345 lines
13 KiB
Plaintext
345 lines
13 KiB
Plaintext
|
Using TopDown metrics in user space
|
||
|
|
-----------------------------------
|
||
|
|
|
||
|
|
Intel CPUs (since Sandy Bridge and Silvermont) support a TopDown
|
||
|
|
methodology to break down CPU pipeline execution into 4 bottlenecks:
|
||
|
|
frontend bound, backend bound, bad speculation, retiring.
|
||
|
|
|
||
|
|
For more details on Topdown see [1][5]
|
||
|
|
|
||
|
|
Traditionally this was implemented by events in generic counters
|
||
|
|
and specific formulas to compute the bottlenecks.
|
||
|
|
|
||
|
|
perf stat --topdown implements this.
|
||
|
|
|
||
|
|
Full Top Down includes more levels that can break down the
|
||
|
|
bottlenecks further. This is not directly implemented in perf,
|
||
|
|
but available in other tools that can run on top of perf,
|
||
|
|
such as toplev[2] or vtune[3]
|
||
|
|
|
||
|
|
New Topdown features in Ice Lake
|
||
|
|
===============================
|
||
|
|
|
||
|
|
With Ice Lake CPUs the TopDown metrics are directly available as
|
||
|
|
fixed counters and do not require generic counters. This allows
|
||
|
|
to collect TopDown always in addition to other events.
|
||
|
|
|
||
|
|
% perf stat -a --topdown -I1000
|
||
|
|
# time retiring bad speculation frontend bound backend bound
|
||
|
|
1.001281330 23.0% 15.3% 29.6% 32.1%
|
||
|
|
2.003009005 5.0% 6.8% 46.6% 41.6%
|
||
|
|
3.004646182 6.7% 6.7% 46.0% 40.6%
|
||
|
|
4.006326375 5.0% 6.4% 47.6% 41.0%
|
||
|
|
5.007991804 5.1% 6.3% 46.3% 42.3%
|
||
|
|
6.009626773 6.2% 7.1% 47.3% 39.3%
|
||
|
|
7.011296356 4.7% 6.7% 46.2% 42.4%
|
||
|
|
8.012951831 4.7% 6.7% 47.5% 41.1%
|
||
|
|
...
|
||
|
|
|
||
|
|
This also enables measuring TopDown per thread/process instead
|
||
|
|
of only per core.
|
||
|
|
|
||
|
|
Using TopDown through RDPMC in applications on Ice Lake
|
||
|
|
======================================================
|
||
|
|
|
||
|
|
For more fine grained measurements it can be useful to
|
||
|
|
access the new directly from user space. This is more complicated,
|
||
|
|
but drastically lowers overhead.
|
||
|
|
|
||
|
|
On Ice Lake, there is a new fixed counter 3: SLOTS, which reports
|
||
|
|
"pipeline SLOTS" (cycles multiplied by core issue width) and a
|
||
|
|
metric register that reports slots ratios for the different bottleneck
|
||
|
|
categories.
|
||
|
|
|
||
|
|
The metrics counter is CPU model specific and is not available on older
|
||
|
|
CPUs.
|
||
|
|
|
||
|
|
Example code
|
||
|
|
============
|
||
|
|
|
||
|
|
Library functions to do the functionality described below
|
||
|
|
is also available in libjevents [4]
|
||
|
|
|
||
|
|
The application opens a group with fixed counter 3 (SLOTS) and any
|
||
|
|
metric event, and allow user programs to read the performance counters.
|
||
|
|
|
||
|
|
Fixed counter 3 is mapped to a pseudo event event=0x00, umask=04,
|
||
|
|
so the perf_event_attr structure should be initialized with
|
||
|
|
{ .config = 0x0400, .type = PERF_TYPE_RAW }
|
||
|
|
The metric events are mapped to the pseudo event event=0x00, umask=0x8X.
|
||
|
|
For example, the perf_event_attr structure can be initialized with
|
||
|
|
{ .config = 0x8000, .type = PERF_TYPE_RAW } for Retiring metric event
|
||
|
|
The Fixed counter 3 must be the leader of the group.
