (Store {t2} p2 (Const32 [x]) _)) && isSamePtr(p1,p2) && t2.(*types.Type).Size() == 4 && is32BitFloat(t1) -> (Const32F [f2i(float64(math.Float32frombits(uint32(x))))])
|
||||
(Load <t1> p1 (Store {t2} p2 (Const64F [x]) _)) && isSamePtr(p1,p2) && t2.(*types.Type).Size() == 8 && is64BitInt(t1) -> (Const64 [x])
|
||||
(Load <t1> p1 (Store {t2} p2 (Const32F [x]) _)) && isSamePtr(p1,p2) && t2.(*types.Type).Size() == 4 && is32BitInt(t1) -> (Const32 [int64(int32(math.Float32bits(float32(i2f(x)))))])
|
||||
(Load <t1> p1 (Store {t2} p2 (Const64 [x]) _)) && isSamePtr(p1,p2) && sizeof(t2) == 8 && is64BitFloat(t1) -> (Const64F [x])
|
||||
(Load <t1> p1 (Store {t2} p2 (Const32 [x]) _)) && isSamePtr(p1,p2) && sizeof(t2) == 4 && is32BitFloat(t1) -> (Const32F [f2i(float64(math.Float32frombits(uint32(x))))])
|
||||
(Load <t1> p1 (Store {t2} p2 (Const64F [x]) _)) && isSamePtr(p1,p2) && sizeof(t2) == 8 && is64BitInt(t1) -> (Const64 [x])
|
||||
(Load <t1> p1 (Store {t2} p2 (Const32F [x]) _)) && isSamePtr(p1,p2) && sizeof(t2) == 4 && is32BitInt(t1) -> (Const32 [int64(int32(math.Float32bits(float32(i2f(x)))))])
|
||||
|
||||
// Float Loads up to Zeros so they can be constant folded.
|
||||
(Load <t1> op:(OffPtr [o1] p1)
|
||||
(Store {t2} p2 _
|
||||
mem:(Zero [n] p3 _)))
|
||||
&& o1 >= 0 && o1+t1.Size() <= n && isSamePtr(p1, p3)
|
||||
&& disjoint(op, t1.Size(), p2, sizeof(t2))
|
||||
-> @mem.Block (Load <t1> op mem)
|
||||
(Load <t1> op:(OffPtr [o1] p1)
|
||||
(Store {t2} p2 _
|
||||
(Store {t3} p3 _
|
||||
mem:(Zero [n] p4 _))))
|
||||
&& o1 >= 0 && o1+t1.Size() <= n && isSamePtr(p1, p4)
|
||||
&& disjoint(op, t1.Size(), p2, sizeof(t2))
|
||||
&& disjoint(op, t1.Size(), p3, sizeof(t3))
|
||||
-> @mem.Block (Load <t1> op mem)
|
||||
(Load <t1> op:(OffPtr [o1] p1)
|
||||
(Store {t2} p2 _
|
||||
(Store {t3} p3 _
|
||||
(Store {t4} p4 _
|
||||
mem:(Zero [n] p5 _)))))
|
||||
&& o1 >= 0 && o1+t1.Size() <= n && isSamePtr(p1, p5)
|
||||
&& disjoint(op, t1.Size(), p2, sizeof(t2))
|
||||
&& disjoint(op, t1.Size(), p3, sizeof(t3))
|
||||
&& disjoint(op, t1.Size(), p4, sizeof(t4))
|
||||
-> @mem.Block (Load <t1> op mem)
|
||||
(Load <t1> op:(OffPtr [o1] p1)
|
||||
(Store {t2} p2 _
|
||||
(Store {t3} p3 _
|
||||
(Store {t4} p4 _
|
||||
(Store {t5} p5 _
|
||||
mem:(Zero [n] p6 _))))))
|
||||
&& o1 >= 0 && o1+t1.Size() <= n && isSamePtr(p1, p6)
|
||||
&& disjoint(op, t1.Size(), p2, sizeof(t2))
|
||||
&& disjoint(op, t1.Size(), p3, sizeof(t3))
|
||||
&& disjoint(op, t1.Size(), p4, sizeof(t4))
|
||||
&& disjoint(op, t1.Size(), p5, sizeof(t5))
|
||||
-> @mem.Block (Load <t1> op mem)
|
||||
|
||||
// Zero to Load forwarding.
|
||||
(Load <t1> (OffPtr [o] p1) (Zero [n] p2 _))
|
||||
&& t1.IsBoolean()
|
||||
&& isSamePtr(p1, p2)
|
||||
&& n >= o + 1
|
||||
-> (ConstBool [0])
|
||||
(Load <t1> (OffPtr [o] p1) (Zero [n] p2 _))
|
||||
&& is8BitInt(t1)
|
||||
&& isSamePtr(p1, p2)
|
||||
&& n >= o + 1
|
||||
-> (Const8 [0])
|
||||
(Load <t1> (OffPtr [o] p1) (Zero [n] p2 _))
|
||||
&& is16BitInt(t1)
|
||||
&& isSamePtr(p1, p2)
|
||||
&& n >= o + 2
|
||||
-> (Const16 [0])
|
||||
(Load <t1> (OffPtr [o] p1) (Zero [n] p2 _))
|
||||
&& is32BitInt(t1)
|
||||
&& isSamePtr(p1, p2)
|
||||
&& n >= o + 4
|
||||
-> (Const32 [0])
|
||||
(Load <t1> (OffPtr [o] p1) (Zero [n] p2 _))
|
||||
&& is64BitInt(t1)
|
||||
&& isSamePtr(p1, p2)
|
||||
&& n >= o + 8
|
||||
-> (Const64 [0])
|
||||
(Load <t1> (OffPtr [o] p1) (Zero [n] p2 _))
|
||||
&& is32BitFloat(t1)
|
||||
&& isSamePtr(p1, p2)
|
||||
&& n >= o + 4
|
||||
-> (Const32F [0])
|
||||
(Load <t1> (OffPtr [o] p1) (Zero [n] p2 _))
|
||||
&& is64BitFloat(t1)
|
||||
&& isSamePtr(p1, p2)
|
||||
&& n >= o + 8
|
||||
-> (Const64F [0])
|
||||
|
||||
// Eliminate stores of values that have just been loaded from the same location.
