Age | Commit message (Collapse) | Author | Files | Lines | |
---|---|---|---|---|---|
2020-03-03 | Clarify operation of 32-bit AMOs on RV64. | Krste Asanovic | 1 | -1/+2 | |
Closes #465 | |||||
2019-12-27 | FENCE.I isn't in the I base | Andrew Waterman | 1 | -1/+1 | |
FENCE.I is, of course, not allowed in LR/SC sequences. But we don't need to explicitly exclude it, since it's now in Zifencei, rather than I. | |||||
2019-12-13 | A extension v2.1 has been ratifiedRatified-IMAFDQC | Andrew Waterman | 1 | -1/+1 | |
2019-10-11 | Incorporate feedback from Paul Donahue | Andrew Waterman | 1 | -2/+2 | |
2019-10-06 | Incorporate Anthony Coulter's feedback | Andrew Waterman | 1 | -3/+4 | |
https://groups.google.com/a/groups.riscv.org/d/msg/isa-dev/6rpIanfXCVc/SIp_dwvCAgAJ | |||||
2019-10-02 | Address some of Derek's feedbacklrsc | Andrew Waterman | 1 | -15/+4 | |
2019-10-02 | Fix editing error that allowed FENCE.I in LR/SC sequences | Andrew Waterman | 1 | -2/+3 | |
2019-10-02 | Fix typo | Andrew Waterman | 1 | -1/+1 | |
2019-10-02 | Incorporate aspects of PR #444 | Andrew Waterman | 1 | -5/+17 | |
h/t Marc | |||||
2019-10-02 | Avoid using "virtual address" in normative text of unprivileged spec (#430) | Andrew Waterman | 1 | -2/+5 | |
2019-10-02 | Incorporate some of #416 and #418 | Andrew Waterman | 1 | -17/+57 | |
2019-10-02 | More LR/SC feedback | Andrew Waterman | 1 | -4/+5 | |
2019-10-02 | Move CAS code figure to the same page it's referenced on | Andrew Waterman | 1 | -34/+32 | |
2019-10-02 | Introduce "reservation set" terminology | Andrew Waterman | 1 | -44/+53 | |
2019-10-02 | More Derek feedback | Andrew Waterman | 1 | -3/+2 | |
2019-10-02 | Address Derek's feedback | Andrew Waterman | 1 | -23/+29 | |
2019-10-02 | Constrained loops must use same *virtual* address for SC | Andrew Waterman | 1 | -2/+2 | |
2019-10-02 | Incorporate Dan's feedback | Andrew Waterman | 1 | -25/+26 | |
2019-10-02 | More LR/SC updates | Andrew Waterman | 1 | -1/+5 | |
2019-10-02 | Remove page breaks | Andrew Waterman | 1 | -2/+0 | |
2019-10-02 | Weaken LR/SC progress guarantee | Andrew Waterman | 1 | -49/+106 | |
2019-07-30 | Use consistent terms for exception types | Andrew Waterman | 1 | -4/+4 | |
@jscheid-ventana originally contributed this, but I tweaked the hyphenation. Resolves #422 | |||||
2019-05-15 | Correct iteration in LR/SC CAS example. (#384) | David-Horner | 1 | -2/+3 | |
Address argument was clobbered. Signed-off-by: David Horner <ds2horner@gmail.com> | |||||
2019-05-07 | Clarify the behaviour of LR.W/D and SC.W/D | Columbus240 | 1 | -7/+9 | |
Concerning issue #376. | |||||
2019-02-08 | Clarify behavior of LR.rl and SC.aq (#339) | Andrew Waterman | 1 | -3/+6 | |
Resolves #338 | |||||
2019-01-17 | JALR is not allowed within LR/SC sequences | Andrew Waterman | 1 | -1/+1 | |
This used to be the case, until an editing error several years ago. | |||||
2018-12-10 | subset -> extension | Andrew Waterman | 1 | -3/+3 | |
2018-11-16 | Improved wording. | Krste Asanovic | 1 | -2/+2 | |
2018-11-16 | Clarified that LR/SC forward progress guarantee might only hold for a subset ↵ | Krste Asanovic | 1 | -3/+5 | |
of instruction and data memory space depending on execution environment. | |||||
2018-11-07 | Describe the AMOs as "bitwise", not "logical" (#259) | Palmer Dabbelt | 1 | -2/+2 | |