|
||
|
|
|
||
|
|
#include <linux/perf_event.h>
|
||
|
|
#include <sys/mman.h>
|
||
|
|
#include <sys/syscall.h>
|
||
|
|
#include <unistd.h>
|
||
|
|
|
||
|
|
/* Provide own perf_event_open stub because glibc doesn't */
|
||
|
|
__attribute__((weak))
|
||
|
|
int perf_event_open(struct perf_event_attr *attr, pid_t pid,
|
||
|
|
int cpu, int group_fd, unsigned long flags)
|
||
|
|
{
|
||
|
|
return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
|
||
|
|
}
|
||
|
|
|
||
|
|
/* Open slots counter file descriptor for current task. */
|
||
|
|
struct perf_event_attr slots = {
|
||
|
|
.type = PERF_TYPE_RAW,
|
||
|
|
.size = sizeof(struct perf_event_attr),
|
||
|
|
.config = 0x400,
|
||
|
|
.exclude_kernel = 1,
|
||
|
|
};
|
||
|
|
|
||
|
|
int slots_fd = perf_event_open(&slots, 0, -1, -1, 0);
|
||
|
|
if (slots_fd < 0)
|
||
|
|
... error ...
|
||
|
|
|
||
|
|
/* Memory mapping the fd permits _rdpmc calls from userspace */
|
||
|
|
void *slots_p = mmap(0, getpagesize(), PROT_READ, MAP_SHARED, slots_fd, 0);
|
||
|
|
if (!slot_p)
|
||
|
|
.... error ...
|
||
|
|
|
||
|
|
/*
|
||
|
|
* Open metrics event file descriptor for current task.
|
||
|
|
* Set slots event as the leader of the group.
|
||
|
|
*/
|
||
|
|
struct perf_event_attr metrics = {
|
||
|
|
.type = PERF_TYPE_RAW,
|
||
|
|
.size = sizeof(struct perf_event_attr),
|
||
|
|
.config = 0x8000,
|
||
|
|
.exclude_kernel = 1,
|
||
|
|
};
|
||
|
|
|
||
|
|
int metrics_fd = perf_event_open(&metrics, 0, -1, slots_fd, 0);
|
||
|
|
if (metrics_fd < 0)
|
||
|
|
... error ...
|
||
|
|
|
||
|
|
/* Memory mapping the fd permits _rdpmc calls from userspace */
|
||
|
|
void *metrics_p = mmap(0, getpagesize(), PROT_READ, MAP_SHARED, metrics_fd, 0);
|
||
|
|
if (!metrics_p)
|
||
|
|
... error ...
|
||
|
|
|
||
|
|
Note: the file descriptors returned by the perf_event_open calls must be memory
|
||
|
|
mapped to permit calls to the _rdpmd instruction. Permission may also be granted
|
||
|
|
by writing the /sys/devices/cpu/rdpmc sysfs node.
|
||
|
|
|
||
|
|
The RDPMC instruction (or _rdpmc compiler intrinsic) can now be used
|
||
|
|
to read slots and the topdown metrics at different points of the program:
|
||
|
|
|
||
|
|
#include <stdint.h>
|
||
|
|
#include <x86intrin.h>
|
||
|
|
|
||
|
|
#define RDPMC_FIXED (1 << 30) /* return fixed counters */
|
||
|
|
#define RDPMC_METRIC (1 << 29) /* return metric counters */
|
||
|
|
|
||
|
|
#define FIXED_COUNTER_SLOTS 3
|
||
|
|
#define METRIC_COUNTER_TOPDOWN_L1_L2 0
|
||
|
|
|
||
|
|
static inline uint64_t read_slots(void)
|
||
|
|
{
|
||
|
|
return _rdpmc(RDPMC_FIXED | FIXED_COUNTER_SLOTS);
|
||
|
|
}
|
||
|
|
|
||
|
|
static inline uint64_t read_metrics(void)
|
||
|
|
{
|
||
|
|
return _rdpmc(RDPMC_METRIC | METRIC_COUNTER_TOPDOWN_L1_L2);
|
||
|
|
}
|
||
|
|
|
||
|
|
Then the program can be instrumented to read these metrics at different
|
||
|
|
points.
