| /linux/tools/perf/pmu-events/arch/x86/broadwellx/ |
| H A D | uncore-memory.json | 236 "PublicDescription": "Counts the total number of cycles spent in a major mode (selected by a filter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) mode.; We group these two modes together so that we can use four counters to track each of the major modes at one time. These major modes are used whenever there is an ISOCH txn in the memory controller. In these mode, only ISOCH transactions are processed.",
246 "PublicDescription": "Counts the total number of cycles spent in a major mode (selected by a filter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) mode.; This major mode is used to drain starved underfill reads. Regular reads and writes are blocked and only underfill reads will be processed.",
256 "PublicDescription": "Counts the total number of cycles spent in a major mode (selected by a filter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) mode.; Read Major Mode is the default mode for the iMC, as reads are generally more critical to forward progress than writes.",
266 "PublicDescription": "Counts the total number of cycles spent in a major mode (selected by a filter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) mode.; This mode is triggered when the WPQ hits high occupancy and causes writes to be higher priority than reads. This can cause blips in the available read bandwidth in the system and temporarily increase read latencies in order to achieve better bus utilizations and higher bandwidth.",
289 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
294 "PublicDescription": "Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).",
299 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
304 "PublicDescription": "Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).",
309 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
314 "PublicDescription": "Number of cycles spent in CKE ON mode. The filter allows you to select a rank t
[all...] |
| /linux/tools/perf/pmu-events/arch/x86/broadwellde/ |
| H A D | uncore-memory.json | 198 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
208 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
218 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
228 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
251 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
256 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
261 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
266 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
271 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
276 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
[all …]
|
| /linux/tools/perf/pmu-events/arch/x86/haswellx/ |
| H A D | uncore-memory.json | 227 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
237 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
247 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
257 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
280 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
285 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
290 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
295 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
300 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
305 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
[all …]
|
| /linux/tools/perf/pmu-events/arch/x86/skylakex/ |
| H A D | uncore-memory.json | 263 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
274 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
285 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
296 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
322 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
328 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
333 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
339 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
344 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
350 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
[all …]
|
| /linux/tools/perf/pmu-events/arch/x86/cascadelakex/ |
| H A D | uncore-memory.json | 281 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
292 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
303 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
314 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
698 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
704 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
709 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
715 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
720 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
726 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
[all …]
|
| /linux/tools/perf/pmu-events/arch/x86/ivytown/ |
| H A D | uncore-memory.json | 198 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
208 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
218 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
228 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
251 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
256 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
261 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
266 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
271 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
276 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
[all …]
|
| /linux/drivers/hwmon/peci/ |
| H A D | dimmtemp.c | 295 int rank = chan / priv->gen_info->dimm_idx_max; in create_dimm_temp_label() local
299 "DIMM %c%d", 'A' + rank, in create_dimm_temp_label()
430 * Device 20, Function 0: IMC 0 channel 0 -> rank 0 in read_thresholds_hsx()
431 * Device 20, Function 1: IMC 0 channel 1 -> rank 1 in read_thresholds_hsx()
432 * Device 21, Function 0: IMC 0 channel 2 -> rank 2 in read_thresholds_hsx()
433 * Device 21, Function 1: IMC 0 channel 3 -> rank 3 in read_thresholds_hsx()
434 * Device 23, Function 0: IMC 1 channel 0 -> rank 4 in read_thresholds_hsx()
435 * Device 23, Function 1: IMC 1 channel 1 -> rank 5 in read_thresholds_hsx()
436 * Device 24, Function 0: IMC 1 channel 2 -> rank 6 in read_thresholds_hsx()
437 * Device 24, Function 1: IMC 1 channel 3 -> rank 7 in read_thresholds_hsx()
[all …]
|
| /linux/Documentation/devicetree/bindings/memory-controllers/ddr/ |
| H A D | jedec,lpddr-channel.yaml | 7 title: LPDDR channel with chip/rank topology description
34 channel is equal to the sum of the densities of each rank on the
51 "^rank@[0-9]+$":
56 transaction on the channel targets exactly one rank, based on the
70 "^rank@[0-9]+$":
79 "^rank@[0-9]+$":
88 "^rank@[0-9]+$":
97 "^rank@[0-9]+$":
116 rank@0 {
131 rank@0 {
[all …]
|
| /linux/tools/perf/pmu-events/arch/x86/jaketown/ |
| H A D | uncore-memory.json | 126 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
136 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
146 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
156 …lter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) m…
179 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
184 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
189 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
194 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
199 "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID",
204 …Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If mul…
[all …]
|
| /linux/Documentation/ABI/testing/ |
| H A D | sysfs-devices-edac | 86 What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/size
90 Description: This attribute file will display the size of dimm or rank.
92 stick. For rank*/size, this is the size, in MB for one rank
93 of the DIMM memory stick. On single rank memories (1R), this
94 is also the total size of the dimm. On dual rank (2R) memories,
97 What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_dev_type
104 What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_edac_mode
112 What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_label
127 What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_location
132 branch/channel/slot or channel/slot) of the dimm or rank.
