There are cases when we need to explicitly unroll loops. For example, cache operations, filling DMA descriptors on very high speeds etc. Add compiler-specific attribute macros to give the compiler a hint that we'd like to unroll a loop. Example usage: #define UNROLL_BATCH 8 unrolled_count(UNROLL_BATCH) for (u32 i = 0; i < UNROLL_BATCH; i++) op(priv, i); Note that sometimes the compilers won't unroll loops if they think this would have worse optimization and perf than without unrolling, and that unroll attributes are available only starting GCC 8. For older compiler versions, no hints/attributes will be applied. For better unrolling/parallelization, don't have any variables that interfere between iterations except for the iterator itself. Co-developed-by: Jose E. Marchesi <jose.marchesi@xxxxxxxxxx> # pragmas Signed-off-by: Jose E. Marchesi <jose.marchesi@xxxxxxxxxx> Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@xxxxxxxxx> Signed-off-by: Alexander Lobakin <aleksander.lobakin@xxxxxxxxx> --- include/linux/unroll.h | 43 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) diff --git a/include/linux/unroll.h b/include/linux/unroll.h index d42fd6366373..2870c89a93f4 100644 --- a/include/linux/unroll.h +++ b/include/linux/unroll.h @@ -9,6 +9,49 @@ #include <linux/args.h> +#ifdef CONFIG_CC_IS_CLANG +#define __pick_unrolled(x, y) _Pragma(#x) +#elif CONFIG_GCC_VERSION >= 80000 +#define __pick_unrolled(x, y) _Pragma(#y) +#else +#define __pick_unrolled(x, y) /* not supported */ +#endif + +/** + * unrolled - loop attributes to ask the compiler to unroll it + * + * Usage: + * + * #define BATCH 4 + * unrolled_count(BATCH) + * for (u32 i = 0; i < BATCH; i++) + * // loop body without cross-iteration dependencies + * + * This is only a hint and the compiler is free to disable unrolling if it + * thinks the count is suboptimal and may hurt performance and/or hugely + * increase object code size. + * Not having any cross-iteration dependencies (i.e. when iter x + 1 depends + * on what iter x will do with variables) is not a strict requirement, but + * provides best performance and object code size. + * Available only on Clang and GCC 8.x onwards. + */ + +/* Ask the compiler to pick an optimal unroll count, Clang only */ +#define unrolled \ + __pick_unrolled(clang loop unroll(enable), /* nothing */) + +/* Unroll each @n iterations of a loop */ +#define unrolled_count(n) \ + __pick_unrolled(clang loop unroll_count(n), GCC unroll n) + +/* Unroll the whole loop */ +#define unrolled_full \ + __pick_unrolled(clang loop unroll(full), GCC unroll 65534) + +/* Never unroll a loop */ +#define unrolled_none \ + __pick_unrolled(clang loop unroll(disable), GCC unroll 1) + #define UNROLL(N, MACRO, args...) CONCATENATE(__UNROLL_, N)(MACRO, args) #define __UNROLL_0(MACRO, args...) -- 2.46.2