|
||
|
|
|
||
|
|
It's not a good idea to do this with too short code regions,
|
||
|
|
as the parallelism and overlap in the CPU program execution will
|
||
|
|
cause too much measurement inaccuracy. For example instrumenting
|
||
|
|
individual basic blocks is definitely too fine grained.
|
||
|
|
|
||
|
|
_rdpmc calls should not be mixed with reading the metrics and slots counters
|
||
|
|
through system calls, as the kernel will reset these counters after each system
|
||
|
|
call.
|
||
|
|
|
||
|
|
Decoding metrics values
|
||
|
|
=======================
|
||
|
|
|
||
|
|
The value reported by read_metrics() contains four 8 bit fields
|
||
|
|
that represent a scaled ratio that represent the Level 1 bottleneck.
|
||
|
|
All four fields add up to 0xff (= 100%)
|
||
|
|
|
||
|
|
The binary ratios in the metric value can be converted to float ratios:
|
||
|
|
|
||
|
|
#define GET_METRIC(m, i) (((m) >> (i*8)) & 0xff)
|
||
|
|
|
||
|
|
/* L1 Topdown metric events */
|
||
|
|
#define TOPDOWN_RETIRING(val) ((float)GET_METRIC(val, 0) / 0xff)
|
||
|
|
#define TOPDOWN_BAD_SPEC(val) ((float)GET_METRIC(val, 1) / 0xff)
|
||
|
|
#define TOPDOWN_FE_BOUND(val) ((float)GET_METRIC(val, 2) / 0xff)
|
||
|
|
#define TOPDOWN_BE_BOUND(val) ((float)GET_METRIC(val, 3) / 0xff)
|
||
|
|
|
||
|
|
/*
|
||
|
|
* L2 Topdown metric events.
|
||
|
|
* Available on Sapphire Rapids and later platforms.
|
||
|
|
*/
|
||
|
|
#define TOPDOWN_HEAVY_OPS(val) ((float)GET_METRIC(val, 4) / 0xff)
|
||
|
|
#define TOPDOWN_BR_MISPREDICT(val) ((float)GET_METRIC(val, 5) / 0xff)
|
||
|
|
#define TOPDOWN_FETCH_LAT(val) ((float)GET_METRIC(val, 6) / 0xff)
|
||
|
|
#define TOPDOWN_MEM_BOUND(val) ((float)GET_METRIC(val, 7) / 0xff)
|
||
|
|
|
||
|
|
and then converted to percent for printing.
|
||
|
|
|
||
|
|
The ratios in the metric accumulate for the time when the counter
|
||
|
|
is enabled. For measuring programs it is often useful to measure
|
||
|
|
specific sections. For this it is needed to deltas on metrics.
|
||
|
|
|
||
|
|
This can be done by scaling the metrics with the slots counter
|
||
|
|
read at the same time.
|
||
|
|
|
||
|
|
Then it's possible to take deltas of these slots counts
|
||
|
|
measured at different points, and determine the metrics
|
||
|
|
for that time period.
|
||
|
|
|
||
|
|
slots_a = read_slots();
|
||
|
|
metric_a = read_metrics();
|
||
|
|
|
||
|
|
... larger code region ...
|
||
|
|
|
||
|
|
slots_b = read_slots()
|
||
|
|
metric_b = read_metrics()
|
||
|
|
|
||
|
|
# compute scaled metrics for measurement a
|
||
|
|
retiring_slots_a = GET_METRIC(metric_a, 0) * slots_a
|
||
|
|
bad_spec_slots_a = GET_METRIC(metric_a, 1) * slots_a
|
||
|
|
fe_bound_slots_a = GET_METRIC(metric_a, 2) * slots_a
|
||
|
|
be_bound_slots_a = GET_METRIC(metric_a, 3) * slots_a
|
||
|
|
|
||
|
|
# compute delta scaled metrics between b and a
|
||
|
|
retiring_slots = GET_METRIC(metric_b, 0) * slots_b - retiring_slots_a
|
||
|
|
bad_spec_slots = GET_METRIC(metric_b, 1) * slots_b - bad_spec_slots_a
|
||
|
|
fe_bound_slots = GET_METRIC(metric_b, 2) * slots_b - fe_bound_slots_a
|
||
|
|
be_bound_slots = GET_METRIC(metric_b, 3) * slots_b - be_bound_slots_a
|
||
|
|
|
||
|
|
Later the individual ratios of L1 metric events for the measurement period can
|
||
|
|
be recreated from these counts.
