Age | Commit message (Collapse) | Author | Files | Lines | |
---|---|---|---|---|---|
2017-05-25 | minNum -> minimumNumberpriv-1.10 | Andrew Waterman | 4 | -8/+16 | |
2017-05-13 | Make C.LI/C.LUI trapping behavior match spec | Andrew Waterman | 2 | -2/+1 | |
2017-04-25 | FMV.X.S/FMV.S.X -> FMV.X.W/FMV.W.X | Andrew Waterman | 2 | -0/+0 | |
2017-04-10 | Implement new FP encoding | Andrew Waterman | 54 | -62/+62 | |
https://groups.google.com/a/groups.riscv.org/d/msg/isa-dev/_r7hBlzsEd8/cWPyJKMzCQAJ | |||||
2017-03-27 | On EBREAK, set badaddr to pc | Andrew Waterman | 2 | -2/+2 | |
2017-03-16 | Simplify interrupt-stack discipline | Andrew Waterman | 2 | -2/+2 | |
https://github.com/riscv/riscv-isa-manual/commit/f2ed45b1791bb602657adc2ea9ab5fc409c62542 | |||||
2017-03-13 | Implement mstatus.TW, mstatus.TVM, and mstatus.TSR | Andrew Waterman | 3 | -2/+3 | |
2017-02-20 | serialize simulator on wfi | Andrew Waterman | 1 | -1/+1 | |
This improves simulator perf when a thread is idle, or waiting on HTIF. | |||||
2017-02-15 | sfence.vm -> sfence.vma | Andrew Waterman | 1 | -0/+0 | |
2017-02-01 | For FMIN(sNaN, x) and FMIN(qNaN, qNaN), return canonical NaN | Andrew Waterman | 4 | -4/+12 | |
Resolves #76 | |||||
2017-02-01 | Set xPIE=1 on xRET | Andrew Waterman | 2 | -2/+2 | |
Resolves #88. | |||||
2016-11-10 | AMOs should always return store faults, not load faults | Andrew Waterman | 18 | -54/+18 | |
This commit also factors out the common AMO code into mmu_t. | |||||
2016-08-17 | Allow mstatus.MPP to store bad values; instead, validate on MRET | Andrew Waterman | 1 | -4/+1 | |
Either approach is legal, but this more closely matches Rocket. | |||||
2016-07-28 | Add support for virtual priv register. (#59) | Tim Newsome | 1 | -1/+4 | |
Users can use this register to inspect and change the privilege level of the core. It doesn't make any assumptions about the actual underlying debug mechanism (as opposed to having the user change DCSR directly, which may not exist in all debug implementations). | |||||
2016-05-23 | Single step appears to work. | Tim Newsome | 1 | -0/+3 | |
2016-05-23 | Add dret. | Tim Newsome | 2 | -3/+6 | |
2016-05-23 | Properly save/restore dpc, mcause, mbadaddr. | Tim Newsome | 1 | -0/+3 | |
Also clear dcsr.cause when leaving Debug Mode so future traps go where they should. | |||||
2016-05-21 | Some bugfixes for CSR reading and setting FS for fflags updates (#43) | Andy Wright | 4 | -8/+20 | |
* csrrc[i] and csrrs[i] don't write CSRs if rs/zimm == 0 * Dirty fp state when setting new fp exceptions * Set FS to dirty for all non-zero fflags writes. | |||||
2016-04-19 | Split ERET into URET, SRET, HRET, MRET | Andrew Waterman | 4 | -13/+15 | |
2016-03-02 | Fix ERET bug | Andrew Waterman | 1 | -1/+1 | |
2016-03-02 | Serialize simulator on ERET | Andrew Waterman | 1 | -2/+2 | |
This guarantees interrupts will eventually be taken. | |||||
2016-03-02 | WIP on priv spec v1.9 | Andrew Waterman | 5 | -11/+11 | |
2016-03-01 | Upgrade to latest SoftFloat | Andrew Waterman | 48 | -52/+48 | |
2015-11-19 | C.ADDIW is reserved for rd=0 | Andrew Waterman | 1 | -1/+2 | |
2015-10-20 | Update to hopefully final RVC 1.9 encoding | Andrew Waterman | 2 | -4/+0 | |
2015-10-05 | more work towards RVC 1.8 | Andrew Waterman | 3 | -7/+7 | |
2015-10-02 | work towards rvc 1.8 | Andrew Waterman | 20 | -13/+40 | |