[all …]
|
| /linux/Documentation/edac/ |
| H A D | memory_repair.rst | 55 sparing has cacheline/row/bank/rank sparing granularities. For example, in
56 rank memory-sparing mode, one memory rank serves as a spare for other ranks on
59 The spare rank is held in reserve and not used as active memory until
64 the content of a failing rank of DIMMs is copied to the spare rank. The
65 failing rank is then taken offline and the spare rank placed online for use as
66 active memory in place of the failed rank.
74 to be replaced. Rank sparing is defined as an operation in which an entire DDR
75 rank is replaced.
132 for this operation, cacheline/row/bank/rank sparing, vary in terms of the
|
| /linux/lib/ |
| H A D | union_find.c | 26 * uf_union - Merge two sets, using union by rank
41 if (root1->rank < root2->rank) { in uf_union()
43 } else if (root1->rank > root2->rank) { in uf_union()
47 root1->rank++; in uf_union()
|
| /linux/Documentation/core-api/ |
| H A D | union_find.rst | 37 the find operation, and using union by rank can reduce the time complexity
59 unsigned int rank;
63 The rank field represents the height of the current tree. During a union
64 operation, the tree with the smaller rank is attached under the tree with the
65 larger rank to maintain balance.
71 interface. Initialize the parent pointer to point to itself and set the rank
102 and then link the smaller node to the larger node based on the rank of the root
|
| /linux/drivers/s390/cio/ |
| H A D | scm.c | 105 scm_attr(rank);
142 scmdev->attrs.rank = sale->rank; in scmdev_setup()
146 scmdev->attrs.rank = sale->rank; in scmdev_setup()
164 changed = scmdev->attrs.rank != sale->rank || in scmdev_update()
166 scmdev->attrs.rank = sale->rank; in scmdev_update()
|
| /linux/drivers/edac/ |
| H A D | i3200_edac.c | 69 #define I3200_C0DRB 0x200 /* Channel 0 DRAM Rank Boundary (16b x 4)
72 * 9:0 Channel 0 DRAM Rank Boundary Address
74 #define I3200_C1DRB 0x600 /* Channel 1 DRAM Rank Boundary (16b x 4) */
83 * 28:27 Error Rank Address (ERRRANK)
137 u64 rank = ((log & I3200_ECCERRLOG_RANK_BITS) >> in eccerrlog_row() local
139 return rank | (channel * I3200_RANKS_PER_CHANNEL); in eccerrlog_row()
317 int channel, int rank) in drb_to_nr_pages() argument
321 n = drbs[channel][rank]; in drb_to_nr_pages()
325 if (rank > 0) in drb_to_nr_pages()
326 n -= drbs[channel][rank - 1]; in drb_to_nr_pages()
[all …]
|
| H A D | x38_edac.c | 69 #define X38_C0DRB 0x200 /* Channel 0 DRAM Rank Boundary (16b x 4)
72 * 9:0 Channel 0 DRAM Rank Boundary Address
74 #define X38_C1DRB 0x600 /* Channel 1 DRAM Rank Boundary (16b x 4) */
83 * 28:27 Error Rank Address (ERRRANK)
301 bool stacked, int channel, int rank) in drb_to_nr_pages() argument
305 n = drbs[channel][rank]; in drb_to_nr_pages()
306 if (rank > 0) in drb_to_nr_pages()
307 n -= drbs[channel][rank - 1]; in drb_to_nr_pages()
308 if (stacked && (channel == 1) && drbs[channel][rank] == in drb_to_nr_pages()
366 * The dram rank boundary (DRB) reg values are boundary addresses in x38_probe1()
[all …]
|
| H A D | i3000_edac.c | 110 #define I3000_C0DRB 0x100 /* Channel 0 DRAM Rank Boundary (8b x 4)
112 * 7:0 Channel 0 DRAM Rank Boundary Address
114 #define I3000_C1DRB 0x180 /* Channel 1 DRAM Rank Boundary (8b x 4)
116 * 7:0 Channel 1 DRAM Rank Boundary Address
119 #define I3000_C0DRA 0x108 /* Channel 0 DRAM Rank Attribute (8b x 2)
122 * 6:4 DRAM odd Rank Attribute
124 * 2:0 DRAM even Rank Attribute
127 * size of the corresponding rank:
135 #define I3000_C1DRA 0x188 /* Channel 1 DRAM Rank Attribute (8b x 2) */
298 * If the rank boundaries for the two channels are different in i3000_is_interleaved()
[all …]
|
| H A D | al_mc_edac.c | 65 u8 rank, u32 row, u8 bg, u8 bank, u16 column, in prepare_msg() argument
69 "%s rank=0x%x row=0x%x bg=0x%x bank=0x%x col=0x%x syn0: 0x%x syn1: 0x%x syn2: 0x%x", in prepare_msg()
71 rank, row, bg, bank, column, syn0, syn1, syn2); in prepare_msg()
81 u8 rank, bg, bank; in handle_ce() local
100 rank = FIELD_GET(AL_MC_ECC_CE_ADDR0_RANK, ecccaddr0); in handle_ce()
108 rank, row, bg, bank, column, in handle_ce()
126 u8 rank, bg, bank; in handle_ue() local
