cmd/compile/internal/ssa: reduce location list memory use

Put everything that showed up in the allocation profile into the cache,
and reuse it across functions.

After this CL, the overhead of enabling location lists is getting
pretty close to the desired 5%:

compilecmp -all -beforeflags -dwarflocationlists=0 -afterflags -dwarflocationlists=1 -n 30 4ebad42292b6a4090faf37753dd768d2965e38c4 4ebad42292b6a4090faf37753dd768d2965e38c4
compilecmp  -dwarflocationlists=0 4ebad42292b6a4090faf37753dd768d2965e38c4  -dwarflocationlists=1 4ebad42292b6a4090faf37753dd768d2965e38c4
benchstat -geomean  /tmp/869550129 /tmp/143495132
completed   30 of   30, estimated time remaining 0s (eta 3:24PM)
name        old time/op       new time/op       delta
Template          199ms ± 4%        209ms ± 6%   +5.17%  (p=0.000 n=29+30)
Unicode          99.2ms ± 8%      100.5ms ± 6%     ~     (p=0.112 n=30+30)
GoTypes           642ms ± 3%        684ms ± 3%   +6.54%  (p=0.000 n=29+30)
SSA               8.00s ± 1%        8.71s ± 1%   +8.78%  (p=0.000 n=29+29)
Flate             129ms ± 7%        134ms ± 5%   +3.77%  (p=0.000 n=30+30)
GoParser          157ms ± 4%        164ms ± 5%   +4.35%  (p=0.000 n=29+30)
Reflect           428ms ± 3%        450ms ± 4%   +5.09%  (p=0.000 n=30+30)
Tar               195ms ± 5%        204ms ± 8%   +4.78%  (p=0.000 n=30+30)
XML               228ms ± 4%        241ms ± 4%   +5.62%  (p=0.000 n=30+29)
StdCmd            15.4s ± 1%        16.7s ± 1%   +8.29%  (p=0.000 n=29+29)
[Geo mean]        476ms             502ms        +5.35%

name        old user-time/op  new user-time/op  delta
Template          294ms ±18%        304ms ±15%     ~     (p=0.242 n=29+29)
Unicode           182ms ±27%        172ms ±28%     ~     (p=0.104 n=30+30)
GoTypes           957ms ±15%       1016ms ±12%   +6.16%  (p=0.000 n=30+30)
SSA               13.3s ± 5%        14.3s ± 3%   +7.32%  (p=0.000 n=30+28)
Flate             188ms ±17%        193ms ±17%     ~     (p=0.288 n=28+29)
GoParser          232ms ±16%        238ms ±13%     ~     (p=0.065 n=30+29)
Reflect           585ms ±13%        620ms ±10%   +5.88%  (p=0.000 n=30+30)
Tar               298ms ±21%        332ms ±23%  +11.32%  (p=0.000 n=30+30)
XML               329ms ±17%        343ms ±12%   +4.18%  (p=0.032 n=30+30)
[Geo mean]        492ms             513ms        +4.13%

name        old alloc/op      new alloc/op      delta
Template         38.3MB ± 0%       40.3MB ± 0%   +5.29%  (p=0.000 n=30+30)
Unicode          29.3MB ± 0%       29.6MB ± 0%   +1.28%  (p=0.000 n=30+29)
GoTypes           110MB ± 0%        118MB ± 0%   +6.97%  (p=0.000 n=29+30)
SSA              1.48GB ± 0%       1.61GB ± 0%   +9.06%  (p=0.000 n=30+30)
Flate            24.8MB ± 0%       26.0MB ± 0%   +4.99%  (p=0.000 n=29+30)
GoParser         30.9MB ± 0%       32.2MB ± 0%   +4.20%  (p=0.000 n=30+30)
Reflect          76.8MB ± 0%       80.6MB ± 0%   +4.97%  (p=0.000 n=30+30)
Tar              39.6MB ± 0%       41.7MB ± 0%   +5.22%  (p=0.000 n=29+30)
XML              42.0MB ± 0%       45.4MB ± 0%   +8.22%  (p=0.000 n=29+30)
[Geo mean]       63.9MB            67.5MB        +5.56%

name        old allocs/op     new allocs/op     delta
Template           383k ± 0%         405k ± 0%   +5.69%  (p=0.000 n=30+30)
Unicode            343k ± 0%         346k ± 0%   +0.98%  (p=0.000 n=30+27)
GoTypes           1.15M ± 0%        1.22M ± 0%   +6.17%  (p=0.000 n=29+29)
SSA               12.2M ± 0%        13.2M ± 0%   +8.15%  (p=0.000 n=30+30)
Flate              234k ± 0%         249k ± 0%   +6.44%  (p=0.000 n=30+30)
GoParser           315k ± 0%         332k ± 0%   +5.31%  (p=0.000 n=30+28)
Reflect            972k ± 0%        1010k ± 0%   +3.89%  (p=0.000 n=30+30)
Tar                394k ± 0%         415k ± 0%   +5.35%  (p=0.000 n=28+30)
XML                404k ± 0%         429k ± 0%   +6.31%  (p=0.000 n=29+29)
[Geo mean]         651k              686k        +5.35%

Change-Id: Ia005a8d6b33ce9f8091322f004376a3d6e5c1a94
Reviewed-on: https://go-review.googlesource.com/89357
Run-TryBot: Heschi Kreinick <heschi@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: David Chase <drchase@google.com>

1 files changed, 23 insertions, 0 deletions

diff --git a/src/cmd/compile/internal/ssa/cache.go b/src/cmd/compile/internal/ssa/cache.go
index f1018da497..caaac0b387 100644
--- a/src/cmd/compile/internal/ssa/cache.go
+++ b/src/cmd/compile/internal/ssa/cache.go
@@ -20,6 +20,16 @@ type Cache struct {
 
 	domblockstore []ID         // scratch space for computing dominators
 	scrSparse     []*sparseSet // scratch sparse sets to be re-used.
+
+	blockDebug      []BlockDebug
+	valueNames      [][]SlotID
+	slotLocs        []VarLoc
+	regContents     [][]SlotID
+	pendingEntries  []pendingEntry
+	pendingSlotLocs []VarLoc
+
+	liveSlotSliceBegin int
+	liveSlots          []liveSlot
 }
 
 func (c *Cache) Reset() {
@@ -38,4 +48,17 @@ func (c *Cache) Reset() {
 	for i := range xl {
 		xl[i] = nil
 	}
+
+	c.liveSlots = c.liveSlots[:0]
+	c.liveSlotSliceBegin = 0
+}
+
+func (c *Cache) AppendLiveSlot(ls liveSlot) {
+	c.liveSlots = append(c.liveSlots, ls)
+}
+
+func (c *Cache) GetLiveSlotSlice() []liveSlot {
+	s := c.liveSlots[c.liveSlotSliceBegin:]
+	c.liveSlotSliceBegin = len(c.liveSlots)
+	return s
 }