Lines Matching +full:micro +full:- +full:tlb
46 .Bl -tag -width "Li PMC_CLASS_IAP"
48 Fixed-function counters that count only one hardware event per counter.
60 .%B "Intel(R) 64 and IA-32 Architectures Software Developer's Manual"
62 .%N "Order Number: 325462-052US"
71 .Bl -column "PMC_CAP_INTERRUPT" "Support"
88 .Bl -tag -width indent
90 Configure the Off-core Response bits.
91 .Bl -tag -width indent
129 M-state initial lookup stat in L3.
131 E-state.
133 S-state.
135 F-state.
139 No details on snoop-related information.
149 Hit denotes a cache-line was valid before snoop effect.
160 A snoop was needed and it HitM-ed in local or remote cache.
161 HitM denotes a cache-line was in modified state before effect as a results of snoop.
167 Target was non-DRAM system address.
175 Configure the PMC to count the number of de-asserted to asserted
202 .Bl -tag -width indent
209 Speculative cache-line split load uops dispatched to
213 Speculative cache-line split Store-address uops
221 Misses in all TLB levels that cause a page walk of any
226 that caused 4K page walks in any TLB levels.
230 that caused 2M/4M page walks in any TLB levels.
233 Completed page walks in any TLB of any page size
250 DTLB demand load misses with low part of linear-to-
265 Number of flags-merge uops allocated.
359 Miss in all TLB levels causes an page walk of any
364 more TLB levels of 4K page structure.
368 more TLB levels of 2M/4M page structure.
371 Completed page walks due to store miss in any TLB
384 Store operations that miss the first TLB level but hit
388 DTLB store misses with low part of linear-to-physical
392 Non-SW-prefetch load dispatches that hit fill buffer
396 Non-SW-prefetch load dispatches that hit fill buffer
596 Count number of non-delivered uops to RAT per
643 Cycles stalled due to re-order buffer full.
678 Counts total number of uops to be executed per-core
714 DTLB flush attempts of the thread-specific entries.
727 Number of transitions from AVX-256 to legacy SSE
731 Number of transitions from SSE to AVX-256 when
739 Counts the number of micro-ops retired, Use
752 Number of self-modifying-code machine clears
858 and cross-core snoop missed in on-pkg core cache.
862 cross-core snoop hits in on-pkg core cache.
877 Number of front end re-steers due to BPU