[gem5-dev] Cron /z/m5/regression/do-regression quick

* build/RISCV/tests/opt/quick/se/02.insttest/riscv/linux-rv64c/minor-timing: FAILED! * build/RISCV/tests/opt/quick/se/02.insttest/riscv/linux-rv64c/o3-timing: FAILED! *** diff[simerr]: SKIPPED* build/RISCV/tests/opt/quick/se/02.insttest/riscv/linux-rv64c/simple-timing: FAILED!

[gem5-dev] Change in gem5/gem5[master]: mem-cache: Create BDI Compressor

Hello Jason Lowe-Power, Nikos Nikoleris, I'd like you to reexamine a change. Please visit https://gem5-review.googlesource.com/c/public/gem5/+/11412 to look at the new patch set (#7). Change subject: mem-cache: Create BDI Compressor .

[gem5-dev] Change in gem5/gem5[master]: mem-cache: Add co-allocation function to compressed tags

Hello Jason Lowe-Power, Nikos Nikoleris, I'd like you to reexamine a change. Please visit https://gem5-review.googlesource.com/c/public/gem5/+/11411 to look at the new patch set (#7). Change subject: mem-cache: Add co-allocation function to compressed tags .

[gem5-dev] Change in gem5/gem5[master]: mem-cache: Handle data expansion

Hello Jason Lowe-Power, Nikos Nikoleris, I'd like you to reexamine a change. Please visit https://gem5-review.googlesource.com/c/public/gem5/+/12087 to look at the new patch set (#4). Change subject: mem-cache: Handle data expansion .

[gem5-dev] Change in gem5/gem5[master]: mem-cache: Create CPack compressor

Hello Jason Lowe-Power, Nikos Nikoleris, I'd like you to reexamine a change. Please visit https://gem5-review.googlesource.com/c/public/gem5/+/11105 to look at the new patch set (#9). Change subject: mem-cache: Create CPack compressor ...

Re: [gem5-dev] cc registers

Hi Gabe, If I remember correctly, we switched from int regs to cc regs in the Arm ISA back in 2014 for the same reason as AMD. I.e., to get a separate register pool in the O3 CPU when renaming. We have similar renaming issues issues for vector registers, which is why we introduced the new vector

[gem5-dev] Change in gem5/gem5[master]: cpu-o3: O3 LSQ Generalisation

Giacomo Travaglini has uploaded a new patch set (#2) to the change originally created by Giacomo Gabrielli. ( https://gem5-review.googlesource.com/c/public/gem5/+/13516 ) Change subject: cpu-o3: O3 LSQ Generalisation .. cpu-

[gem5-dev] Change in gem5/gem5[master]: base: Iterable CircularQueue implementation

Giacomo Travaglini has uploaded a new patch set (#8) to the change originally created by Giacomo Gabrielli. ( https://gem5-review.googlesource.com/c/public/gem5/+/13127 ) Change subject: base: Iterable CircularQueue implementation ..

[gem5-dev] Change in gem5/gem5[master]: base: Ported circlebuf to CircularQueue

Giacomo Travaglini has uploaded a new patch set (#8) to the change originally created by Giacomo Gabrielli. ( https://gem5-review.googlesource.com/c/public/gem5/+/13128 ) Change subject: base: Ported circlebuf to CircularQueue ..

[gem5-dev] Change in gem5/gem5[master]: dev-arm: Fix Gicv2 distributor group register

Giacomo Travaglini has uploaded this change for review. ( https://gem5-review.googlesource.com/c/public/gem5/+/13555 Change subject: dev-arm: Fix Gicv2 distributor group register .. dev-arm: Fix Gicv2 distributor group regist

[gem5-dev] Change in gem5/gem5[master]: dev-arm: Don't panic when EOIR a non active PPI

Giacomo Travaglini has uploaded this change for review. ( https://gem5-review.googlesource.com/c/public/gem5/+/13556 Change subject: dev-arm: Don't panic when EOIR a non active PPI .. dev-arm: Don't panic when EOIR a non acti

[gem5-dev] Change in gem5/gem5[master]: dev-arm: Don't panic when EOIR a non active PPI

Giacomo Travaglini has submitted this change and it was merged. ( https://gem5-review.googlesource.com/c/public/gem5/+/13556 ) Change subject: dev-arm: Don't panic when EOIR a non active PPI .. dev-arm: Don't panic when EOIR a

[gem5-dev] Change in gem5/gem5[master]: dev-arm: Fix Gicv2 distributor group register

Giacomo Travaglini has submitted this change and it was merged. ( https://gem5-review.googlesource.com/c/public/gem5/+/13555 ) Change subject: dev-arm: Fix Gicv2 distributor group register .. dev-arm: Fix Gicv2 distributor gro

[gem5-dev] Change in gem5/gem5[master]: arch: Get rid of the unused type AnyReg.

Gabe Black has submitted this change and it was merged. ( https://gem5-review.googlesource.com/c/public/gem5/+/13539 ) Change subject: arch: Get rid of the unused type AnyReg. .. arch: Get rid of the unused type AnyReg. This

[gem5-dev] Change in gem5/gem5[master]: dev: Build the PCI device models even in NULL_ISA builds.

Gabe Black has submitted this change and it was merged. ( https://gem5-review.googlesource.com/c/public/gem5/+/13468 ) Change subject: dev: Build the PCI device models even in NULL_ISA builds. .. dev: Build the PCI device mode

[gem5-dev] Change in gem5/gem5[master]: dev: Build most of the networking devices in the NULL_ISA build.