|
||||
// We also handle the common case where there are some intermediate stores to non-overlapping struct fields.
|
||||
(Store {t1} p1 (Load <t2> p2 mem) mem) &&
|
||||
isSamePtr(p1, p2) &&
|
||||
t2.Size() == t1.(*types.Type).Size() -> mem
|
||||
(Store {t1} (OffPtr [o1] p1) (Load <t2> (OffPtr [o1] p2) oldmem) mem:(Store {t3} (OffPtr [o3] p3) _ oldmem)) &&
|
||||
isSamePtr(p1, p2) &&
|
||||
isSamePtr(p1, p3) &&
|
||||
t2.Size() == t1.(*types.Type).Size() &&
|
||||
!overlap(o1, t2.Size(), o3, t3.(*types.Type).Size()) -> mem
|
||||
(Store {t1} (OffPtr [o1] p1) (Load <t2> (OffPtr [o1] p2) oldmem) mem:(Store {t3} (OffPtr [o3] p3) _ (Store {t4} (OffPtr [o4] p4) _ oldmem))) &&
|
||||
isSamePtr(p1, p2) &&
|
||||
isSamePtr(p1, p3) &&
|
||||
isSamePtr(p1, p4) &&
|
||||
t2.Size() == t1.(*types.Type).Size() &&
|
||||
!overlap(o1, t2.Size(), o3, t3.(*types.Type).Size()) &&
|
||||
!overlap(o1, t2.Size(), o4, t4.(*types.Type).Size()) -> mem
|
||||
(Store {t1} (OffPtr [o1] p1) (Load <t2> (OffPtr [o1] p2) oldmem) mem:(Store {t3} (OffPtr [o3] p3) _ (Store {t4} (OffPtr [o4] p4) _ (Store {t5} (OffPtr [o5] p5) _ oldmem)))) &&
|
||||
isSamePtr(p1, p2) &&
|
||||
isSamePtr(p1, p3) &&
|
||||
isSamePtr(p1, p4) &&
|
||||
isSamePtr(p1, p5) &&
|
||||
t2.Size() == t1.(*types.Type).Size() &&
|
||||
!overlap(o1, t2.Size(), o3, t3.(*types.Type).Size()) &&
|
||||
!overlap(o1, t2.Size(), o4, t4.(*types.Type).Size()) &&
|
||||
!overlap(o1, t2.Size(), o5, t5.(*types.Type).Size()) -> mem
|
||||
// We also handle the common case where there are some intermediate stores.
|
||||
(Store {t1} p1 (Load <t2> p2 mem) mem)
|
||||
&& isSamePtr(p1, p2)
|
||||
&& t2.Size() == sizeof(t1)
|
||||
-> mem
|
||||
(Store {t1} p1 (Load <t2> p2 oldmem) mem:(Store {t3} p3 _ oldmem))
|
||||
&& isSamePtr(p1, p2)
|
||||
&& t2.Size() == sizeof(t1)
|
||||
&& disjoint(p1, sizeof(t1), p3, sizeof(t3))
|
||||
-> mem
|
||||
(Store {t1} p1 (Load <t2> p2 oldmem) mem:(Store {t3} p3 _ (Store {t4} p4 _ oldmem)))
|
||||
&& isSamePtr(p1, p2)
|
||||
&& t2.Size() == sizeof(t1)
|
||||
&& disjoint(p1, sizeof(t1), p3, sizeof(t3))
|
||||
&& disjoint(p1, sizeof(t1), p4, sizeof(t4))
|
||||
-> mem
|
||||
(Store {t1} p1 (Load <t2> p2 oldmem) mem:(Store {t3} p3 _ (Store {t4} p4 _ (Store {t5} p5 _ oldmem))))
|
||||
&& isSamePtr(p1, p2)
|
||||
&& t2.Size() == sizeof(t1)
|
||||
&& disjoint(p1, sizeof(t1), p3, sizeof(t3))
|
||||
&& disjoint(p1, sizeof(t1), p4, sizeof(t4))
|
||||
&& disjoint(p1, sizeof(t1), p5, sizeof(t5))
|
||||
-> mem
|
||||
|
||||
// Don't Store zeros to cleared variables.