|
||
|
|
|
||
|
|
slots_delta = slots_b - slots_a
|
||
|
|
retiring_ratio = (float)retiring_slots / slots_delta
|
||
|
|
bad_spec_ratio = (float)bad_spec_slots / slots_delta
|
||
|
|
fe_bound_ratio = (float)fe_bound_slots / slots_delta
|
||
|
|
be_bound_ratio = (float)be_bound_slots / slota_delta
|
||
|
|
|
||
|
|
printf("Retiring %.2f%% Bad Speculation %.2f%% FE Bound %.2f%% BE Bound %.2f%%\n",
|
||
|
|
retiring_ratio * 100.,
|
||
|
|
bad_spec_ratio * 100.,
|
||
|
|
fe_bound_ratio * 100.,
|
||
|
|
be_bound_ratio * 100.);
|
||
|
|
|
||
|
|
The individual ratios of L2 metric events for the measurement period can be
|
||
|
|
recreated from L1 and L2 metric counters. (Available on Sapphire Rapids and
|
||
|
|
later platforms)
|
||
|
|
|
||
|
|
# compute scaled metrics for measurement a
|
||
|
|
heavy_ops_slots_a = GET_METRIC(metric_a, 4) * slots_a
|
||
|
|
br_mispredict_slots_a = GET_METRIC(metric_a, 5) * slots_a
|
||
|
|
fetch_lat_slots_a = GET_METRIC(metric_a, 6) * slots_a
|
||
|
|
mem_bound_slots_a = GET_METRIC(metric_a, 7) * slots_a
|
||
|
|
|
||
|
|
# compute delta scaled metrics between b and a
|
||
|
|
heavy_ops_slots = GET_METRIC(metric_b, 4) * slots_b - heavy_ops_slots_a
|
||
|
|
br_mispredict_slots = GET_METRIC(metric_b, 5) * slots_b - br_mispredict_slots_a
|
||
|
|
fetch_lat_slots = GET_METRIC(metric_b, 6) * slots_b - fetch_lat_slots_a
|
||
|
|
mem_bound_slots = GET_METRIC(metric_b, 7) * slots_b - mem_bound_slots_a
|
||
|
|
|
||
|
|
slots_delta = slots_b - slots_a
|
||
|
|
heavy_ops_ratio = (float)heavy_ops_slots / slots_delta
|
||
|
|
light_ops_ratio = retiring_ratio - heavy_ops_ratio;
|
||
|
|
|
||
|
|
br_mispredict_ratio = (float)br_mispredict_slots / slots_delta
|
||
|
|
machine_clears_ratio = bad_spec_ratio - br_mispredict_ratio;
|
||
|
|
|
||
|
|
fetch_lat_ratio = (float)fetch_lat_slots / slots_delta
|
||
|
|
fetch_bw_ratio = fe_bound_ratio - fetch_lat_ratio;
|
||
|
|
|
||
|
|
mem_bound_ratio = (float)mem_bound_slots / slota_delta
|
||
|
|
core_bound_ratio = be_bound_ratio - mem_bound_ratio;
|
||
|
|
|
||
|
|
printf("Heavy Operations %.2f%% Light Operations %.2f%% "
|
||
|
|
"Branch Mispredict %.2f%% Machine Clears %.2f%% "
|
||
|
|
"Fetch Latency %.2f%% Fetch Bandwidth %.2f%% "
|
||
|
|
"Mem Bound %.2f%% Core Bound %.2f%%\n",
|
||
|
|
heavy_ops_ratio * 100.,
|
||
|
|
light_ops_ratio * 100.,
|
||
|
|
br_mispredict_ratio * 100.,
|
||
|
|
machine_clears_ratio * 100.,
|
||
|
|
fetch_lat_ratio * 100.,
|
||
|
|
fetch_bw_ratio * 100.,
|
||
|
|
mem_bound_ratio * 100.,
|
||
|
|
core_bound_ratio * 100.);
|
||
|
|
|
||
|
|
Resetting metrics counters
|
||
|
|
==========================
|
||
|
|
|
||
|
|
Since the individual metrics are only 8bit they lose precision for
|
||
|
|
short regions over time because the number of cycles covered by each
|
||
|
|
fraction bit shrinks. So the counters need to be reset regularly.
