| Author | Tokens | Token Proportion | Commits | Commit Proportion |
|---|---|---|---|---|
| Andi Kleen | 315 | 42.74% | 2 | 11.11% |
| Jan Beulich | 253 | 34.33% | 2 | 11.11% |
| Ard Biesheuvel | 48 | 6.51% | 1 | 5.56% |
| Linus Torvalds (pre-git) | 41 | 5.56% | 2 | 11.11% |
| Suresh B. Siddha | 34 | 4.61% | 1 | 5.56% |
| Joe Perches | 20 | 2.71% | 2 | 11.11% |
| Thomas Gleixner | 12 | 1.63% | 2 | 11.11% |
| Jeremy Fitzhardinge | 4 | 0.54% | 1 | 5.56% |
| Vegard Nossum | 4 | 0.54% | 1 | 5.56% |
| Alexander (Sasha) Levin | 2 | 0.27% | 1 | 5.56% |
| David Howells | 2 | 0.27% | 1 | 5.56% |
| Ingo Molnar | 1 | 0.14% | 1 | 5.56% |
| Jim Kukunas | 1 | 0.14% | 1 | 5.56% |
| Total | 737 | 18 |
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502
/* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _ASM_X86_XOR_H #define _ASM_X86_XOR_H /* * Optimized RAID-5 checksumming functions for SSE. */ /* * Cache avoiding checksumming functions utilizing KNI instructions * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo) */ /* * Based on * High-speed RAID5 checksumming functions utilizing SSE instructions. * Copyright (C) 1998 Ingo Molnar. */ /* * x86-64 changes / gcc fixes from Andi Kleen. * Copyright 2002 Andi Kleen, SuSE Labs. * * This hasn't been optimized for the hammer yet, but there are likely * no advantages to be gotten from x86-64 here anyways. */ #include <asm/fpu/api.h> #ifdef CONFIG_X86_32 /* reduce register pressure */ # define XOR_CONSTANT_CONSTRAINT "i" #else # define XOR_CONSTANT_CONSTRAINT "re" #endif #define OFFS(x) "16*("#x")" #define PF_OFFS(x) "256+16*("#x")" #define PF0(x) " prefetchnta "PF_OFFS(x)"(%[p1]) ;\n" #define LD(x, y) " movaps "OFFS(x)"(%[p1]), %%xmm"#y" ;\n" #define ST(x, y) " movaps %%xmm"#y", "OFFS(x)"(%[p1]) ;\n" #define PF1(x) " prefetchnta "PF_OFFS(x)"(%[p2]) ;\n" #define PF2(x) " prefetchnta "PF_OFFS(x)"(%[p3]) ;\n" #define PF3(x) " prefetchnta "PF_OFFS(x)"(%[p4]) ;\n" #define PF4(x) " prefetchnta "PF_OFFS(x)"(%[p5]) ;\n" #define XO1(x, y) " xorps "OFFS(x)"(%[p2]), %%xmm"#y" ;\n" #define XO2(x, y) " xorps "OFFS(x)"(%[p3]), %%xmm"#y" ;\n" #define XO3(x, y) " xorps "OFFS(x)"(%[p4]), %%xmm"#y" ;\n" #define XO4(x, y) " xorps "OFFS(x)"(%[p5]), %%xmm"#y" ;\n" #define NOP(x) #define BLK64(pf, op, i) \ pf(i) \ op(i, 0) \ op(i + 1, 1) \ op(i + 2, 2) \ op(i + 3, 3) static void xor_sse_2(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p2) { unsigned long lines = bytes >> 8; kernel_fpu_begin(); asm volatile( #undef BLOCK #define BLOCK(i) \ LD(i, 0) \ LD(i + 1, 1) \ PF1(i) \ PF1(i + 2) \ LD(i + 2, 2) \ LD(i + 3, 3) \ PF0(i + 4) \ PF0(i + 6) \ XO1(i, 0) \ XO1(i + 1, 1) \ XO1(i + 2, 2) \ XO1(i + 3, 3) \ ST(i, 0) \ ST(i + 1, 1) \ ST(i + 2, 2) \ ST(i + 3, 3) \ PF0(0) PF0(2) " .align 32 ;\n" " 1: ;\n" BLOCK(0) BLOCK(4) BLOCK(8) BLOCK(12) " add %[inc], %[p1] ;\n" " add %[inc], %[p2] ;\n" " dec %[cnt] ;\n" " jnz 1b ;\n" : [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2) : [inc] XOR_CONSTANT_CONSTRAINT (256UL) : "memory"); kernel_fpu_end(); } static void