11 Commits

Author	SHA1	Message	Date
thead_admin	d4c68ef2c1	Linux_SDK_V1.4.2 ... Signed-off-by: thead_admin <occ_thead@service.alibaba.com>	2024-01-31 22:09:29 +08:00
thead_admin	e17ac7bab2	Linux_SDK_V1.3.3 ... Signed-off-by: thead_admin <occ_thead@service.alibaba.com>	2024-01-31 22:09:29 +08:00
Han Gao	95a545985b	riscv: default enable xtheadc ... Signed-off-by: Han Gao <gaohan@iscas.ac.cn>	2023-11-29 23:46:21 +08:00
Jisheng Zhang	186355454e	riscv: select ARCH_USE_CMPXCHG_LOCKREF ... Select ARCH_USE_CMPXCHG_LOCKREF to enable the cmpxchg-based lockless lockref implementation for riscv. Using Linus' test case[1] on TH1520 platform, I see a 11.2% improvement. On JH7110 platform, I see 12.0% improvement. Link: http://marc.info/?l=linux-fsdevel&m=137782380714721&w=4 [1] Signed-off-by: Jisheng Zhang <jszhang@kernel.org>	2023-11-29 23:46:21 +08:00
Jisheng Zhang	b25b9b6b16	riscv: select ARCH_HAS_FAST_MULTIPLIER ... Currently, riscv linux requires at least IMA, so all platforms have a multiplier. And I assume the 'mul' efficiency is comparable or better than a sequence of five or so register-dependent arithmetic instructions. Select ARCH_HAS_FAST_MULTIPLIER to get slightly nicer codegen. Refer to commit f9b4192923fa ("[PATCH] bitops: hweight() speedup") for more details. In a simple benchmark test calling hweight64() in a loop, it got: about 14% preformance improvement on JH7110, tested on Milkv Mars. about 23% performance improvement on TH1520 and SG2042, tested on Sipeed LPI4A and SG2042 platform. a slight performance drop on CV1800B, tested on milkv duo. Among all riscv platforms in my hands, this is the only one which sees a slight performance drop. It means the 'mul' isn't quick enough. However, the situation exists on x86 too, for example, P4 doesn't have fast integer multiplies as said in the above commit, x86 also selects ARCH_HAS_FAST_MULTIPLIER. So let's select ARCH_HAS_FAST_MULTIPLIER which can benefit almost riscv platforms. Signed-off-by: Jisheng Zhang <jszhang@kernel.org> Reviewed-by: Samuel Holland <samuel.holland@sifive.com> Tested-by: Samuel Holland <samuel.holland@sifive.com>	2023-11-29 23:46:21 +08:00
thead_admin	afef388b8e	Linux_SDK_V1.2.1 ... Signed-off-by: thead_admin <occ_thead@service.alibaba.com>	2023-08-19 15:26:40 +08:00
Han Gao	0a18500133	chore: restore only support v0p7 ... Signed-off-by: Han Gao <gaohan@iscas.ac.cn>	2023-06-26 16:02:44 +08:00
thead_admin	ada47f394b	Linux_SDK_V1.1.2	2023-03-05 22:36:24 +08:00
thead_admin	221913b496	Linux_SDK_V1.0.3	2023-01-04 13:12:21 +08:00
thead_admin	c20e64a982	Linux_SDK_V1.0.2	2022-11-22 15:53:40 +08:00
thead_admin	c9df2bbe57	Linux_SDK_V0.9.5	2022-09-13 11:05:52 +08:00