Skip to content

Commit 71adc65

Browse files
ianlancetaylorianlancetaylor
committed
runtime: change time.now to ABIInternal
This reduces the number of instructions executed for time.now by nine, by eliminating the wrapper. Somehow BenchmarkNow is 0.2ns slower. On the other hand BenchmarkNowUnixNano is 0.8ns faster. name old time/op new time/op delta AfterFunc-12 66.7µs ± 4% 67.3µs ± 2% ~ (p=0.573 n=20+18) After-12 97.6µs ± 4% 97.4µs ± 4% ~ (p=0.758 n=20+20) Stop-12 66.7µs ±12% 64.8µs ±10% ~ (p=0.072 n=20+20) SimultaneousAfterFunc-12 109µs ± 0% 110µs ± 1% +1.47% (p=0.000 n=17+20) StartStop-12 31.9µs ±15% 32.7µs ±14% ~ (p=0.799 n=20+20) Reset-12 3.67µs ± 2% 3.68µs ± 2% ~ (p=0.132 n=20+20) Sleep-12 132µs ± 2% 133µs ± 2% +0.70% (p=0.035 n=20+19) Ticker-12 32.4µs ± 1% 32.3µs ± 2% ~ (p=0.270 n=20+19) TickerReset-12 3.71µs ± 2% 3.74µs ± 2% +0.89% (p=0.012 n=20+20) TickerResetNaive-12 65.7µs ±10% 67.2µs ±10% ~ (p=0.174 n=20+20) Now-12 29.6ns ± 1% 29.8ns ± 0% +0.78% (p=0.000 n=17+17) NowUnixNano-12 31.1ns ± 1% 30.3ns ± 0% -2.69% (p=0.000 n=19+18) NowUnixMilli-12 30.9ns ± 0% 31.1ns ± 0% +0.90% (p=0.000 n=18+20) NowUnixMicro-12 30.9ns ± 0% 31.1ns ± 1% +0.68% (p=0.000 n=20+18) Format-12 304ns ± 1% 301ns ± 2% -0.81% (p=0.004 n=18+19) FormatNow-12 187ns ± 2% 185ns ± 2% -0.90% (p=0.036 n=20+18) MarshalJSON-12 267ns ± 3% 265ns ± 3% -1.00% (p=0.004 n=18+18) MarshalText-12 267ns ± 2% 265ns ± 3% -0.87% (p=0.038 n=19+20) Parse-12 150ns ± 1% 149ns ± 1% -0.83% (p=0.000 n=18+20) ParseDuration-12 79.6ns ± 0% 80.1ns ± 1% +0.61% (p=0.000 n=20+20) Hour-12 4.42ns ± 1% 4.45ns ± 0% +0.83% (p=0.000 n=20+20) Second-12 4.42ns ± 0% 4.42ns ± 1% ~ (p=0.075 n=18+20) Year-12 11.1ns ± 1% 11.1ns ± 1% ~ (p=0.489 n=20+19) Day-12 14.8ns ± 1% 14.8ns ± 0% ~ (p=0.616 n=20+18) ISOWeek-12 17.2ns ± 1% 17.2ns ± 0% ~ (p=0.179 n=20+19) name old avg-late-ns new avg-late-ns delta ParallelTimerLatency-12 380k ± 4% 379k ± 3% ~ (p=0.879 n=20+19) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=1-12 137k ± 3% 137k ± 2% ~ (p=0.261 n=19+18) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=2-12 106k ±16% 95k ± 8% -9.76% (p=0.003 n=19+20) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=3-12 88.6k ±22% 74.6k ± 3% -15.78% (p=0.000 n=19+20) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=4-12 76.1k ±18% 70.8k ± 5% -7.04% (p=0.020 n=20+20) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=5-12 67.3k ±27% 65.6k ±13% ~ (p=0.211 n=16+18) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=6-12 59.5k ±24% 57.3k ±32% ~ (p=0.607 n=19+20) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=7-12 41.8k ±34% 46.2k ±33% +10.54% (p=0.039 n=17+20) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=8-12 57.5k ±37% 65.6k ±46% ~ (p=0.283 n=17+20) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=9-12 118k ±60% 136k ±59% ~ (p=0.169 n=19+18) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=10-12 3.66M ±236% 2.55M ±36% ~ (p=0.158 n=16+20) StaggeredTickerLatency/work-dur=2ms/tickers-per-P=1-12 81.7k ± 4% 80.7k ± 5% ~ (p=0.107 n=20+19) name old max-late-ns new max-late-ns delta ParallelTimerLatency-12 5.88M ±124% 7.28M ±183% ~ (p=0.640 n=20+20) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=1-12 384k ±17% 371k ±11% ~ (p=0.540 n=17+17) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=2-12 503k ±180% 373k ±19% ~ (p=0.057 n=17+18) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=3-12 519k ±129% 340k ±17% -34.47% (p=0.000 n=18+19) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=4-12 491k ±141% 341k ±26% -30.52% (p=0.015 n=18+17) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=5-12 457k ±123% 405k ±48% ~ (p=0.786 n=17+17) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=6-12 491k ±85% 502k ±74% ~ (p=0.916 n=18+19) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=7-12 572k ±100% 574k ±65% ~ (p=0.858 n=18+17) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=8-12 1.95M ±205% 1.65M ±155% ~ (p=0.641 n=18+19) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=9-12 7.77M ±104% 8.72M ±103% ~ (p=0.512 n=20+20) StaggeredTickerLatency/work-dur=300µs/tickers-per-P=10-12 29.5M ±187% 18.5M ±43% ~ (p=0.186 n=18+20) StaggeredTickerLatency/work-dur=2ms/tickers-per-P=1-12 981k ±14% 1033k ±12% +5.30% (p=0.048 n=20+18) Change-Id: Ie794a932a929b46053a6c3020b67d640b98d2335 Reviewed-on: https://go-review.googlesource.com/c/go/+/315369 Trust: Ian Lance Taylor <[email protected]> Run-TryBot: Ian Lance Taylor <[email protected]> TryBot-Result: Go Bot <[email protected]> Reviewed-by: Michael Knyszek <[email protected]>
1 parent 146e8d4 commit 71adc65