xor_sse_2_pf64(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p2) { unsigned long lines = bytes >> 8; kernel_fpu_begin(); asm volatile( #undef BLOCK #define BLOCK(i) \ BLK64(PF0, LD, i) \ BLK64(PF1, XO1, i) \ BLK64(NOP, ST, i) \ " .align 32 ;\n" " 1: ;\n" BLOCK(0) BLOCK(4) BLOCK(8) BLOCK(12) " add %[inc], %[p1] ;\n" " add %[inc], %[p2] ;\n" " dec %[cnt] ;\n" " jnz 1b ;\n" : [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2) : [inc] XOR_CONSTANT_CONSTRAINT (256UL) : "memory"); kernel_fpu_end(); } static void xor_sse_3(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p2, const unsigned long * __restrict p3) { unsigned long lines = bytes >> 8; kernel_fpu_begin(); asm volatile( #undef BLOCK #define BLOCK(i) \ PF1(i) \ PF1(i + 2) \ LD(i, 0) \ LD(i + 1, 1) \ LD(i + 2, 2) \ LD(i + 3, 3) \ PF2(i) \ PF2(i + 2) \ PF0(i + 4) \ PF0(i + 6) \ XO1(i, 0) \ XO1(i + 1, 1) \ XO1(i + 2, 2) \ XO1(i + 3, 3) \ XO2(i, 0) \ XO2(i + 1, 1) \ XO2(i + 2, 2) \ XO2(i + 3, 3) \ ST(i, 0) \ ST(i + 1, 1) \ ST(i + 2, 2) \ ST(i + 3, 3) \ PF0(0) PF0(2) " .align 32 ;\n" " 1: ;\n" BLOCK(0) BLOCK(4) BLOCK(8) BLOCK(12) " add %[inc], %[p1] ;\n" " add %[inc], %[p2] ;\n" " add %[inc], %[p3] ;\n" " dec %[cnt] ;\n" " jnz 1b ;\n" : [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3) : [inc] XOR_CONSTANT_CONSTRAINT (256UL) : "memory"); kernel_fpu_end(); } static void xor_sse_3_pf64(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p2, const unsigned long * __restrict p3) { unsigned long lines = bytes >> 8; kernel_fpu_begin(); asm volatile( #undef BLOCK #define BLOCK(i) \ BLK64(PF0, LD, i) \ BLK64(PF1, XO1, i) \ BLK64(PF2, XO2, i) \ BLK64(NOP, ST, i) \ " .align 32 ;\n" " 1: ;\n" BLOCK(0) BLOCK(4) BLOCK(8) BLOCK(12) " add %[inc], %[p1] ;\n" " add %[inc], %[p2] ;\n" " add %[inc], %[p3] ;\n" " dec %[cnt] ;\n" " jnz 1b ;\n" : [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3) : [inc] XOR_CONSTANT_CONSTRAINT (256UL) : "memory"); kernel_fpu_end(); } static void xor_sse_4(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p2, const unsigned long * __restrict p3, const unsigned long * __restrict p4) { unsigned long lines = bytes >> 8; kernel_fpu_begin(); asm volatile( #undef BLOCK #define BLOCK(i) \ PF1(i) \ PF1(i + 2) \ LD(i, 0) \ LD(i + 1, 1) \ LD(i + 2, 2) \ LD(i + 3, 3) \ PF2(i) \ PF2(i + 2) \ XO1(i, 0) \ XO1(i + 1, 1) \ XO1(i + 2, 2) \ XO1(i + 3, 3) \ PF3(i) \ PF3(i + 2) \ PF0(i + 4) \ PF0(i + 6) \ XO2(i, 0) \ XO2(i + 1, 1) \ XO2(i + 2, 2) \ XO2(i + 3, 3) \ XO3(i, 0) \ XO3(i + 1, 1) \ XO3(i + 2, 2) \ XO3(i + 3, 3) \ ST(i, 0) \ ST(i + 1, 1) \ ST(i + 2, 2) \ ST(i + 3, 3) \ PF0(0) PF0(2) " .align 32 ;\n" " 1: ;\n" BLOCK(0) BLOCK(4) BLOCK(8) BLOCK(12) " add %[inc], %[p1] ;\n" " add %[inc], %[p2] ;\n" " add %[inc], %[p3] ;\n" " add %[inc], %[p4] ;\n" " dec %[cnt] ;\n" " jnz 1b ;\n" : [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4) : [inc] XOR_CONSTANT_CONSTRAINT (256UL) : "memory"); kernel_fpu_end(); } static void xor_sse_4_pf64(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p2, const unsigned long * __restrict p3, const unsigned long * __restrict p4) { unsigned long lines = bytes >> 8; kernel_fpu_begin(); asm volatile( #undef BLOCK #define BLOCK(i) \ BLK64(PF0, LD, i) \ BLK64(PF1, XO1, i) \ BLK64(PF2, XO2, i) \ BLK64(PF3, XO3, i) \ BLK64(NOP, ST, i) \ " .align 32 ;\n" " 1: ;\n" BLOCK(0) BLOCK(4) BLOCK(8) BLOCK(12) " add %[inc], %[p1] ;\n" " add %[inc], %[p2] ;\n" " add %[inc], %[p3] ;\n" " add %[inc], %[p4] ;\n" " dec %[cnt] ;\n" " jnz 1b ;\n" : [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4) : [inc] XOR_CONSTANT_CONSTRAINT (256UL) : "memory"); kernel_fpu_end(); } static void xor_sse_5(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p2, const unsigned long * __restrict p3, const unsigned long * __restrict p4, const unsigned long * __restrict p5) { unsigned long lines = bytes >> 8; kernel_fpu_begin(); asm volatile( #undef BLOCK #define BLOCK(i) \ PF1(i) \ PF1(i + 2) \ LD(i, 0) \ LD(i + 1, 1) \ LD(i + 2, 2) \ LD(i + 3, 3) \ PF2(i) \ PF2(i + 2) \ XO1(i, 0) \ XO1(i + 1, 1) \ XO1(i + 2, 2) \ XO1(i + 3, 3) \ PF3(i) \ PF3(i + 2) \ XO2(i, 0) \ XO2(i + 1, 1) \ XO2(i + 2, 2) \ XO2(i + 3, 3) \ PF4(i) \ PF4(i + 2) \ PF0(i + 4) \ PF0(i + 6) \ XO3(i, 0) \ XO3(i + 1, 1) \ XO3(i + 2, 2) \ XO3(i + 3, 3) \ XO4(i, 0) \ XO4(i + 1, 1) \ XO4(i + 2, 2) \ XO4(i + 3, 3) \ ST(i, 0) \ ST(i + 1, 1) \ ST(i + 2, 2) \ ST(i + 3, 3) \ PF0(0) PF0(2) " .align 32 ;\n" " 1: ;\n" BLOCK(0) BLOCK(4) BLOCK(8) BLOCK(12) " add %[inc], %[p1] ;\n" " add %[inc], %[p2] ;\n" " add %[inc], %[p3] ;\n" " add %[inc], %[p4] ;\n" " add %[inc], %[p5] ;\n" " dec %[cnt] ;\n" " jnz 1b ;\n" : [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4), [p5] "+r" (p5) : [inc] XOR_CONSTANT_CONSTRAINT (256UL) : "memory"); kernel_fpu_end(); } static void xor_sse_5_pf64(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p2, const unsigned long * __restrict p3, const unsigned long * __restrict p4, const unsigned long * __restrict p5) { unsigned long lines = bytes >> 8; kernel_fpu_begin(); asm volatile( #undef BLOCK #define BLOCK(i) \ BLK64(PF0, LD, i) \ BLK64(PF1, XO1, i) \ BLK64(PF2, XO2, i) \ BLK64(PF3, XO3, i) \ BLK64(PF4, XO4, i) \ BLK64(NOP, ST, i) \ " .align 32 ;\n" " 1: ;\n" BLOCK(0) BLOCK(4) BLOCK(8) BLOCK(12) " add %[inc], %[p1] ;\n" " add %[inc], %[p2] ;\n" " add %[inc], %[p3] ;\n" " add %[inc], %[p4] ;\n" " add %[inc], %[p5] ;\n" " dec %[cnt] ;\n" " jnz 1b ;\n" : [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4), [p5] "+r" (p5) : [inc] XOR_CONSTANT_CONSTRAINT (256UL) : "memory"); kernel_fpu_end(); } static struct xor_block_template xor_block_sse_pf64 = { .name = "prefetch64-sse", .do_2 = xor_sse_2_pf64, .do_3 = xor_sse_3_pf64, .do_4 = xor_sse_4_pf64, .do_5 = xor_sse_5_pf64, }; #undef LD #undef XO1 #undef XO2 #undef XO3 #undef XO4 #undef ST #undef NOP #undef BLK64 #undef BLOCK #undef XOR_CONSTANT_CONSTRAINT #ifdef CONFIG_X86_32 # include <asm/xor_32.h> #else # include <asm/xor_64.h> #endif #define XOR_SELECT_TEMPLATE(FASTEST) \ AVX_SELECT(FASTEST) #endif /* _ASM_X86_XOR_H */
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with Cregit http://github.com/cregit/cregit
Version 2.0-RC1