|
||||
(Store {t} (OffPtr [o] p1) x mem:(Zero [n] p2 _))
|
||||
&& isConstZero(x)
|
||||
&& o >= 0 && sizeof(t) + o <= n && isSamePtr(p1, p2)
|
||||
-> mem
|
||||
(Store {t1} op:(OffPtr [o1] p1) x mem:(Store {t2} p2 _ (Zero [n] p3 _)))
|
||||
&& isConstZero(x)
|
||||
&& o1 >= 0 && sizeof(t1) + o1 <= n && isSamePtr(p1, p3)
|
||||
&& disjoint(op, sizeof(t1), p2, sizeof(t2))
|
||||
-> mem
|
||||
(Store {t1} op:(OffPtr [o1] p1) x mem:(Store {t2} p2 _ (Store {t3} p3 _ (Zero [n] p4 _))))
|
||||
&& isConstZero(x)
|
||||
&& o1 >= 0 && sizeof(t1) + o1 <= n && isSamePtr(p1, p4)
|
||||
&& disjoint(op, sizeof(t1), p2, sizeof(t2))
|
||||
&& disjoint(op, sizeof(t1), p3, sizeof(t3))
|
||||
-> mem
|
||||
(Store {t1} op:(OffPtr [o1] p1) x mem:(Store {t2} p2 _ (Store {t3} p3 _ (Store {t4} p4 _ (Zero [n] p5 _)))))
|
||||
&& isConstZero(x)
|
||||
&& o1 >= 0 && sizeof(t1) + o1 <= n && isSamePtr(p1, p5)
|
||||
&& disjoint(op, sizeof(t1), p2, sizeof(t2))
|
||||
&& disjoint(op, sizeof(t1), p3, sizeof(t3))
|
||||
&& disjoint(op, sizeof(t1), p4, sizeof(t4))
|
||||
-> mem
|
||||
|
||||
// Collapse OffPtr
|
||||
(OffPtr (OffPtr p [b]) [a]) -> (OffPtr p [a+b])
|
||||
@ -657,9 +779,9 @@
|
||||
|
||||
// un-SSAable values use mem->mem copies
|
||||
(Store {t} dst (Load src mem) mem) && !fe.CanSSA(t.(*types.Type)) ->
|
||||
(Move {t} [t.(*types.Type).Size()] dst src mem)
|
||||
(Move {t} [sizeof(t)] dst src mem)
|
||||
(Store {t} dst (Load src mem) (VarDef {x} mem)) && !fe.CanSSA(t.(*types.Type)) ->
|
||||
(Move {t} [t.(*types.Type).Size()] dst src (VarDef {x} mem))
|
||||
(Move {t} [sizeof(t)] dst src (VarDef {x} mem))
|
||||
|
||||
// array ops
|
||||
(ArraySelect (ArrayMake1 x)) -> x
|
||||
@ -1278,3 +1400,382 @@
|
||||
// so this rule should trigger reliably.
|
||||
(InterCall [argsize] (Load (OffPtr [off] (ITab (IMake (Addr {itab} (SB)) _))) _) mem) && devirt(v, itab, off) != nil ->
|
||||
(StaticCall [argsize] {devirt(v, itab, off)} mem)
|
||||
|
||||
// Move and Zero optimizations.
|
||||
// Move source and destination may overlap.
|
||||
|
||||
// Convert Moves into Zeros when the source is known to be zeros.
|
||||
(Move {t} [n] dst1 src mem:(Zero {t} [n] dst2 _)) && isSamePtr(src, dst2)
|
||||
-> (Zero {t} [n] dst1 mem)
|
||||
(Move {t} [n] dst1 src mem:(VarDef (Zero {t} [n] dst0 _))) && isSamePtr(src, dst0)
|
||||
-> (Zero {t} [n] dst1 mem)
|
||||
|
||||
// Don't Store to variables that are about to be overwritten by Move/Zero.
|
||||
(Zero {t1} [n] p1 store:(Store {t2} (OffPtr [o2] p2) _ mem))
|
||||
&& isSamePtr(p1, p2) && store.Uses == 1
|
||||
&& n >= o2 + sizeof(t2)
|
||||
&& clobber(store)
|
||||
-> (Zero {t1} [n] p1 mem)
|
||||
(Move {t1} [n] dst1 src1 store:(Store {t2} op:(OffPtr [o2] dst2) _ mem))
|
||||
&& isSamePtr(dst1, dst2) && store.Uses == 1
|
||||
&& n >= o2 + sizeof(t2)
|
||||
&& disjoint(src1, n, op, sizeof(t2))
|
||||
&& clobber(store)
|
||||
-> (Move {t1} [n] dst1 src1 mem)
|
||||
|
||||
// Don't Move to variables that are immediately completely overwritten.