145 rank = FIELD_GET(AL_MC_ECC_UE_ADDR0_RANK, eccuaddr0); in handle_ue()
153 rank, row, bg, bank, column, in handle_ue()
|
| H A D | i5100_edac.c | 317 unsigned rank[I5100_MAX_RANK_INTERLEAVE]; member
355 /* map a rank/chan to a slot number on the mainboard */
357 int chan, int rank) in i5100_rank_to_slot() argument
367 if (priv->dimm_csmap[i][j] == rank) in i5100_rank_to_slot()
409 /* convert csrow index into a rank (per channel -- 0..5) */
430 unsigned rank, in i5100_handle_ce() argument
445 chan, rank, -1, in i5100_handle_ce()
452 unsigned rank, in i5100_handle_ue() argument
467 chan, rank, -1, in i5100_handle_ue()
481 unsigned rank; in i5100_read_log() local
[all …]
|
| H A D | octeon_edac-lmc.c | 32 unsigned long rank; member
49 "DIMM %d rank %d bank %d row %d col %d", in octeon_lmc_edac_poll()
94 fadr.cn61xx.fbunk = pvt->rank; in octeon_lmc_edac_poll_o2()
100 "DIMM %d rank %d bank %d row %d col %d", in octeon_lmc_edac_poll_o2()
160 TEMPLATE_SHOW(rank);
161 TEMPLATE_STORE(rank);
203 static DEVICE_ATTR(rank, S_IRUGO | S_IWUSR,
|
| /linux/include/linux/ |
| H A D | union_find.h | 16 unsigned int rank; member
20 #define UF_INIT_NODE(node) {.parent = &node, .rank = 0}
27 * initializes its rank to 0.
32 node->rank = 0; in uf_node_init()
|
| /linux/tools/perf/pmu-events/arch/x86/snowridgex/ |
| H A D | uncore-memory.json | 259 "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID",
265 …cription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter a…
270 "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID",
276 …cription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter a…
281 "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID",
287 …cription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter a…
292 "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID",
298 …cription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter a…
303 "BriefDescription": "Throttle Cycles for Rank 0",
309 …Rank 0 : Counts the number of cycles while the iMC is being throttled by either thermal constraint…
[all …]
|
| /linux/Documentation/filesystems/ |
| H A D | directory-locking.rst | 124 it should be possible to rank the filesystems so that directory operation
138 them in order of non-decreasing rank. Namely,
140 * rank ->i_rwsem of non-directories on given filesystem in inode pointer
142 * put ->i_rwsem of all directories on a filesystem at the same rank,
144 * put ->s_vfs_rename_mutex at rank lower than that of any ->i_rwsem
147 rank of those filesystems.
152 2. ->i_rwsem of directories on that NFS filesystem, same rank for all
156 5. ->i_rwsem of directories on the local filesystem, same rank for all
160 It's easy to verify that operations never take a lock with rank
168 contended locks in the minimal deadlock will be of the same rank,
|
| /linux/lib/zstd/compress/ |
| H A D | huf_compress.c | 310 /* Prepare base value per rank */ in HUF_readCTable()
328 /* determine stating value per rank */ in HUF_readCTable()
332 valPerRank[n] = min; /* get starting value within each rank */ in HUF_readCTable()
336 /* assign value within rank, symbol order */ in HUF_readCTable()
411 /* Get pos of last (smallest = lowest cum. count) symbol per rank */ in HUF_setMaxHeight()
423 * gain back half the rank. in HUF_setMaxHeight()
438 …/* only triggered when no more rank 1 symbol left => find closest one (note : there is necessarily… in HUF_setMaxHeight()
444 /* Increase the number of bits to gain back half the rank cost. */ in HUF_setMaxHeight()
448 /* Fix up the new rank. in HUF_setMaxHeight()
449 * If the new rank was empty, this symbol is now its smallest. in HUF_setMaxHeight()
[all …]
|
| /linux/drivers/cxl/core/ |
| H A D | trace.h | 408 { CXL_GMER_VALID_RANK, "RANK" }, \
472 __field(u8, rank)
494 __entry->rank = rec->media_hdr.rank;
517 "transaction_type='%s' channel=%u rank=%u " \
528 __entry->channel, __entry->rank, __entry->device,
580 { CXL_DER_VALID_RANK, "RANK" }, \
616 __field(u8, rank) /* Out of order to pack trace record */
643 __entry->rank = rec->media_hdr.rank;
671 "transaction_type='%s' channel=%u rank=%u nibble_mask=%x " \
683 __entry->channel, __entry->rank, __entry->nibble_mask,
[all …]
|