Intel® Xeon® Processor E5-2600 Product Family Uncore Performance Monitoring
108
Reference Number: 327043-001
"speed" (for example, 8.0 GT/s), the "transfers" here refer to "fits". Therefore, in L0, the system
will transfer 1 "flit" at the rate of 1/4th the Intel® QPI speed. One can calculate the bandwidth of
the link by taking: flits*80b/time. Note that this is not the same as "data" bandwidth. For exam-
ple, when we are transfering a 64B cacheline across Intel® QPI, we will break it into 9 flits -- 1 with
header information and 8 with 64 bits of actual "data" and an additional 16 bits of other informa-
tion. To calculate "data" bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B
instead of 8B for L0p.
TxL_FLITS_G1
• Title:
Flits Transferred - Group 1
• Category:
FLITS_TX Events
• Event Code:
0x00
• Extra Select Bit:
Y
• Max. Inc/Cyc:
2,
Register Restrictions:
0-3
• Definition:
Counts the number of flits trasmitted across the Intel® QPI Link. This is one of three
"groups" that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes.
Each "flit" is made up of 80 bits of information (in addition to some ECC data). In full-width (L0)
mode, flits are made up of four "fits", each of which contains 20 bits of data (along with some addi-
tional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as
many fits to transmit a flit. When one talks about Intel® QPI "speed" (for example, 8.0 GT/s), the
"transfers" here refer to "fits". Therefore, in L0, the system will transfer 1 "flit" at the rate of 1/4th
the Intel® QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note
that this is not the same as "data" bandwidth. For example, when we are transfering a 64B cache-
line across Intel® QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of
actual "data" and an additional 16 bits of other information. To calculate "data" bandwidth, one
should therefore do: data flits * 8B / time.
Table 2-101. Unit Masks for TxL_FLITS_G0
Extension
umask
[15:8]
Description
IDLE
bxxxxxxx1
Idle and Null Flits:
Number of flits transmitted over Intel® QPI that do not hold protocol
payload. When Intel® QPI is not in a power saving state, it
continuously transmits flits across the link. When there are no
protocol flits to send, it will send IDLE and NULL flits across. These
flits sometimes do carry a payload, such as credit returns, but are
generall not considered part of the Intel® QPI bandwidth.
DATA
bxxxxxx1x
Data Tx Flits:
Number of data flits transmitted over Intel® QPI. Each flit contains
64b of data. This includes both DRS and NCB data flits (coherent and
non-coherent). This can be used to calculate the data bandwidth of
the Intel® QPI link. One can get a good picture of the Intel® QPI-
link characteristics by evaluating the protocol flits, data flits, and idle/
null flits. This does not include the header flits that go in data
packets.
NON_DATA
bxxxxx1xx
Non-Data protocol Tx Flits:
Number of non-NULL non-data flits transmitted across Intel® QPI.
This basically tracks the protocol overhead on the Intel® QPI link.
One can get a good picture of the Intel® QPI-link characteristics by
evaluating the protocol flits, data flits, and idle/null flits. This
includes the header flits for data packets.