Gabe Black has submitted this change and it was merged. ( https://gem5-review.googlesource.com/c/public/gem5/+/13469 ) Change subject: dev: Build most of the networking devices in the NULL_ISA build. .. dev: Build most of t

[gem5-dev] Change in gem5/gem5[master]: python: Stop conditionally excluding code from pyobject.cc

Gabe Black has submitted this change and it was merged. ( https://gem5-review.googlesource.com/c/public/gem5/+/13470 ) Change subject: python: Stop conditionally excluding code from pyobject.cc .. python: Stop conditionally ex

[gem5-dev] Change in gem5/gem5[master]: dev: Explicitly specify the endianness for packet accessors.

Gabe Black has submitted this change and it was merged. ( https://gem5-review.googlesource.com/c/public/gem5/+/13462 ) Change subject: dev: Explicitly specify the endianness for packet accessors. .. dev: Explicitly specify the

[gem5-dev] Change in gem5/gem5[master]: dev: Remove using namespace TheISA in uart8250.cc.

Gabe Black has submitted this change and it was merged. ( https://gem5-review.googlesource.com/c/public/gem5/+/13537 ) Change subject: dev: Remove using namespace TheISA in uart8250.cc. .. dev: Remove using namespace TheISA in

[gem5-dev] Change in gem5/gem5[master]: arch: Include some additional headers in arch/generic/mmapped_ipr.cc.

Gabe Black has submitted this change and it was merged. ( https://gem5-review.googlesource.com/c/public/gem5/+/13538 ) Change subject: arch: Include some additional headers in arch/generic/mmapped_ipr.cc. .. arch: Include s

Re: [gem5-dev] cc registers

Yes, the CC registers should both not be a single logical register (I don't think they ever were in x86? can't remember for sure) to avoid false dependencies between unrelated sets of bits, and they shouldn't be a single physical register and should be renamed. I see what you're saying about havin

Re: [gem5-dev] Order of exit callbacks and last stat dump

Hi Andreas, Good question. I don't see any reason why we couldn't reverse the order in simulate.py ( https://gem5.googlesource.com/public/gem5/+/master/src/python/m5/simulate.py#155). TBH, I'm not sure it's really appropriate to have the stats dump like that anyway. I'd rather see explicit calls v

[gem5-dev] Change in gem5/gem5[master]: null: Stop specifying an endianness in isa_traits.hh.

Hello Jason Lowe-Power, Alec Roelke, Andreas Sandberg, I'd like you to reexamine a change. Please visit https://gem5-review.googlesource.com/c/public/gem5/+/13466 to look at the new patch set (#3). Change subject: null: Stop specifying an endianness in isa_traits.hh. ..

[gem5-dev] Change in gem5/gem5[master]: gpu-compute: Explicitly use little endian packet accessors.

Hello Anthony Gutierrez, Jason Lowe-Power, Alec Roelke, Andreas Sandberg, I'd like you to reexamine a change. Please visit https://gem5-review.googlesource.com/c/public/gem5/+/13463 to look at the new patch set (#3). Change subject: gpu-compute: Explicitly use little endian packet accessor

[gem5-dev] Change in gem5/gem5[master]: mem: Mark the guest endianness packet accessors as deprecated.

Gabe Black has uploaded this change for review. ( https://gem5-review.googlesource.com/c/public/gem5/+/13575 Change subject: mem: Mark the guest endianness packet accessors as deprecated. .. mem: Mark the guest endianness

[gem5-dev] Change in gem5/gem5[master]: mem: Delete the packet accessors which use guest endianness.

Hello Jason Lowe-Power, Alec Roelke, Andreas Sandberg, I'd like you to reexamine a change. Please visit https://gem5-review.googlesource.com/c/public/gem5/+/13465 to look at the new patch set (#3). Change subject: mem: Delete the packet accessors which use guest endianness. ...

[gem5-dev] Change in gem5/gem5[master]: mem: Explicitly specify the endianness in the abstract memory.

Hello Jason Lowe-Power, Nikos Nikoleris, Alec Roelke, Andreas Sandberg, I'd like you to reexamine a change. Please visit https://gem5-review.googlesource.com/c/public/gem5/+/13464 to look at the new patch set (#3). Change subject: mem: Explicitly specify the endianness in the abstract me

[gem5-dev] Change in gem5/gem5[master]: gpu-compute: Explicitly use little endian packet accessors.

Gabe Black has submitted this change and it was merged. ( https://gem5-review.googlesource.com/c/public/gem5/+/13463 ) Change subject: gpu-compute: Explicitly use little endian packet accessors. .. gpu-compute: Explicitly use

[gem5-dev] Change in gem5/gem5[master]: mem: Delete the packet accessors which use guest endianness.

Hello Jason Lowe-Power, Alec Roelke, Andreas Sandberg, I'd like you to reexamine a change. Please visit https://gem5-review.googlesource.com/c/public/gem5/+/13465 to look at the new patch set (#4). Change subject: mem: Delete the packet accessors which use guest endianness. ...

[gem5-dev] Change in gem5/gem5[master]: mem: Mark the guest endianness packet accessors as deprecated.

Hello Jason Lowe-Power, Alec Roelke, Andreas Sandberg, I'd like you to reexamine a change. Please visit https://gem5-review.googlesource.com/c/public/gem5/+/13575 to look at the new patch set (#2). Change subject: mem: Mark the guest endianness packet accessors as deprecated. ..

Re: [gem5-dev] Change in gem5/gem5[master]: cpu-kvm, arch-x86: Fix KVM on Intel platforms

To avoid having to sign into github or writing a big comment on an only semi-related CL, I'll put this in an email. I did some digging and I think I know what the problem is from and why your patch fixes it, based on my reading of gem5 and the kernel's source. First, the guest tries to do a mov fr