.. | .. |
---|
| 1 | +# SPDX-License-Identifier: GPL-2.0-only |
---|
1 | 2 | comment "Processor Features" |
---|
2 | 3 | |
---|
3 | 4 | config CPU_BIG_ENDIAN |
---|
.. | .. |
---|
6 | 7 | config CPU_LITTLE_ENDIAN |
---|
7 | 8 | bool "Little endian" |
---|
8 | 9 | default y |
---|
| 10 | + |
---|
| 11 | +config FPU |
---|
| 12 | + bool "FPU support" |
---|
| 13 | + default n |
---|
| 14 | + help |
---|
| 15 | + If FPU ISA is used in user space, this configuration shall be Y to |
---|
| 16 | + enable required support in kernel such as fpu context switch and |
---|
| 17 | + fpu exception handler. |
---|
| 18 | + |
---|
| 19 | + If no FPU ISA is used in user space, say N. |
---|
| 20 | + |
---|
| 21 | +config LAZY_FPU |
---|
| 22 | + bool "lazy FPU support" |
---|
| 23 | + depends on FPU |
---|
| 24 | + default y |
---|
| 25 | + help |
---|
| 26 | + Say Y here to enable the lazy FPU scheme. The lazy FPU scheme can |
---|
| 27 | + enhance system performance by reducing the context switch |
---|
| 28 | + frequency of the FPU register. |
---|
| 29 | + |
---|
| 30 | + For normal case, say Y. |
---|
| 31 | + |
---|
| 32 | +config SUPPORT_DENORMAL_ARITHMETIC |
---|
| 33 | + bool "Denormal arithmetic support" |
---|
| 34 | + depends on FPU |
---|
| 35 | + default n |
---|
| 36 | + help |
---|
| 37 | + Say Y here to enable arithmetic of denormalized number. Enabling |
---|
| 38 | + this feature can enhance the precision for tininess number. |
---|
| 39 | + However, performance loss in float point calculations is |
---|
| 40 | + possibly significant due to additional FPU exception. |
---|
| 41 | + |
---|
| 42 | + If the calculated tolerance for tininess number is not critical, |
---|
| 43 | + say N to prevent performance loss. |
---|
9 | 44 | |
---|
10 | 45 | config HWZOL |
---|
11 | 46 | bool "hardware zero overhead loop support" |
---|
.. | .. |
---|
38 | 73 | the cache aliasing issue. The rest cpus(N13, N10 and D10) are |
---|
39 | 74 | implemented as VIPT data cache. It may cause the cache aliasing issue |
---|
40 | 75 | if its cache way size is larger than page size. You can specify the |
---|
41 | | - CPU type direcly or choose CPU_V3 if unsure. |
---|
| 76 | + CPU type directly or choose CPU_V3 if unsure. |
---|
42 | 77 | |
---|
43 | 78 | A kernel built for N10 is able to run on N15, D15, N13, N10 or D10. |
---|
44 | 79 | A kernel built for N15 is able to run on N15 or D15. |
---|
.. | .. |
---|
122 | 157 | config HIGHMEM |
---|
123 | 158 | bool "High Memory Support" |
---|
124 | 159 | depends on MMU && !CPU_CACHE_ALIASING |
---|
| 160 | + select KMAP_LOCAL |
---|
125 | 161 | help |
---|
126 | 162 | The address space of Andes processors is only 4 Gigabytes large |
---|
127 | 163 | and it has to accommodate user address space, kernel address |
---|
.. | .. |
---|
143 | 179 | Say Y here to enable L2 cache if your SoC are integrated with L2CC. |
---|
144 | 180 | If unsure, say N. |
---|
145 | 181 | |
---|
| 182 | +config HW_PRE |
---|
| 183 | + bool "Enable hardware prefetcher" |
---|
| 184 | + default y |
---|
| 185 | + help |
---|
| 186 | + Say Y here to enable hardware prefetcher feature. |
---|
| 187 | + Only when CPU_VER.REV >= 0x09 can support. |
---|
| 188 | + |
---|
146 | 189 | menu "Memory configuration" |
---|
147 | 190 | |
---|
148 | 191 | choice |
---|