From 7c26472d09548905d8c158b26b6a2b12de6cdc32 Mon Sep 17 00:00:00 2001 From: Tim Peters Date: Mon, 24 Jan 2022 19:06:00 -0600 Subject: [PATCH] bpo-46504: faster code for trial quotient in x_divrem() (GH-30856) * bpo-46504: faster code for trial quotient in x_divrem() This brings x_divrem() back into synch with x_divrem1(), which was changed in bpo-46406 to generate faster code to find machine-word division quotients and remainders. Modern processors compute both with a single machine instruction, but convincing C to exploit that requires writing _less_ "clever" C code. --- Objects/longobject.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/Objects/longobject.c b/Objects/longobject.c index ee20e2638bc..5f0cc579c2c 100644 --- a/Objects/longobject.c +++ b/Objects/longobject.c @@ -2767,8 +2767,15 @@ x_divrem(PyLongObject *v1, PyLongObject *w1, PyLongObject **prem) vtop = vk[size_w]; assert(vtop <= wm1); vv = ((twodigits)vtop << PyLong_SHIFT) | vk[size_w-1]; + /* The code used to compute the remainder via + * r = (digit)(vv - (twodigits)wm1 * q); + * and compilers generally generated code to do the * and -. + * But modern processors generally compute q and r with a single + * instruction, and modern optimizing compilers exploit that if we + * _don't_ try to optimize it. + */ q = (digit)(vv / wm1); - r = (digit)(vv - (twodigits)wm1 * q); /* r = vv % wm1 */ + r = (digit)(vv % wm1); while ((twodigits)wm2 * q > (((twodigits)r << PyLong_SHIFT) | vk[size_w-2])) { --q;