| Rev |
Log message |
Author |
Age |
Path |
| 87 |
Added support for "When an Operand2 constant is used with the instructions MOVS, MVNS, ANDS, ORRS, ORNS, EORS, BICS, TEQ or TST, the carry flag is updated to bit[31] of the constant, if the constant is greater than 255 and can be produced by shifting an 8-bit value" to amber23 |
csantifort |
3526d 16h |
/amber/trunk/hw/tests/ |
| 86 |
Fixed bug in amber 25 where a read was taken from user mode register in subervisor mode immediately following a ldm to user mode registers |
csantifort |
3539d 12h |
/amber/trunk/hw/tests/ |
| 83 |
Fixed bug with carry bit - now only use the carry bit as an input to specific instruments that use it - add with carry and subtract with carry |
csantifort |
3539d 20h |
/amber/trunk/hw/tests/ |
| 82 |
Fixed overflag bug, ldmia user regs bug and status_bits_mode set on non-ececuting command bug |
csantifort |
3553d 08h |
/amber/trunk/hw/tests/ |
| 70 |
The mlas_bug testcase tried to use stack without setting stack pointer
register, causing unpredictable behavoiur.
The patch uses an expilict stack area for the test.
Contributed by: Dmitry Tarnyagin <dmitry.tarnyagin@lockless.no> |
csantifort |
4239d 14h |
/amber/trunk/hw/tests/ |
| 60 |
Bug fix; removed a combinational loop from the a25_decode logic. |
csantifort |
4744d 11h |
/amber/trunk/hw/tests/ |
| 56 |
Remove the timeouts file from svn. Its an output file and gets now just gets created automatically
when sims are run for the first time. |
csantifort |
4814d 12h |
/amber/trunk/hw/tests/ |
| 54 |
Bug fix for bug reported by Botao Lee. The mode bits in the decode stage did not change immediately
after a mode switch from a teqp instruction, but 1 cycle later. This meant the wrong set of registers
was selected for writing to for 1 clock cycle. |
csantifort |
4831d 11h |
/amber/trunk/hw/tests/ |
| 50 |
Revert to previous version |
csantifort |
4887d 09h |
/amber/trunk/hw/tests/ |
| 49 |
Added a note n how to change timeouts |
csantifort |
4887d 09h |
/amber/trunk/hw/tests/ |
| 48 |
Fixed a bug in linux that caused the os to not return to the running application after an interrupt.
Hello-world now runs stand-alone again.
Added initrd-200k-dhry, a disk image that uses the dhry program for init. |
csantifort |
4891d 16h |
/amber/trunk/hw/tests/ |
| 40 |
Added wishbone bus jitter testing option.
Cleaned up waveform log .do files, now seperate files for a23 and a25 cores.
Added vmlinux executable elf file for running on hardware. |
csantifort |
4943d 09h |
/amber/trunk/hw/tests/ |
| 36 |
Changed boot_mem for the a25 system to be 128 bits wide to match the 128-bit wide wishbone bus |
csantifort |
4946d 08h |
/amber/trunk/hw/tests/ |
| 35 |
Amber25 improvements:
Use 128-bit wishbone bus, instead of 32-bit to reduce cache miss fetch times
Use a fast barrel shifter for shifts between 0 and 4 to improve timing
Use a 2 cycle full barrel shifter for complex shifts |
csantifort |
4947d 16h |
/amber/trunk/hw/tests/ |
| 20 |
Added feature to A25 core to directly use a read value from the write back stage
to reduce the stall to 1 cycle when there is a register conflict with the
following instruction. This increases performance by about 3%. |
csantifort |
5032d 15h |
/amber/trunk/hw/tests/ |
| 17 |
amber25 core bug fix. The return address for irq interrupts was off by 4 bytes
when the interrupt occurred during a stm instruction with the following instruction
having some register conflicts. Added test irq_stm to catch the bug.
Cleaned up some header descriptions |
csantifort |
5036d 13h |
/amber/trunk/hw/tests/ |
| 15 |
Copied amber to amber23, Many system changes to support new amber25 core. |
csantifort |
5039d 04h |
/amber/trunk/hw/tests/ |
| 11 |
Added vmlinux test. |
csantifort |
5055d 16h |
/amber/trunk/hw/tests/ |
| 6 |
Set ignore property for output files |
csantifort |
5068d 13h |
/amber/trunk/hw/tests/ |
| 2 |
Baseline release of the Amber 2 core |
csantifort |
5069d 14h |
/amber/trunk/hw/tests/ |
