GCC rychle kopirovani pameti
Jaroslav Buchta
jaroslav.buchta na hascomp.cz
Pátek Červen 8 12:09:55 CEST 2018
Resenim je dat fci fastcopy do jineho modulu ale stejne by me zajimalo,
jestli to je normalni.
Dne 08.06.2018 v 12:01 Jaroslav Buchta napsal(a):
> Zdravim, dnes se zase nestiham divit, nevim, na cem je to jak zavisle
> ale bezna funkce memcpy vede jak v optimalizovanem tak v
> neoptimalizovanem prekladu k hloupemu kopirovani po 1B
>
> Zkusil jsem si napsat takovouto fci
>
> void fastcpy(void *dst, void *src, int len)
> {
> while (len >= 8)
> {
> *(uint64_t*)dst = *(uint64_t*)src;
> dst += 8;
> src += 8;
> len -= 8;
> }
> while (len >= 4)
> {
> *(uint32_t*)dst = *(uint32_t*)src;
> dst += 4;
> src += 4;
> len -= 4;
> }
> if (len >= 2)
> {
> *(uint16_t*)dst = *(uint16_t*)src;
> dst += 2;
> src += 2;
> len -= 2;
> }
> if (len != 0)
> {
> *(uint8_t*)dst = *(uint8_t*)src;
> }
> }
>
> ktera vede ke kyzenemu vysledku, je to vyrazne rychlejsi, ovsem POUZE,
> KDYZ NENI NASTAVENA OPTIMALIZACE O3, tam nejak prekladac usoudi, ze je
> to kopirovani bloku a vola memcpy... Je to vubec mozne, nebo delam
> nejakou chybu???
>
> Jak mam vynutit volani te funkce? (krome obchuzky, ze pro ni zakazu
> optimalizaci...)
>
>
> ////////////////////////////////
>
> Optimalizovany kod:
>
> 100 mccState.iB = (float)(mccState.bufAdc1[2]);
> 080004c2: vstr s14, [r4, #68] ; 0x44
> 080004c6: vstr s15, [r4, #72] ; 0x48
> 102 if (!mccStateCopy.f_LockCopy)
> 080004ca: bmi.n 0x8000400 <HAL_ADC_ConvCpltCallback+24>
> 080004cc: movs r2, #72 ; 0x48
> 080004ce: mov r1, r4
> 080004d0: add.w r0, r4, #76 ; 0x4c
> 080004d4: bl 0x8005e00 <memcpy>
> 72 *(uint32_t*)dst = *(uint32_t*)src;
>
>
> Neoptimalizovany kod:
>
> 101 mccState.iC = (float)(mccState.bufAdc1[3]);
> 08000528: vmov s15, r1
> 0800052c: vcvt.f32.u32 s15, s15
> 08000530: vstr s15, [r3, #72] ; 0x48
> 102 if (!mccStateCopy.f_LockCopy)
> 08000534: ldrb.w r3, [r3, #76] ; 0x4c
> 08000538: tst.w r3, #2
> 0800053c: bne.n 0x8000470 <HAL_ADC_ConvCpltCallback+24>
> 104 fastcpy((void *)&mccStateCopy, (void
> *)&mccState, sizeof(MCCOMSTATE));
> 0800053e: ldr r0, [pc, #16] ; (0x8000550
> <HAL_ADC_ConvCpltCallback+248>)
> 08000540: movs r2, #76 ; 0x4c
> 08000542: mov r1, r0
> 08000544: add r0, r2
> 08000546: bl 0x80003f4 <fastcpy>
>
>
> fastcpy:
> 080003f4: cmp r2, #7
> 080003f6: ble.n 0x800043a <fastcpy+70>
> 62 {
> 080003f8: push {r4, r5}
> 65 *(uint64_t*)dst = *(uint64_t*)src;
> 080003fa: ldrd r4, r5, [r1], #8
> 080003fe: strd r4, r5, [r0], #8
> 68 len -= 8;
> 08000402: subs r2, #8
> 63 while (len >= 8)
> 08000404: cmp r2, #7
> 08000406: bgt.n 0x80003fa <fastcpy+6>
> 08000408: b.n 0x8000414 <fastcpy+32>
> 72 *(uint32_t*)dst = *(uint32_t*)src;
> 0800040a: ldr.w r3, [r1], #4
> 0800040e: str.w r3, [r0], #4
> 75 len -= 4;
> 08000412: subs r2, #4
> 70 while (len >= 4)
> 08000414: cmp r2, #3
> 08000416: bgt.n 0x800040a <fastcpy+22>
> 77 if (len >= 2)
> 08000418: cmp r2, #1
> 0800041a: ble.n 0x8000426 <fastcpy+50>
> 79 *(uint16_t*)dst = *(uint16_t*)src;
> 0800041c: ldrh.w r3, [r1], #2
> 08000420: strh.w r3, [r0], #2
> 82 len -= 2;
> 08000424: subs r2, #2
> 84 if (len != 0)
> 08000426: cbz r2, 0x800042c <fastcpy+56>
> 86 *(uint8_t*)dst = *(uint8_t*)src;
> 08000428: ldrb r3, [r1, #0]
> 0800042a: strb r3, [r0, #0]
> 88 }
> 0800042c: pop {r4, r5}
> 0800042e: bx lr
> 08000430: ldr.w r3, [r1], #4
> 08000434: str.w r3, [r0], #4
> 75 len -= 4;
> 08000438: subs r2, #4
> 0800043a: cmp r2, #3
> 0800043c: bgt.n 0x8000430 <fastcpy+60>
> 0800043e: cmp r2, #1
> 08000440: ble.n 0x800044c <fastcpy+88>
> 08000442: ldrh.w r3, [r1], #2
> 08000446: strh.w r3, [r0], #2
> 82 len -= 2;
> 0800044a: subs r2, #2
> 84 if (len != 0)
> 0800044c: cmp r2, #0
> 0800044e: beq.n 0x800042e <fastcpy+58>
> 86 *(uint8_t*)dst = *(uint8_t*)src;
> 08000450: ldrb r3, [r1, #0]
> 08000452: strb r3, [r0, #0]
> 08000454: bx lr
>
>
>
> _______________________________________________
> HW-list mailing list - sponsored by www.HW.cz
> Hw-list na list.hw.cz
> http://list.hw.cz/mailman/listinfo/hw-list
Další informace o konferenci Hw-list