File tree

1 file changed

+19
-18
lines changed

1 file changed

+19
-18
lines changed

‎src/runtime/time_linux_amd64.s

+19-18
Original file line numberDiff line numberDiff line change
@@ -12,14 +12,11 @@
1212
#define SYS_clock_gettime 228
1313

1414
// func time.now() (sec int64, nsec int32, mono int64)
15-
TEXT time·now(SB),NOSPLIT,$16-24
15+
TEXT time·now<ABIInternal>(SB),NOSPLIT,$16-24
1616
MOVQ SP, R12 // Save old SP; R12 unchanged by C code.
1717

1818
MOVQ g_m(R14), BX // BX unchanged by C code.
1919

20-
// Store CLOCK_REALTIME results directly to return space.
21-
LEAQ sec+0(FP), SI
22-
2320
// Set vdsoPC and vdsoSP for SIGPROF traceback.
2421
// Save the old values on stack and restore them on exit,
2522
// so this function is reentrant.
@@ -28,9 +25,10 @@ TEXT time·now(SB),NOSPLIT,$16-24
2825
MOVQ CX, 0(SP)
2926
MOVQ DX, 8(SP)
3027

31-
MOVQ -8(SI), CX // Sets CX to function return address.
28+
LEAQ sec+0(FP), DX
29+
MOVQ -8(DX), CX // Sets CX to function return address.
3230
MOVQ CX, m_vdsoPC(BX)
33-
MOVQ SI, m_vdsoSP(BX)
31+
MOVQ DX, m_vdsoSP(BX)
3432

3533
CMPQ R14, m_curg(BX) // Only switch if on curg.
3634
JNE noswitch
@@ -39,10 +37,11 @@ TEXT time·now(SB),NOSPLIT,$16-24
3937
MOVQ (g_sched+gobuf_sp)(DX), SP // Set SP to g0 stack
4038

4139
noswitch:
42-
SUBQ $16, SP // Space for monotonic time results
40+
SUBQ $32, SP // Space for two time results
4341
ANDQ $~15, SP // Align for C code
4442

4543
MOVL $0, DI // CLOCK_REALTIME
44+
LEAQ 16(SP), SI
4645
MOVQ runtime·vdsoClockgettimeSym(SB), AX
4746
CMPQ AX, $0
4847
JEQ fallback
@@ -54,25 +53,27 @@ noswitch:
5453
CALL AX
5554

5655
ret:
57-
MOVQ 0(SP), AX // sec
58-
MOVQ 8(SP), DX // nsec
56+
MOVQ 16(SP), AX // realtime sec
57+
MOVQ 24(SP), DI // realtime nsec (moved to BX below)
58+
MOVQ 0(SP), CX // monotonic sec
59+
IMULQ $1000000000, CX
60+
MOVQ 8(SP), DX // monotonic nsec
5961

6062
MOVQ R12, SP // Restore real SP
63+
6164
// Restore vdsoPC, vdsoSP
6265
// We don't worry about being signaled between the two stores.
6366
// If we are not in a signal handler, we'll restore vdsoSP to 0,
6467
// and no one will care about vdsoPC. If we are in a signal handler,
6568
// we cannot receive another signal.
66-
MOVQ 8(SP), CX
67-
MOVQ CX, m_vdsoSP(BX)
68-
MOVQ 0(SP), CX
69-
MOVQ CX, m_vdsoPC(BX)
69+
MOVQ 8(SP), SI
70+
MOVQ SI, m_vdsoSP(BX)
71+
MOVQ 0(SP), SI
72+
MOVQ SI, m_vdsoPC(BX)
7073

71-
// sec is in AX, nsec in DX
72-
// return nsec in AX
73-
IMULQ $1000000000, AX
74-
ADDQ DX, AX
75-
MOVQ AX, mono+16(FP)
74+
// set result registers; AX is already correct
75+
MOVQ DI, BX
76+
ADDQ DX, CX
7677
RET
7778

7879
fallback:

0 commit comments

Comments
 (0)