Searched refs:PI (Results 1 – 25 of 34) sorted by relevance
12
1 Futex Requeue PI4 Requeueing of tasks from a non-PI futex to a PI futex requires6 left without an owner if it has waiters; doing so would break the PI10 "PI".50 previously mentioned PI-boosting algorithms.52 In order to support PI-aware pthread_condvar's, the kernel needs to53 be able to requeue tasks to PI futexes. This support implies that55 user space already holding the PI futex. The glibc implementation80 The actual glibc implementation will likely test for PI and make the82 calls for the PI cases. Similar changes are needed for[all …]
1 Lightweight PI-futexes6 - in the user-space fastpath a PI-enabled futex involves no kernel work7 (or any other PI complexity) at all. No registration, no extra kernel13 - the in-kernel PI implementation is streamlined around the mutex22 The short reply: user-space PI helps achieving/improving determinism for24 determinism and well-bound latencies. Even in the worst-case, PI will65 Currently (without PI), if a high-prio and a low-prio task shares a lock77 As mentioned before, the userspace fastpath of PI-enabled pthread93 own TID into the futex value], and attaches a 'PI state' structure to94 the futex-queue. The pi_state includes an rt-mutex, which is a PI-aware,[all …]
16 inheritance (PI) algorithm that is used, as well as reasons for the17 decisions that were made to implement PI in the manner that was done.57 Priority Inheritance (PI)61 for this document. Here we only discuss PI.63 PI is where a process inherits the priority of another process if the other76 the design that is used to implement PI.78 PI chain - The PI chain is an ordered series of locks and processes that cause84 PI and spin locks that are used in the PI code, from now on85 the PI locks will be called a mutex.88 referring to spin locks that are used to protect parts of the PI[all …]
1 RT-mutex subsystem with PI support4 RT-mutexes with priority inheritance are used to support PI-futexes,7 about PI-futexes.]
264 - documentation on lightweight PI-futexes.288 - desc. of RT-mutex subsystem with PI (Priority Inheritance) support.
83 |--N*PI/2, -32 <= N <= 32, IN A LEADING TERM IN EXT. AND TRAILING84 |--TERM IN SGL. NOTE THAT PI IS 64-BIT LONG, THUS N*PI/2 IS AT181 cmpil #0x4004BC7E,%d0 | ...|X| < 15 PI?187 |--THIS IS THE USUAL CASE, |X| <= 15 PI.190 fmuld TWOBYPI,%fp1 | ...X*2/PI193 leal PITBL+0x200,%a1 | ...TABLE OF N*PI/2, N = -32,...,32292 |--IF |X| > 15PI, WE USE THE GENERAL ARGUMENT REDUCTION.322 | ;create 2**16383*PI/2327 | ;PI/2 at FP_SCR3340 |--ON ENTRY, FP0 IS X, ON RETURN, FP0 IS X REM PI/2, |X| <= PI/4.[all …]
48 PI: .long 0x40000000,0xC90FDAA2,0x2168C235,0x00000000 label57 |--ACOS(X) = PI/2 FOR DENORMALIZED X
194 cmpil #0x4004BC7E,%d0 | ...|X| < 15 PI?199 |--THIS IS THE USUAL CASE, |X| <= 15 PI.202 fmuld TWOBYPI,%fp1 | ...X*2/PI205 lea PITBL+0x200,%a1 | ...TABLE OF N*PI/2, N = -32,...,32459 addil #0x00003FFF,%d2 | ...BIASED EXPO OF 2**L * (PI/2)548 cmpil #0x4004BC7E,%d0 | ...|X| < 15 PI?554 |--THIS IS THE USUAL CASE, |X| <= 15 PI.557 fmuld TWOBYPI,%fp1 | ...X*2/PI560 lea PITBL+0x200,%a1 | ...TABLE OF N*PI/2, N = -32,...,32
57 PPIBY2: .long 0x3FFF0000,0xC90FDAA2,0x2168C235 |+PI/258 MPIBY2: .long 0xbFFF0000,0xC90FDAA2,0x2168C235 |-PI/2504 |**Returns +PI/2510 |**Returns -PI/2
92 |--|X| = 1, ASIN(X) = +- PI/2.
402 |--IF |X| > 2^(100), RETURN SIGN(X)*(PI/2 - TINY). OTHERWISE,403 |--RETURN SIGN(X)*PI/2 + ATAN(-1/X).
25 1.b) The Processor Interface (PI) node33 - reg : should contain the PI registers location and length39 the PI node.
34 1.b) The Processor Interface (PI) node42 - reg : should contain the PI registers location and length48 the PI node.
82 PI, /* producer index */ enumerator
232 pm8001_ha->memoryMap.region[PI].num_elements = 1; in pm8001_alloc()233 pm8001_ha->memoryMap.region[PI].element_size = 4; in pm8001_alloc()234 pm8001_ha->memoryMap.region[PI].total_len = 4; in pm8001_alloc()235 pm8001_ha->memoryMap.region[PI].alignment = 4; in pm8001_alloc()
48 # 3 threads 1 lock PI
48 # 3 threads 2 lock PI
48 # 3 threads 1 lock PI steal pending ownership
48 # 5 threads 4 lock PI
48 # 4 threads 2 lock PI
48 # 5 threads 4 lock PI - modify priority of blocked threads
27 TrendNET TEW-288PI
177 the biggest challenge as the current linux PI infrastructure is geared towards182 This means the whole PI machinery will have to be reworked - and that is one of