Load Latency PEBS

Mohamed_Husain — Mon, 04 Nov 2013 06:36:35 GMT

Hi,

I was measuring the load latencies in my core i5 2450 using PEBS + load latency feature of the PMU. The document says , latency value is measured in core cycles from micro-operation (uop) dispatch to when data is globally observable (GO). I have the following queries

1. What is meant by 'when data is globally observable' ?
2. The L1 latency is around 4-5 cycles. But when I measure it using the PEBS, I get L1 hit latency values of even >100 cycles also. ( It is a hit in dtlb/stlvb)

Can some one give a clarification

Thank you.

1) I think that "Globally

Bernard — Mon, 04 Nov 2013 07:51:44 GMT

1) I think that "Globally Observable" might be related to data beign seen and accessed by the software(registers and or memory location).

topic Load Latency PEBS in Software Tuning, Performance Optimization & Platform Monitoring

Load Latency PEBS

1) I think that "Globally