|
||||
(Zero {t} [n] dst1 move:(Move {t} [n] dst2 _ mem))
|
||||
&& move.Uses == 1
|
||||
&& isSamePtr(dst1, dst2)
|
||||
&& clobber(move)
|
||||
-> (Zero {t} [n] dst1 mem)
|
||||
(Move {t} [n] dst1 src1 move:(Move {t} [n] dst2 _ mem))
|
||||
&& move.Uses == 1
|
||||
&& isSamePtr(dst1, dst2) && disjoint(src1, n, dst2, n)
|
||||
&& clobber(move)
|
||||
-> (Move {t} [n] dst1 src1 mem)
|
||||
(Zero {t} [n] dst1 vardef:(VarDef {x} move:(Move {t} [n] dst2 _ mem)))
|
||||
&& move.Uses == 1 && vardef.Uses == 1
|
||||
&& isSamePtr(dst1, dst2)
|
||||
&& clobber(move) && clobber(vardef)
|
||||
-> (Zero {t} [n] dst1 (VarDef {x} mem))
|
||||
(Move {t} [n] dst1 src1 vardef:(VarDef {x} move:(Move {t} [n] dst2 _ mem)))
|
||||
&& move.Uses == 1 && vardef.Uses == 1
|
||||
&& isSamePtr(dst1, dst2) && disjoint(src1, n, dst2, n)
|
||||
&& clobber(move) && clobber(vardef)
|
||||
-> (Move {t} [n] dst1 src1 (VarDef {x} mem))
|
||||
(Store {t1} op1:(OffPtr [o1] p1) d1
|
||||
m2:(Store {t2} op2:(OffPtr [0] p2) d2
|
||||
m3:(Move [n] p3 _ mem)))
|
||||
&& m2.Uses == 1 && m3.Uses == 1
|
||||
&& o1 == sizeof(t2)
|
||||
&& n == sizeof(t2) + sizeof(t1)
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3)
|
||||
&& clobber(m2) && clobber(m3)
|
||||
-> (Store {t1} op1 d1 (Store {t2} op2 d2 mem))
|
||||
(Store {t1} op1:(OffPtr [o1] p1) d1
|
||||
m2:(Store {t2} op2:(OffPtr [o2] p2) d2
|
||||
m3:(Store {t3} op3:(OffPtr [0] p3) d3
|
||||
m4:(Move [n] p4 _ mem))))
|
||||
&& m2.Uses == 1 && m3.Uses == 1 && m4.Uses == 1
|
||||
&& o2 == sizeof(t3)
|
||||
&& o1-o2 == sizeof(t2)
|
||||
&& n == sizeof(t3) + sizeof(t2) + sizeof(t1)
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4)
|
||||
&& clobber(m2) && clobber(m3) && clobber(m4)
|
||||
-> (Store {t1} op1 d1 (Store {t2} op2 d2 (Store {t3} op3 d3 mem)))
|
||||
(Store {t1} op1:(OffPtr [o1] p1) d1
|
||||
m2:(Store {t2} op2:(OffPtr [o2] p2) d2
|
||||
m3:(Store {t3} op3:(OffPtr [o3] p3) d3
|
||||
m4:(Store {t4} op4:(OffPtr [0] p4) d4
|
||||
m5:(Move [n] p5 _ mem)))))
|
||||
&& m2.Uses == 1 && m3.Uses == 1 && m4.Uses == 1 && m5.Uses == 1
|
||||
&& o3 == sizeof(t4)
|
||||
&& o2-o3 == sizeof(t3)
|
||||
&& o1-o2 == sizeof(t2)
|
||||
&& n == sizeof(t4) + sizeof(t3) + sizeof(t2) + sizeof(t1)
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4) && isSamePtr(p4, p5)
|
||||
&& clobber(m2) && clobber(m3) && clobber(m4) && clobber(m5)
|
||||
-> (Store {t1} op1 d1 (Store {t2} op2 d2 (Store {t3} op3 d3 (Store {t4} op4 d4 mem))))
|
||||
|
||||
// Don't Zero variables that are immediately completely overwritten
|
||||
// before being accessed.
|
||||
(Move {t} [n] dst1 src1 zero:(Zero {t} [n] dst2 mem))
|
||||
&& zero.Uses == 1
|
||||
&& isSamePtr(dst1, dst2) && disjoint(src1, n, dst2, n)
|
||||
&& clobber(zero)
|
||||
-> (Move {t} [n] dst1 src1 mem)
|
||||
(Move {t} [n] dst1 src1 vardef:(VarDef {x} zero:(Zero {t} [n] dst2 mem)))
|
||||
&& zero.Uses == 1 && vardef.Uses == 1
|
||||
&& isSamePtr(dst1, dst2) && disjoint(src1, n, dst2, n)
|
||||
&& clobber(zero) && clobber(vardef)
|
||||
-> (Move {t} [n] dst1 src1 (VarDef {x} mem))
|
||||
(Store {t1} op1:(OffPtr [o1] p1) d1
|
||||
m2:(Store {t2} op2:(OffPtr [0] p2) d2
|
||||
m3:(Zero [n] p3 mem)))
|
||||
&& m2.Uses == 1 && m3.Uses == 1
|
||||
&& o1 == sizeof(t2)
|
||||
&& n == sizeof(t2) + sizeof(t1)
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3)
|
||||
&& clobber(m2) && clobber(m3)
|
||||
-> (Store {t1} op1 d1 (Store {t2} op2 d2 mem))
|
||||
(Store {t1} op1:(OffPtr [o1] p1) d1
|
||||
m2:(Store {t2} op2:(OffPtr [o2] p2) d2
|
||||
m3:(Store {t3} op3:(OffPtr [0] p3) d3
|
||||
m4:(Zero [n] p4 mem))))
|
||||
&& m2.Uses == 1 && m3.Uses == 1 && m4.Uses == 1
|
||||
&& o2 == sizeof(t3)
|
||||
&& o1-o2 == sizeof(t2)
|
||||
&& n == sizeof(t3) + sizeof(t2) + sizeof(t1)
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4)
|
||||
&& clobber(m2) && clobber(m3) && clobber(m4)
|
||||
-> (Store {t1} op1 d1 (Store {t2} op2 d2 (Store {t3} op3 d3 mem)))
|
||||
(Store {t1} op1:(OffPtr [o1] p1) d1
|
||||
m2:(Store {t2} op2:(OffPtr [o2] p2) d2
|
||||
m3:(Store {t3} op3:(OffPtr [o3] p3) d3
|
||||
m4:(Store {t4} op4:(OffPtr [0] p4) d4
|
||||
m5:(Zero [n] p5 mem)))))
|
||||
&& m2.Uses == 1 && m3.Uses == 1 && m4.Uses == 1 && m5.Uses == 1
|
||||
&& o3 == sizeof(t4)
|
||||
&& o2-o3 == sizeof(t3)
|
||||
&& o1-o2 == sizeof(t2)
|
||||
&& n == sizeof(t4) + sizeof(t3) + sizeof(t2) + sizeof(t1)
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4) && isSamePtr(p4, p5)
|
||||
&& clobber(m2) && clobber(m3) && clobber(m4) && clobber(m5)
|
||||
-> (Store {t1} op1 d1 (Store {t2} op2 d2 (Store {t3} op3 d3 (Store {t4} op4 d4 mem))))
|
||||
|
||||
// Don't Move from memory if the values are likely to already be
|
||||
// in registers.
