On 13-Mar 20:48, Peter Zijlstra wrote:

On Wed, Mar 13, 2019 at 04:12:29PM +0000, Patrick Bellasi wrote:

quoted

On 13-Mar 14:40, Peter Zijlstra wrote:

quoted

On Fri, Feb 08, 2019 at 10:05:40AM +0000, Patrick Bellasi wrote:

quoted

+static inline unsigned int uclamp_bucket_id(unsigned int clamp_value)
+{
+	return clamp_value / UCLAMP_BUCKET_DELTA;
+}
+
+static inline unsigned int uclamp_bucket_value(unsigned int clamp_value)
+{
+	return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value);

	return clamp_value - (clamp_value % UCLAMP_BUCKET_DELTA);

might generate better code; just a single division, instead of a div and
mult.

Wondering if compilers cannot do these optimizations... but yes, looks
cool and will do it in v8, thanks.

I'd be most impressed if they pull this off. Check the generated code
and see I suppose :-)

On x86 the code generated looks exactly the same:

   https://godbolt.org/z/PjmA7k

While on on arm64 it seems the difference boils down to:
 - one single "mul" instruction
vs
 - two instructions: "sub" _plus_ one "multiply subtract"

  https://godbolt.org/z/0shU0S

So, if I din't get something wrong... perhaps the original version is
even better, isn't it?


Test code:

---8<---
#define UCLAMP_BUCKET_DELTA 52

static inline unsigned int uclamp_bucket_id(unsigned int clamp_value)
{
    return clamp_value / UCLAMP_BUCKET_DELTA;
}

static inline unsigned int uclamp_bucket_value1(unsigned int clamp_value)
{
    return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value);
}

static inline unsigned int uclamp_bucket_value2(unsigned int clamp_value)
{
    return clamp_value - (clamp_value % UCLAMP_BUCKET_DELTA);
}

int test1(int argc, char *argv[]) {
    return uclamp_bucket_value1(argc);
}

int test2(int argc, char *argv[]) {
    return uclamp_bucket_value2(argc);
}

int test3(int argc, char *argv[]) {
    return uclamp_bucket_value1(argc) - uclamp_bucket_value2(argc);
}
---8<---

which gives on arm64:

---8<---
test1:
        mov     w1, 60495
        movk    w1, 0x4ec4, lsl 16
        umull   x0, w0, w1
        lsr     x0, x0, 36
        mov     w1, 52
        mul     w0, w0, w1
        ret
test2:
        mov     w1, 60495
        movk    w1, 0x4ec4, lsl 16
        umull   x1, w0, w1
        lsr     x1, x1, 36
        mov     w2, 52
        msub    w1, w1, w2, w0
        sub     w0, w0, w1
        ret
test3:
        mov     w0, 0
        ret
---8<---


-- 
#include <best/regards.h>

Patrick Bellasi