如何解释 iTLB-loads 小于 iTLB-load-misses

     1,262,817      dTLB-loads                                                  
        13,950      dTLB-load-misses          #    1.10% of all dTLB cache hits 
            75      iTLB-loads                                                  
         6,882      iTLB-load-misses          # 9176.00% of all iTLB cache hits 

   3.999720948 seconds time elapsed

On your Broadwell processor, perf maps iTLB-loads to ITLB_MISSES.STLB_HIT, which represents the event of a TLB lookup that misses the L1 ITLB but hits the unified TLB for all page sizes, and iTLB-load-misses to ITLB_MISSES.MISS_CAUSES_A_WALK, which represents the event of a TLB lookup that misses both the L1 ITLB and the unified TLB (causing a page walk) for all page sizes. Therefore, iTLB-load-misses can be larger or smaller than or equal to iTLB-loads. They are independent events.

https://stackoverflow.com/questions/49933319/how-to-interpret-perf-itlb-loads-itlb-load-misses

# 考虑增加某个计数,会不会提高socre import numpy as np from sklearn.linear_model import LinearRegression # from sklearn.metrics import mean_squared_error file_soft = "/home/maillee/chip_temp_predict/data_handle/ftc_to_select_event/soft_event_ftc.xlsx" file_hard = "/home/maillee/chip_temp_predict/data_handle/ftc_to_select_event/hard_event_ftc.xlsx" file_hard_cache = "/home/maillee/chip_temp_predict/data_handle/ftc_to_select_event/hard_cahce_event_ftc.xlsx" pd_data_soft = pd.read_excel(file_soft,index_col=0) pd_data_hard = pd.read_excel(file_hard,index_col=0) pd_data_hard_cache = pd.read_excel(file_hard_cache,index_col=0) pd_y = pd_data_hard_cache['cores-power'] not_selected_event = ['branch-misses','bus-cycles','cache-misses','instructions', 'ref-cycles','L1-dcache-load-misses', 'L1-dcache-stores','L1-icache-load-misses', 'LLC-load-misses','LLC-store-misses','LLC-stores', 'branch-load-misses','dTLB-load-misses','dTLB-loads', 'dTLB-store-misses','dTLB-stores','iTLB-load-misses', 'iTLB-loads','node-load-misses','node-loads','node-store-misses', 'node-stores','alignment-faults','bpf-output','cgroup-switches', 'cpu-migrations','dummy','emulation-faults','major-faults','minor-faults', 'page-faults','task-clock',] count =0 pd_x = pd.concat([pd_data_hard,pd_data_hard_cache,pd_data_soft],axis=1,join='outer') for i in not_selected_event: count = count+1 pd_x =pd.concat(pd_x[i],pd_x[['cpu-clock','context-switches', 'branch-instructions','cpu-cycles','cache-references', 'L1-dcache-loads','LLC-loads','branch-loads']],axis=1,join='outer') model = LinearRegression().fit(pd_x, pd_y) # print(model.score(pd_x,pd_y)) #R2 score y_pred = model.predict(pd_x) # plt.plot(y_pred) # plt.plot(pd_y) mse = mean_squared_error(pd_y, y_pred) print(count,i,model.score(pd_x,pd_y), mse,'\n') woatis wring
最新发布
06-07
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值