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(Store {t2} op2:(OffPtr [o2] p2) d1
|
||||
(Store {t3} op3:(OffPtr [0] p3) d2 _)))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& registerizable(b, t3)
|
||||
&& o2 == sizeof(t3)
|
||||
&& n == sizeof(t2) + sizeof(t3)
|
||||
-> (Store {t2} (OffPtr <t2.(*types.Type)> [o2] dst) d1
|
||||
(Store {t3} (OffPtr <t3.(*types.Type)> [0] dst) d2 mem))
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(Store {t2} op2:(OffPtr [o2] p2) d1
|
||||
(Store {t3} op3:(OffPtr [o3] p3) d2
|
||||
(Store {t4} op4:(OffPtr [0] p4) d3 _))))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& alignof(t4) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& registerizable(b, t3)
|
||||
&& registerizable(b, t4)
|
||||
&& o3 == sizeof(t4)
|
||||
&& o2-o3 == sizeof(t3)
|
||||
&& n == sizeof(t2) + sizeof(t3) + sizeof(t4)
|
||||
-> (Store {t2} (OffPtr <t2.(*types.Type)> [o2] dst) d1
|
||||
(Store {t3} (OffPtr <t3.(*types.Type)> [o3] dst) d2
|
||||
(Store {t4} (OffPtr <t4.(*types.Type)> [0] dst) d3 mem)))
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(Store {t2} op2:(OffPtr [o2] p2) d1
|
||||
(Store {t3} op3:(OffPtr [o3] p3) d2
|
||||
(Store {t4} op4:(OffPtr [o4] p4) d3
|
||||
(Store {t5} op5:(OffPtr [0] p5) d4 _)))))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4) && isSamePtr(p4, p5)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& alignof(t4) <= alignof(t1)
|
||||
&& alignof(t5) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& registerizable(b, t3)
|
||||
&& registerizable(b, t4)
|
||||
&& registerizable(b, t5)
|
||||
&& o4 == sizeof(t5)
|
||||
&& o3-o4 == sizeof(t4)
|
||||
&& o2-o3 == sizeof(t3)
|
||||
&& n == sizeof(t2) + sizeof(t3) + sizeof(t4) + sizeof(t5)
|
||||
-> (Store {t2} (OffPtr <t2.(*types.Type)> [o2] dst) d1
|
||||
(Store {t3} (OffPtr <t3.(*types.Type)> [o3] dst) d2
|
||||
(Store {t4} (OffPtr <t4.(*types.Type)> [o4] dst) d3
|
||||
(Store {t5} (OffPtr <t5.(*types.Type)> [0] dst) d4 mem))))
|
||||
|
||||
// Same thing but with VarDef in the middle.
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(VarDef
|
||||
(Store {t2} op2:(OffPtr [o2] p2) d1
|
||||
(Store {t3} op3:(OffPtr [0] p3) d2 _))))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& registerizable(b, t3)
|
||||
&& o2 == sizeof(t3)
|
||||
&& n == sizeof(t2) + sizeof(t3)
|
||||
-> (Store {t2} (OffPtr <t2.(*types.Type)> [o2] dst) d1
|
||||
(Store {t3} (OffPtr <t3.(*types.Type)> [0] dst) d2 mem))
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(VarDef
|
||||
(Store {t2} op2:(OffPtr [o2] p2) d1
|
||||
(Store {t3} op3:(OffPtr [o3] p3) d2
|
||||
(Store {t4} op4:(OffPtr [0] p4) d3 _)))))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& alignof(t4) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& registerizable(b, t3)
|
||||
&& registerizable(b, t4)
|
||||
&& o3 == sizeof(t4)
|
||||
&& o2-o3 == sizeof(t3)
|
||||
&& n == sizeof(t2) + sizeof(t3) + sizeof(t4)
|
||||
-> (Store {t2} (OffPtr <t2.(*types.Type)> [o2] dst) d1
|
||||
(Store {t3} (OffPtr <t3.(*types.Type)> [o3] dst) d2
|
||||
(Store {t4} (OffPtr <t4.(*types.Type)> [0] dst) d3 mem)))
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(VarDef
|
||||
(Store {t2} op2:(OffPtr [o2] p2) d1
|
||||
(Store {t3} op3:(OffPtr [o3] p3) d2
|
||||
(Store {t4} op4:(OffPtr [o4] p4) d3
|
||||
(Store {t5} op5:(OffPtr [0] p5) d4 _))))))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4) && isSamePtr(p4, p5)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& alignof(t4) <= alignof(t1)
|
||||
&& alignof(t5) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& registerizable(b, t3)
|
||||
&& registerizable(b, t4)
|
||||
&& registerizable(b, t5)
|
||||
&& o4 == sizeof(t5)
|
||||
&& o3-o4 == sizeof(t4)
|
||||
&& o2-o3 == sizeof(t3)
|
||||
&& n == sizeof(t2) + sizeof(t3) + sizeof(t4) + sizeof(t5)
|
||||
-> (Store {t2} (OffPtr <t2.(*types.Type)> [o2] dst) d1
|
||||
(Store {t3} (OffPtr <t3.(*types.Type)> [o3] dst) d2
|
||||
(Store {t4} (OffPtr <t4.(*types.Type)> [o4] dst) d3
|
||||
(Store {t5} (OffPtr <t5.(*types.Type)> [0] dst) d4 mem))))
|
||||
|
||||
// Prefer to Zero and Store than to Move.
