libtoolbuild error #108
Open
libtoolbuild error #108
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
In case any level of cache is not used.
so that it is compatible with queue length sum per channel
remove redundant cache configuration fix wrong organization string for DDR4, LPDDR4
1. use macro to hide some statistics from gem5 2. change gem5wrapper. parse config file before passing it to gem5wrapper, so that we can inject configurations from gem5 side.
Changes to integrate Ramulator with the Structural Simulation Toolkit…
…earching for past hits using direct map indexing can generate an empty element if the search is not found. This will cause future desired insertion to the table to fail.
…les with 100 million warmup instructions; added 3200 data rate option for DDR4; fixed some command scheduling bugs that were leading to activate-precharge without read or write command; changed the default scheduler to FRFCFS_Cap;
… few write requests left in the write queue in the controller;
…is set to 0 in the config file. When expected_num_insts == 0 the trace will run until completion and the simulation will finish; Included a warning for a case where the warmup_insts is larger than the number of instructions in the trace file and the end of the trace file is reached, i.e., expected_num_insts == 0;
… reached until the completion of the trace;
Source: Micron 8Gb DDR4 datasheet (tRFC+10ns) Signed-off-by: Roy Spliet <[email protected]>
Signed-off-by: Roy Spliet <[email protected]>
Change is cosmetic only. Timing is unaffected, as both tBL and tCCDS are in practice always 4*tCK. Signed-off-by: Roy Spliet <[email protected]>
This constraint was taken into account for explicit precharge operations, but not for the implicit "auto precharge" bit on RDA/WRA. Note that, like the original constraint, this assumes per-rank refresh rather than (staggered) per-bank. Signed-off-by: Roy Spliet <[email protected]>
DDR4: Timing constraint fixes
* added stt-mram files. * added sttmram case to main.cpp
* Support for custom mapping; * disabling dump * Update README.md * Applied requirements for the pull request: Default mapping should remain the same; Lang fixes in README; Disabling debugging;
* Adding PCM model * added PCM model files. * Added PCM case to main.cpp
This is a safeguard when e.g. the following sequence of commands occurs with minimal distance: ACT(x), RDA(x), REF In this case RDA will be issued as early as possible for minimum data arrival delay, but not finish until after tRC. The existing distance between RDA and REF is insufficient to guarantee compliant timing, as generally nRAS > nRTP+nRP. This patch adds a minimal distance between ACT and REF, mirroring the ACT-ACT distance at the bank level. Signed-off-by: Roy Spliet <[email protected]>
…. Also made Scheduler.h more readable (#74)
* Fixed a bug which made FCFS Scheduler fail an assert in DDR3 and DDR4. Also made Scheduler.h more readable * 75% documentation done for src/scheduler.h * Added Documentation to Scheduler.h
* DDR3: Honour ACT->REF distance. Analogue to 448232b DDR4: Honour ACT->REF distance. (#69) Enforces the minimal distance between activate and refresh even if precharge was performed by RDA or WRA. Signed-off-by: Roy Spliet <[email protected]> * DDR3: Honour RDA/WRA->REF distance. Analogue to c14cb18 DDR4: Honour RDA/WRA->REF distance. Signed-off-by: Roy Spliet <[email protected]>
…ssued to different bank;
as it leads to incorrect behavior when using --mode=dram
The new test runs Ramulator using the default DDR3/DDR4 configurations with synthetic and spec traces. It compares the simulation statistics against the golden results and checks Ramulator's runtime, and memory usage
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
make libramulator.a
libtool: error: unrecognised option: '-static'
Solution:$(OBJS) $ (OBJDIR)/Gem5Wrapper.o
$(AR) rcs $ @ $^
libramulator.a: