3rd-party/linux-kernel-module-cheat
1
0
Fork 0
mirror of https://github.com/cirosantilli/linux-kernel-module-cheat.git synced 2026-01-25 03:01:36 +01:00
Code Issues Releases Wiki Activity

x86 paddq: test entire family

Browse Source
This commit is contained in:
Ciro Santilli 六四事件 法轮功
2019-05-11 00:00:00 +00:00
parent 16ecab4af0
commit 300671cd39
2 changed files with 30 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
README.adoc
View File

@@ -11838,8 +11838,17 @@ Once those are done, everything else left on userland is just to learn a huge li
==== x86 SIMD
* SVE2
History:
* link:https://en.wikipedia.org/wiki/MMX_(instruction_set)[MMX]: 1997
* link:https://en.wikipedia.org/wiki/Streaming_SIMD_Extensions[SSE]: Streaming SIMD Extensions. 1999. 128-bit XMM registers.
* link:https://en.wikipedia.org/wiki/SSE2[SSE2]: 2004
** link:userland/arch/x86_64/paddq.S[]
* link:https://en.wikipedia.org/wiki/SSE3[SSE3]: 2006
* link:https://en.wikipedia.org/wiki/SSE4[SSE4]: 2006
* link:https://en.wikipedia.org/wiki/Advanced_Vector_Extensions[AVX]: Advanced Vector Extensions. 2011. 256-bit YMM registers. Extension of XMM.
* AVX2:2013
* AVX-512: 2016. 512-bit ZMM registers. Extension of YMM.
=== rdtsc

30
userland/arch/x86_64/paddq.S
View File

@@ -1,21 +1,31 @@
/* https://github.com/cirosantilli/linux-kernel-module-cheat#x86-simd
*
* Add 4 32-bit integeres in one go.
* Add a bunch of integers in one go.
*/
#include "common.h"
ENTRY
.data
u32_0: .long 0xF111F111, 0xF222F222, 0xF333F333, 0xF444F444
u32_1: .long 0x15551555, 0x16661666, 0x17771777, 0x18881888
u32_expect: .long 0x06670666, 0x08890889, 0x0AAB0AAA, 0x0CCD0CCD
input0: .long 0xF1F1F1F1, 0xF2F2F2F2, 0xF3F3F3F3, 0xF4F4F4F4
input1: .long 0x12121212, 0x13131313, 0x14141414, 0x15151515
paddb_expect: .long 0x03030303, 0x05050505, 0x07070707, 0x09090909
paddw_expect: .long 0x04030403, 0x06050605, 0x08070807, 0x0A090A09
paddd_expect: .long 0x04040403, 0x06060605, 0x08080807, 0x0A0A0A09
paddq_expect: .long 0x04040403, 0x06060606, 0x08080807, 0x0A0A0A0A
.bss
u32_result: .skip 16
result: .skip 16
.text
movups u32_0, %xmm0
movups u32_1, %xmm1
paddq %xmm1, %xmm0
movups %xmm0, u32_result
ASSERT_MEMCMP(u32_result, u32_expect, $0x10)
movups input1, %xmm1
#define TEST(size) \
movups input0, %xmm0; \
padd ## size %xmm1, %xmm0; \
movups %xmm0, result; \
ASSERT_MEMCMP(result, padd ## size ## _expect, $0x10)
TEST(b)
TEST(w)
TEST(d)
TEST(q)
#undef TEST
EXIT