libpfm_intel_snbep_unc_cbo man page
libpfm_intel_snbep_unc_cbo — support for Intel Sandy Bridge-EP C-Box uncore PMU
#include <perfmon/pfmlib.h> PMU name: snbep_unc_cbo[0-7] PMU desc: Intel Sandy Bridge-EP C-Box uncore PMU
The library supports the Intel Sandy Bridge C-Box (coherency engine) uncore PMU. This PMU model only exists on Sandy Bridge model 45. There is one C-box PMU per physical core. Therefore there are eight identical C-Box PMU instances numbered frmo 0 to 7. On dual-socket systems, the number refers to the C-Box PMU on the socket where the program runs. For instance, if running on CPU8, then snbep_unc_cbo0 refers to the C-Box for physical core 0 on socket 1. Conversely, if running on CPU0, then the same snbep_unc_cbo0 refers to the C-Box for physical core 0 but on socket 0.
Each C-Box PMU implements 4 generic counters and a filter register used only with certain events and umasks.
The following modifiers are supported on Intel Sandy Bridge C-Box uncore PMU:
Invert the meaning of the event. The counter will now count C-Box cycles in which the event is not occurring. This is a boolean modifier
Enable edge detection, i.e., count only when there is a state transition from no occurrence of the event to at least one occurrence. This modifier must be combined with a threshold modifier (t) with a value greater or equal to one. This is a boolean modifier.
Set the threshold value. When set to a non-zero value, the counter counts the number of C-Box cycles in which the number of occurrences of the event is greater or equal to the threshold. This is an integer modifier with values in the range [0:255].
Node filter. Certain events, such as UNC_C_LLC_LOOKUP, UNC_C_LLC_VICTIMS, provide a NID umask. Sometimes the NID is combined with other filtering capabilities, such as opcodes. The node filter is an 8-bit max bitmask. A node corresponds to a processor socket. The legal values therefore depend on the underlying hardware configuration. For dual-socket systems, the bitmask has two valid bits [0:1].
Core Filter. This is a 3-bit filter which is used to filter based on physical core origin of the C-Box request. Possible values are 0-7. If the filter is not specified, then no filtering takes place.
Thread Filter. This is a 1-bit filter which is used to filter C-Box requests based on logical processor (hyper-thread) identification. Possibles values are 0-1. If the filter is not specified, then no filtering takes place.
Certain events, such as UNC_C_TOR_INSERTS supports opcode matching on the C-BOX transaction type. To use this feature, first an opcode matching umask must be selected, e.g., MISS_OPCODE. Second, the opcode to match on must be selected via a second umask among the OPC_* umasks. For instance, UNC_C_TOR_INSERTS:OPCODE:OPC_RFO, counts the number of TOR insertions for RFO transactions.
Opcode matching may be combined with node filtering with certain umasks. In general the filtering support is encoded into the umask name, e.g., NID_OPCODE supports both node and opcode filtering. For instance, UNC_C_TOR_INSERTS:NID_OPCODE:OPC_RFO:nf=1.
Stephane Eranian <email@example.com>