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(Store {t2} op2:(OffPtr <tt2> [o2] p2) d1
|
||||
(Zero {t3} [n] p3 _)))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& n >= o2 + sizeof(t2)
|
||||
-> (Store {t2} (OffPtr <tt2> [o2] dst) d1
|
||||
(Zero {t1} [n] dst mem))
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(Store {t2} (OffPtr <tt2> [o2] p2) d1
|
||||
(Store {t3} (OffPtr <tt3> [o3] p3) d2
|
||||
(Zero {t4} [n] p4 _))))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& alignof(t4) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& registerizable(b, t3)
|
||||
&& n >= o2 + sizeof(t2)
|
||||
&& n >= o3 + sizeof(t3)
|
||||
-> (Store {t2} (OffPtr <tt2> [o2] dst) d1
|
||||
(Store {t3} (OffPtr <tt3> [o3] dst) d2
|
||||
(Zero {t1} [n] dst mem)))
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(Store {t2} (OffPtr <tt2> [o2] p2) d1
|
||||
(Store {t3} (OffPtr <tt3> [o3] p3) d2
|
||||
(Store {t4} (OffPtr <tt4> [o4] p4) d3
|
||||
(Zero {t5} [n] p5 _)))))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4) && isSamePtr(p4, p5)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& alignof(t4) <= alignof(t1)
|
||||
&& alignof(t5) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& registerizable(b, t3)
|
||||
&& registerizable(b, t4)
|
||||
&& n >= o2 + sizeof(t2)
|
||||
&& n >= o3 + sizeof(t3)
|
||||
&& n >= o4 + sizeof(t4)
|
||||
-> (Store {t2} (OffPtr <tt2> [o2] dst) d1
|
||||
(Store {t3} (OffPtr <tt3> [o3] dst) d2
|
||||
(Store {t4} (OffPtr <tt4> [o4] dst) d3
|
||||
(Zero {t1} [n] dst mem))))
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(Store {t2} (OffPtr <tt2> [o2] p2) d1
|
||||
(Store {t3} (OffPtr <tt3> [o3] p3) d2
|
||||
(Store {t4} (OffPtr <tt4> [o4] p4) d3
|
||||
(Store {t5} (OffPtr <tt5> [o5] p5) d4
|
||||
(Zero {t6} [n] p6 _))))))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4) && isSamePtr(p4, p5) && isSamePtr(p5, p6)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& alignof(t4) <= alignof(t1)
|
||||
&& alignof(t5) <= alignof(t1)
|
||||
&& alignof(t6) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& registerizable(b, t3)
|
||||
&& registerizable(b, t4)
|
||||
&& registerizable(b, t5)
|
||||
&& n >= o2 + sizeof(t2)
|
||||
&& n >= o3 + sizeof(t3)
|
||||
&& n >= o4 + sizeof(t4)
|
||||
&& n >= o5 + sizeof(t5)
|
||||
-> (Store {t2} (OffPtr <tt2> [o2] dst) d1
|
||||
(Store {t3} (OffPtr <tt3> [o3] dst) d2
|
||||
(Store {t4} (OffPtr <tt4> [o4] dst) d3
|
||||
(Store {t5} (OffPtr <tt5> [o5] dst) d4
|
||||
(Zero {t1} [n] dst mem)))))
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(VarDef
|
||||
(Store {t2} op2:(OffPtr <tt2> [o2] p2) d1
|
||||
(Zero {t3} [n] p3 _))))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& n >= o2 + sizeof(t2)
|
||||
-> (Store {t2} (OffPtr <tt2> [o2] dst) d1
|
||||
(Zero {t1} [n] dst mem))
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(VarDef
|
||||
(Store {t2} (OffPtr <tt2> [o2] p2) d1
|
||||
(Store {t3} (OffPtr <tt3> [o3] p3) d2
|
||||
(Zero {t4} [n] p4 _)))))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& alignof(t4) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& registerizable(b, t3)
|
||||
&& n >= o2 + sizeof(t2)
|
||||
&& n >= o3 + sizeof(t3)
|
||||
-> (Store {t2} (OffPtr <tt2> [o2] dst) d1
|
||||
(Store {t3} (OffPtr <tt3> [o3] dst) d2
|
||||
(Zero {t1} [n] dst mem)))
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(VarDef
|
||||
(Store {t2} (OffPtr <tt2> [o2] p2) d1
|
||||
(Store {t3} (OffPtr <tt3> [o3] p3) d2
|
||||
(Store {t4} (OffPtr <tt4> [o4] p4) d3
|
||||
(Zero {t5} [n] p5 _))))))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4) && isSamePtr(p4, p5)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& alignof(t4) <= alignof(t1)
|
||||
&& alignof(t5) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& registerizable(b, t3)
|
||||
&& registerizable(b, t4)
|
||||
&& n >= o2 + sizeof(t2)
|
||||
&& n >= o3 + sizeof(t3)
|
||||
&& n >= o4 + sizeof(t4)
|
||||
-> (Store {t2} (OffPtr <tt2> [o2] dst) d1
|
||||
(Store {t3} (OffPtr <tt3> [o3] dst) d2
|
||||
(Store {t4} (OffPtr <tt4> [o4] dst) d3
|
||||
(Zero {t1} [n] dst mem))))
|
||||
(Move {t1} [n] dst p1
|
||||
mem:(VarDef
|
||||
(Store {t2} (OffPtr <tt2> [o2] p2) d1
|
||||
(Store {t3} (OffPtr <tt3> [o3] p3) d2
|
||||
(Store {t4} (OffPtr <tt4> [o4] p4) d3