|
||
|
|
|
||
|
|
When using the kernel perf API the kernel resets on every read.
|
||
|
|
So as long as the reading is at reasonable intervals (every few
|
||
|
|
seconds) the precision is good.
|
||
|
|
|
||
|
|
When using perf stat it is recommended to always use the -I option,
|
||
|
|
with no longer interval than a few seconds
|
||
|
|
|
||
|
|
perf stat -I 1000 --topdown ...
|
||
|
|
|
||
|
|
For user programs using RDPMC directly the counter can
|
||
|
|
be reset explicitly using ioctl:
|
||
|
|
|
||
|
|
ioctl(perf_fd, PERF_EVENT_IOC_RESET, 0);
|
||
|
|
|
||
|
|
This "opens" a new measurement period.
|
||
|
|
|
||
|
|
A program using RDPMC for TopDown should schedule such a reset
|
||
|
|
regularly, as in every few seconds.
|
||
|
|
|
||
|
|
Limits on Ice Lake
|
||
|
|
==================
|
||
|
|
|
||
|
|
Four pseudo TopDown metric events are exposed for the end-users,
|
||
|
|
topdown-retiring, topdown-bad-spec, topdown-fe-bound and topdown-be-bound.
|
||
|
|
They can be used to collect the TopDown value under the following
|
||
|
|
rules:
|
||
|
|
- All the TopDown metric events must be in a group with the SLOTS event.
|
||
|
|
- The SLOTS event must be the leader of the group.
|
||
|
|
- The PERF_FORMAT_GROUP flag must be applied for each TopDown metric
|
||
|
|
events
|
||
|
|
|
||
|
|
The SLOTS event and the TopDown metric events can be counting members of
|
||
|
|
a sampling read group. Since the SLOTS event must be the leader of a TopDown
|
||
|
|
group, the second event of the group is the sampling event.
|
||
|
|
For example, perf record -e '{slots, $sampling_event, topdown-retiring}:S'
|
||
|
|
|
||
|
|
Extension on Sapphire Rapids Server
|
||
|
|
===================================
|
||
|
|
The metrics counter is extended to support TMA method level 2 metrics.
|
||
|
|
The lower half of the register is the TMA level 1 metrics (legacy).
|
||
|
|
The upper half is also divided into four 8-bit fields for the new level 2
|
||
|
|
metrics. Four more TopDown metric events are exposed for the end-users,
|
||
|
|
topdown-heavy-ops, topdown-br-mispredict, topdown-fetch-lat and
|
||
|
|
topdown-mem-bound.
|
||
|
|
|
||
|
|
Each of the new level 2 metrics in the upper half is a subset of the
|
||
|
|
corresponding level 1 metric in the lower half. Software can deduce the
|
||
|
|
other four level 2 metrics by subtracting corresponding metrics as below.
|
||
|
|
|
||
|
|
Light_Operations = Retiring - Heavy_Operations
|
||
|
|
Machine_Clears = Bad_Speculation - Branch_Mispredicts
|
||
|
|
Fetch_Bandwidth = Frontend_Bound - Fetch_Latency
|
||
|
|
Core_Bound = Backend_Bound - Memory_Bound
|
||
|
|
|
||
|
|
|
||
|
|
[1] https://software.intel.com/en-us/top-down-microarchitecture-analysis-method-win
|
||
|
|
[2] https://github.com/andikleen/pmu-tools/wiki/toplev-manual
|
||
|
|
[3] https://software.intel.com/en-us/intel-vtune-amplifier-xe
|
||
|
|
[4] https://github.com/andikleen/pmu-tools/tree/master/jevents
|
||
|
|
[5] https://sites.google.com/site/analysismethods/yasin-pubs
|