"logical AND" usually means C's "&&" operator, not "&" operator. Thanks to Bodhisattva Debnath for pointing out the issue! | |||||
2018-11-06 | Allow access exceptions to be reported on misaligned atomic memory ↵ | Krste Asanovic | 1 | -10/+18 | |
operations where they should not be emulated. | |||||
2018-08-12 | Removed redundant text that LR can reserve a different subset on each ↵ | Krste Asanovic | 1 | -3/+1 | |
invocation. | |||||
2018-08-09 | Clarified reservation range and that SC only pairs with immediately ↵ | Krste Asanovic | 1 | -20/+25 | |
preceding LR. | |||||
2018-08-07 | Clarified A definitions. | Krste Asanovic | 1 | -27/+18 | |
2018-08-06 | Removed obsolete commentary. | Krste Asanovic | 1 | -11/+0 | |
2018-07-06 | Merge branch 'misc-fixes' of https://github.com/tymcauley/riscv-isa-manual ↵ | Andrew Waterman | 1 | -1/+1 | |
into tymcauley-misc-fixes | |||||
2018-06-18 | Strengthen guidance on the need to clear a reservation using SC (#198) | Alex Bradbury | 1 | -2/+3 | |
Commit 170f3c5 clarified that reservations can be cleared with an SC to a dummy memory location. As discussed <https://github.com/riscv/riscv-isa-manual/commit/170f3c52bd134ac90c3467f77925fdaa68e9b8f6#commitcomment-29386537>, this patch makes it clear that the reservation "should" be cleared in this way during a preemptive context switch. Anyone writing preemptive context switch code should be forcibly clearing load reservations. Although other mechanisms might be used, this is the standard way of doing it (hence "should" rather than "must"). | |||||
2018-06-16 | Fixed grammar inconsistency in a.tex. | Tynan McAuley | 1 | -1/+1 | |
Changed "can not" to "cannot". While both are acceptable, "cannot" is used throughout the document. | |||||
2018-06-14 | Fix outdated commentary about LR/SC and context switching | Andrew Waterman | 1 | -6/+2 | |
Closes #193 | |||||
2018-06-11 | Remove misleading note about AMOSWAP elision | Andrew Waterman | 1 | -6/+0 | |
The note implied that it's legal to elide silent stores. This is not true with respect to the consistency model. | |||||
2018-05-06 | Luke's feedback | Andrew Waterman | 1 | -1/+1 | |
2018-05-02 | Updates to the memory consistency model spec | Daniel Lustig | 1 | -56/+48 | |
This giant patch is the result of months of work from a lot of different people in the memory model TG. | |||||
2018-03-28 | Make LR/SC CAS example adhere to the forward-progress constraints | Andrew Waterman | 1 | -1/+2 | |
2018-02-07 | Add commentary about LR/SC forward-progress guarantee | Andrew Waterman | 1 | -0/+5 | |
2017-12-12 | Describe optional support for misaligned AMOs (#117) | Andrew Waterman | 1 | -9/+28 | |
* Fix typo * Describe misaligned AMOs * Improve commentary for misaligned AMO emulation | |||||
2017-10-20 | Remove privileged architecture detail from user spec | Andrew Waterman | 1 | -3/+11 | |
2017-07-21 | Fix description of LR/SC for data size | Andrew Waterman | 1 | -3/+4 | |
LR.D/SC.W and LR.W/SC.D aren't guaranteed to succeed. | |||||
2017-05-06 | Updated to define and use hart more consistently. | Krste Asanovic | 1 | -13/+22 | |
Added warnings about changes to memory model. | |||||
2017-04-17 | Recommend LR for sequentially consistent loads | Andrew Waterman | 1 | -6/+6 | |
2017-04-09 | Fix typo | Andrew Waterman | 1 | -1/+1 | |