|
||||
(Store {t5} (OffPtr <tt5> [o5] p5) d4
|
||||
(Zero {t6} [n] p6 _)))))))
|
||||
&& isSamePtr(p1, p2) && isSamePtr(p2, p3) && isSamePtr(p3, p4) && isSamePtr(p4, p5) && isSamePtr(p5, p6)
|
||||
&& alignof(t2) <= alignof(t1)
|
||||
&& alignof(t3) <= alignof(t1)
|
||||
&& alignof(t4) <= alignof(t1)
|
||||
&& alignof(t5) <= alignof(t1)
|
||||
&& alignof(t6) <= alignof(t1)
|
||||
&& registerizable(b, t2)
|
||||
&& registerizable(b, t3)
|
||||
&& registerizable(b, t4)
|
||||
&& registerizable(b, t5)
|
||||
&& n >= o2 + sizeof(t2)
|
||||
&& n >= o3 + sizeof(t3)
|
||||
&& n >= o4 + sizeof(t4)
|
||||
&& n >= o5 + sizeof(t5)
|
||||
-> (Store {t2} (OffPtr <tt2> [o2] dst) d1
|
||||
(Store {t3} (OffPtr <tt3> [o3] dst) d2
|
||||
(Store {t4} (OffPtr <tt4> [o4] dst) d3
|
||||
(Store {t5} (OffPtr <tt5> [o5] dst) d4
|
||||
(Zero {t1} [n] dst mem)))))
|
||||
|
||||
@ -456,6 +456,50 @@ func isSamePtr(p1, p2 *Value) bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// disjoint reports whether the memory region specified by [p1:p1+n1)
|
||||
// does not overlap with [p2:p2+n2).
|
||||
// A return value of false does not imply the regions overlap.
|
||||
func disjoint(p1 *Value, n1 int64, p2 *Value, n2 int64) bool {
|
||||
if n1 == 0 || n2 == 0 {
|
||||
return true
|
||||
}
|
||||
if p1 == p2 {
|
||||
return false
|
||||
}
|
||||
baseAndOffset := func(ptr *Value) (base *Value, offset int64) {
|
||||
base, offset = ptr, 0
|
||||
if base.Op == OpOffPtr {
|
||||
offset += base.AuxInt
|
||||
base = base.Args[0]
|
||||
}
|
||||
return base, offset
|
||||
}
|
||||
p1, off1 := baseAndOffset(p1)
|
||||
p2, off2 := baseAndOffset(p2)
|
||||
if isSamePtr(p1, p2) {
|
||||
return !overlap(off1, n1, off2, n2)
|
||||
}
|
||||
// p1 and p2 are not the same, so if they are both OpAddrs then
|
||||
// they point to different variables.
|
||||
// If one pointer is on the stack and the other is an argument
|
||||
// then they can't overlap.
|
||||
switch p1.Op {
|
||||
case OpAddr:
|
||||
if p2.Op == OpAddr || p2.Op == OpSP {
|
||||
return true
|
||||
}
|
||||
return p2.Op == OpArg && p1.Args[0].Op == OpSP
|
||||
case OpArg:
|
||||
if p2.Op == OpSP {
|
||||
return true
|
||||
}
|
||||
return p2.Op == OpAddr && p2.Args[0].Op == OpSP
|
||||
case OpSP:
|
||||
return p2.Op == OpAddr || p2.Op == OpArg || p2.Op == OpSP
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// moveSize returns the number of bytes an aligned MOV instruction moves
|
||||
func moveSize(align int64, c *Config) int64 {
|
||||
switch {
|
||||
@ -879,3 +923,30 @@ func arm64BFWidth(mask, rshift int64) int64 {
|
||||
}
|
||||
return nto(shiftedMask)
|
||||
}
|
||||
|
||||
// sizeof returns the size of t in bytes.
|
||||
// It will panic if t is not a *types.Type.
|
||||
func sizeof(t interface{}) int64 {
|
||||
return t.(*types.Type).Size()
|
||||
}
|
||||
|
||||
// alignof returns the alignment of t in bytes.
|
||||
// It will panic if t is not a *types.Type.
|
||||
func alignof(t interface{}) int64 {
|
||||
return t.(*types.Type).Alignment()
|
||||
}
|
||||
|
||||
// registerizable reports whether t is a primitive type that fits in
|
||||
// a register. It assumes float64 values will always fit into registers
|
||||
// even if that isn't strictly true.
|
||||
// It will panic if t is not a *types.Type.
|
||||
func registerizable(b *Block, t interface{}) bool {
|
||||
typ := t.(*types.Type)
|
||||
if typ.IsPtrShaped() || typ.IsFloat() {
|
||||
return true
|
||||
}
|
||||
if typ.IsInteger() {
|
||||
return typ.Size() <= b.Func.Config.RegSize
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@ -93,8 +93,10 @@ func TestUnaligned64(t *testing.T) {
|
||||
}
|
||||
|
||||
x := make([]uint32, 4)
|
||||
up64 := (*uint64)(unsafe.Pointer(&x[1])) // misaligned
|
||||
p64 := (*int64)(unsafe.Pointer(&x[1])) // misaligned
|
||||
u := unsafe.Pointer(uintptr(unsafe.Pointer(&x[0])) | 4) // force alignment to 4
|
||||
|
||||
up64 := (*uint64)(u) // misaligned
|
||||
p64 := (*int64)(u) // misaligned
|
||||
|
||||
shouldPanic(t, "Load64", func() { atomic.Load64(up64) })
|
||||
shouldPanic(t, "Loadint64", func() { atomic.Loadint64(p64) })
|
||||
|
||||
@ -11,22 +11,81 @@ import "runtime"
|
||||
// This file contains code generation tests related to the use of the
|
||||
// stack.
