1
0
mirror of https://github.com/golang/go synced 2024-11-19 23:24:45 -07:00
go/src/pkg/runtime/atomic_386.c

33 lines
541 B
C
Raw Normal View History

runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
#include "runtime.h"
#pragma textflag 7
uint32
runtime·atomicload(uint32 volatile* addr)
{
return *addr;
}
#pragma textflag 7
void*
runtime·atomicloadp(void* volatile* addr)
{
return *addr;
}
#pragma textflag 7
uint64
runtime·xadd64(uint64 volatile* addr, int64 v)
{
uint64 old;
old = *addr;
while(!runtime·cas64(addr, &old, old+v)) {
// nothing
}
return old+v;
}