Lines Matching +full:user +full:- +full:programmable

45 .Bl -tag -width "Li PMC_CLASS_IAP"
47 Fixed-function counters that count only one hardware event per counter.
49 Programmable counters that may be configured to count one of a defined
59 .%B "Intel(R) 64 and IA-32 Architectures Software Developer's Manual"
61 .%N "Order Number: 325462-045US"
68 .Ss HASWELL PROGRAMMABLE PMCS
69 The programmable PMCs support the following capabilities:
70 .Bl -column "PMC_CAP_INTERRUPT" "Support"
87 .Bl -tag -width indent
89 Configure the Off-core Response bits.
90 .Bl -tag -width indent
128 M-state initial lookup stat in L3.
130 E-state.
132 S-state.
134 F-state.
138 No details on snoop-related information.
148 Hit denotes a cache-line was valid before snoop effect.
159 A snoop was needed and it HitM-ed in local or remote cache.
160 HitM denotes a cache-line was in modified state before effect as a results of snoop.
166 Target was non-DRAM system address.
174 Configure the PMC to count the number of de-asserted to asserted
199 .Ss Event Specifiers (Programmable PMCs)
200 Haswell programmable PMCs support the following events:
201 .Bl -tag -width indent
208 Speculative cache-line split load uops dispatched to
212 Speculative cache-line split Store-address uops
249 DTLB demand load misses with low part of linear-to-
264 Number of flags-merge uops allocated.
384 DTLB store misses with low part of linear-to-physical
388 Non-SW-prefetch load dispatches that hit fill buffer
392 Non-SW-prefetch load dispatches that hit fill buffer
583 Count number of non-delivered uops to RAT per
630 Cycles stalled due to re-order buffer full.
666 Counts total number of uops to be executed per-core
702 DTLB flush attempts of the thread-specific entries.
715 Number of transitions from AVX-256 to legacy SSE
719 Number of transitions from SSE to AVX-256 when
727 Counts the number of micro-ops retired, Use
740 Number of self-modifying-code machine clears
803 Randomly sampled loads whose latency is above a user defined threshold.
845 and cross-core snoop missed in on-pkg core cache.
849 cross-core snoop hits in on-pkg core cache.
864 Number of front end re-steers due to BPU
938 .An -nosplit