|
||||
|
||||
// check that stack stores are optimized away
|
||||
// Check that stack stores are optimized away.
|
||||
|
||||
// 386:"TEXT\t.*, [$]0-4"
|
||||
// amd64:"TEXT\t.*, [$]0-8"
|
||||
// arm:"TEXT\t.*, [$]-4-4"
|
||||
// arm64:"TEXT\t.*, [$]-8-8"
|
||||
// s390x:"TEXT\t.*, [$]0-8"
|
||||
// ppc64le:"TEXT\t.*, [$]0-8"
|
||||
// mips:"TEXT\t.*, [$]-4-4"
|
||||
// 386:"TEXT\t.*, [$]0-"
|
||||
// amd64:"TEXT\t.*, [$]0-"
|
||||
// arm:"TEXT\t.*, [$]-4-"
|
||||
// arm64:"TEXT\t.*, [$]-8-"
|
||||
// mips:"TEXT\t.*, [$]-4-"
|
||||
// ppc64le:"TEXT\t.*, [$]0-"
|
||||
// s390x:"TEXT\t.*, [$]0-"
|
||||
func StackStore() int {
|
||||
var x int
|
||||
return *(&x)
|
||||
}
|
||||
|
||||
type T struct {
|
||||
A, B, C, D int // keep exported fields
|
||||
x, y, z int // reset unexported fields
|
||||
}
|
||||
|
||||
// Check that large structs are cleared directly (issue #24416).
|
||||
|
||||
// 386:"TEXT\t.*, [$]0-"
|
||||
// amd64:"TEXT\t.*, [$]0-"
|
||||
// arm:"TEXT\t.*, [$]0-" (spills return address)
|
||||
// arm64:"TEXT\t.*, [$]-8-"
|
||||
// mips:"TEXT\t.*, [$]-4-"
|
||||
// ppc64le:"TEXT\t.*, [$]0-"
|
||||
// s390x:"TEXT\t.*, [$]0-"
|
||||
func ZeroLargeStruct(x *T) {
|
||||
t := T{}
|
||||
*x = t
|
||||
}
|
||||
|
||||
// Check that structs are partially initialised directly (issue #24386).
|
||||
|
||||
// Notes:
|
||||
// - 386 fails due to spilling a register
|
||||
// amd64:"TEXT\t.*, [$]0-"
|
||||
// arm:"TEXT\t.*, [$]0-" (spills return address)
|
||||
// arm64:"TEXT\t.*, [$]-8-"
|
||||
// ppc64le:"TEXT\t.*, [$]0-"
|
||||
// s390x:"TEXT\t.*, [$]0-"
|
||||
// Note: that 386 currently has to spill a register.
|
||||
func KeepWanted(t *T) {
|
||||
*t = T{A: t.A, B: t.B, C: t.C, D: t.D}
|
||||
}
|
||||
|
||||
// Check that small array operations avoid using the stack (issue #15925).
|
||||
|
||||
// Notes:
|
||||
// - 386 fails due to spilling a register
|
||||
// - arm & mips fail due to softfloat calls
|
||||
// amd64:"TEXT\t.*, [$]0-"
|
||||
// arm64:"TEXT\t.*, [$]-8-"
|
||||
// ppc64le:"TEXT\t.*, [$]0-"
|
||||
// s390x:"TEXT\t.*, [$]0-"
|
||||
func ArrayAdd64(a, b [4]float64) [4]float64 {
|
||||
return [4]float64{a[0] + b[0], a[1] + b[1], a[2] + b[2], a[3] + b[3]}
|
||||
}
|
||||
|
||||
// Check that small array initialization avoids using the stack.
|
||||
|
||||
// 386:"TEXT\t.*, [$]0-"
|
||||
// amd64:"TEXT\t.*, [$]0-"
|
||||
// arm:"TEXT\t.*, [$]0-" (spills return address)
|
||||
// arm64:"TEXT\t.*, [$]-8-"
|
||||
// mips:"TEXT\t.*, [$]-4-"
|
||||
// ppc64le:"TEXT\t.*, [$]0-"
|
||||
// s390x:"TEXT\t.*, [$]0-"
|
||||
func ArrayInit(i, j int) [4]int {
|
||||
return [4]int{i, 0, j, 0}
|
||||
}
|
||||
|
||||
// Check that assembly output has matching offset and base register
|
||||
// (Issue #21064).
|
||||
// (issue #21064).
|
||||
|
||||
// amd64:`.*b\+24\(SP\)`
|
||||
// arm:`.*b\+4\(FP\)`
|
||||
|
||||
@ -13,6 +13,9 @@
|
||||
|
||||
package p
|
||||
|
||||
import "runtime"
|
||||
|
||||
func f() { // ERROR "stack frame too large"
|
||||
_ = [][]int{1e9: []int{}}
|
||||
x := [][]int{1e9: []int{}}
|
||||
runtime.KeepAlive(x)
|
||||
}
|
||||
|
||||
Loading…
Reference in New Issue
Block a user