2015-10-02 | clean up shift instruction implementation | Andrew Waterman | 4 | -22/+6 | |
2015-09-15 | Zero-extend flw, fmv_s_x instructions | Christopher Celio | 2 | -2/+2 | |
- This makes Spike more consistent with its zero-extending behavior regarding other SP operations when placed into the 64b f-registers. | |||||
2015-09-08 | Improve instruction fetch | Andrew Waterman | 8 | -22/+20 | |
- Performance for variable-length instructions is much better - Refill is simpler and faster - Support for instructions with overlapping opcodes (e.g. C.ADD + C.JALR) | |||||
2015-09-04 | Move towards RVC v1.8 | Andrew Waterman | 25 | -103/+57 | |
2015-05-31 | Add rest of RV32C instructions | Andrew Waterman | 5 | -14/+68 | |
2015-05-31 | Fix c.slliw implementation | Andrew Waterman | 1 | -1/+3 | |
2015-05-31 | New RV64C proposal | Andrew Waterman | 24 | -17/+64 | |
2015-05-31 | Take interrupts as soon as interrupts are enabled | Andrew Waterman | 2 | -6/+0 | |
Previously, if interrupts were enabled then disabled quickly enough, no interrupt would ever be taken, resulting in deadlock. | |||||
2015-05-09 | Upgrade to privileged architecture 1.7 | Andrew Waterman | 4 | -1/+10 | |
2015-04-03 | Support setting ISA/subsets with --isa flag | Andrew Waterman | 152 | -22/+119 | |
Default is RV64IMAFDC. Can do things like --isa=RV32 (which implies IMAFDC) --isa=IM (which implies RV64) --isa=RV64IMAFDXhwacha | |||||
2015-04-02 | Simplify RV32 comparisons | Andrew Waterman | 10 | -10/+10 | |
No need to eliminate the upper 32 bits of the 64-bit x-register, as all RV32 instructions should sign-extend their results to 64 bits. | |||||
2015-03-30 | Implement RVC draft | Andrew Waterman | 22 | -8/+62 | |
2015-03-17 | Merge [shm]call into ecall, [shm]ret into eret | Andrew Waterman | 5 | -8/+7 | |
2015-03-12 | Use hcall instead of mcall | Andrew Waterman | 2 | -2/+3 | |
2015-03-12 | Update to new privileged spec | Andrew Waterman | 57 | -63/+74 | |
Sorry, everyone. | |||||
2015-02-08 | Use xlen, not xprlen, to refer to x-register width | Andrew Waterman | 17 | -26/+26 | |
2015-01-02 | On misaligned fetch, set EPC to target, not branch itself | Andrew Waterman | 2 | -4/+5 | |
2014-11-30 | Implement timer faithfully | Andrew Waterman | 6 | -6/+18 | |
rdcycle/rdinstret now have single-instruction granularity. Questionable behavior when timer interrupts occurred around the same time as the compare register is written should be fixed. | |||||
2014-11-22 | Revert "Enable support for the four custom instructions" | Yunsup Lee | 24 | -0/+0 | |
This reverts commit fd18dc43f64d1938144f6c883ba4a2ca247611c6. Refactoring support for custom instructions. | |||||
2014-10-23 | Enable support for the four custom instructions | Arun Thomas | 24 | -0/+0 | |
* Update generated encoding.h (generated from riscv-opcodes) * Add empty implementations for the custom instructions | |||||
2014-09-27 | Avoid use of __int128_t | Andrew Waterman | 3 | -14/+6 | |
It is nonstandard, and GCC doesn't support it on 32-bit platforms. The resulting code for MULH[[S]U] is crappier, but that doesn't really matter, as these instructions are dynamically infrequent. | |||||
2014-03-18 | Support RV32 RDTIMEH/RDCYCLEH/RDINSTRETH | Andrew Waterman | 6 | -6/+6 | |
2014-03-06 | Add fclass.{s|d} instructions | Andrew Waterman | 2 | -0/+4 | |