972 	add	%o0, 4, %o0		! advance SRC by 4
1003 	add	%o0, 8, %o0		! update SRC
1014 	add	%o0, 2, %o0		! advance SRC by 2
1084 	add	%o0, 4, %o0		! advance SRC by 4
1098 	add	%o0, 32, %o0		! advance SRC by 32
1113 	add	%o0, 8, %o0		! advance SRC by 8
1148 	add	%o0, 16, %o0		! advance SRC by 16
1163 	add	%o0, 4, %o0		! advance SRC by 4
1195 	add	%o0, 8, %o0		! advance SRC by 8
1266 #define	SRC	%i3
1275 	! Using SRC as a tmp here
1281 	ldub	[REALSRC], SRC		! move 4 bytes per loop iteration
1282 	stb	SRC, [DST]
1284 	ldub	[REALSRC + 1], SRC
1286 	stb	SRC, [DST + 1]
1287 	ldub	[REALSRC - 2], SRC
1289 	stb	SRC, [DST - 2]
1290 	ldub	[REALSRC - 1], SRC
1292 	  stb	SRC, [DST - 1]
1297 1:	ldub	[REALSRC], SRC
1302 	  stb	SRC, [DST - 1]
1306 	andn	REALSRC, 0x7, SRC
1308 	! SRC - 8-byte aligned
1310 	ldd	[SRC], %f0
1311 	prefetch [SRC + (1 * VIS_BLOCKSIZE)], #n_reads
1313 	ldd	[SRC + 0x08], %f2
1314 	prefetch [SRC + (2 * VIS_BLOCKSIZE)], #n_reads
1316 	ldd	[SRC + 0x10], %f4
1317 	prefetch [SRC + (3 * VIS_BLOCKSIZE)], #n_reads
1319 	ldd	[SRC + 0x18], %f6
1320 	prefetch [SRC + (4 * VIS_BLOCKSIZE)], #one_read
1322 	ldd	[SRC + 0x20], %f8
1323 	prefetch [SRC + (8 * VIS_BLOCKSIZE)], #one_read
1325 	ldd	[SRC + 0x28], %f10
1326 	prefetch [SRC + (12 * VIS_BLOCKSIZE)], #one_read
1328 	ldd	[SRC + 0x30], %f12
1329 	prefetch [SRC + (16 * VIS_BLOCKSIZE)], #one_read
1331 	ldd	[SRC + 0x38], %f14
1332 	ldd	[SRC + VIS_BLOCKSIZE], %f0
1334 	add	SRC, VIS_BLOCKSIZE, SRC
1335 	prefetch [SRC + (19 * VIS_BLOCKSIZE)], #one_read
1338 	  prefetch [SRC + (23 * VIS_BLOCKSIZE)], #one_read
1341 	ldd	[SRC + 0x08], %f2
1343 	ldd	[SRC + 0x10], %f4
1346 	ldd	[SRC + 0x18], %f6
1348 	ldd	[SRC + 0x20], %f8
1350 	ldd	[SRC + 0x28], %f10
1352 	ldd	[SRC + 0x30], %f12
1355 	ldd	[SRC + 0x38], %f14
1358 	ldd	[SRC + VIS_BLOCKSIZE], %f0
1361 	prefetch [SRC + (3 * VIS_BLOCKSIZE)], #n_reads
1362 	add	SRC, VIS_BLOCKSIZE, SRC
1363 	prefetch [SRC + ((OLYMPUS_C_PREFETCH) * VIS_BLOCKSIZE)], #one_read
1366 	  prefetch [SRC + ((OLYMPUS_C_2ND_PREFETCH) * VIS_BLOCKSIZE)], #one_read
1382 	ldd	[SRC + 0x08], %f2
1384 	ldd	[SRC + 0x10], %f4
1387 	ldd	[SRC + 0x18], %f6
1389 	ldd	[SRC + 0x20], %f8
1391 	ldd	[SRC + 0x28], %f10
1393 	ldd	[SRC + 0x30], %f12
1395 	ldd	[SRC + 0x38], %f14
1399 	add	SRC, VIS_BLOCKSIZE, SRC
1540 	mov	REALSRC, SRC
1542 	ldd	[SRC], %f0
1543 	prefetch [SRC + (1 * VIS_BLOCKSIZE)], #n_reads
1544 	ldd	[SRC + 0x08], %f2
1545 	prefetch [SRC + (2 * VIS_BLOCKSIZE)], #n_reads
1547 	ldd	[SRC + 0x10], %f4
1548 	prefetch [SRC + (3 * VIS_BLOCKSIZE)], #n_reads
1550 	ldd	[SRC + 0x18], %f6
1551 	prefetch [SRC + (4 * VIS_BLOCKSIZE)], #one_read
1553 	ldd	[SRC + 0x20], %f8
1554 	prefetch [SRC + (8 * VIS_BLOCKSIZE)], #one_read
1556 	ldd	[SRC + 0x28], %f10
1557 	prefetch [SRC + (12 * VIS_BLOCKSIZE)], #one_read
1559 	ldd	[SRC + 0x30], %f12
1560 	prefetch [SRC + (16 * VIS_BLOCKSIZE)], #one_read
1562 	ldd	[SRC + 0x38], %f14
1563 	ldd	[SRC + VIS_BLOCKSIZE], %f0
1565 	add	SRC, VIS_BLOCKSIZE, SRC
1566 	prefetch [SRC + (19 * VIS_BLOCKSIZE)], #one_read
1568 	prefetch [SRC + (23 * VIS_BLOCKSIZE)], #one_read
1571 	ldd	[SRC + 0x08], %f2
1573 	ldd	[SRC + 0x10], %f4
1576 	ldd	[SRC + 0x18], %f6
1578 	ldd	[SRC + 0x20], %f8
1580 	ldd	[SRC + 0x28], %f10
1582 	ldd	[SRC + 0x30], %f12
1584 	ldd	[SRC + 0x38], %f14
1586 	ldd	[SRC + VIS_BLOCKSIZE], %f0
1589 	prefetch [SRC + (3 * VIS_BLOCKSIZE)], #n_reads
1591 	prefetch [SRC + ((OLYMPUS_C_PREFETCH) * VIS_BLOCKSIZE)], #one_read
1592 	add	SRC, VIS_BLOCKSIZE, SRC
1595 	  prefetch [SRC + ((OLYMPUS_C_2ND_PREFETCH) * VIS_BLOCKSIZE)], #one_read
1598 	ldd	[SRC + 0x08], %f2
1600 	ldd	[SRC + 0x10], %f4
1603 	ldd	[SRC + 0x18], %f6
1605 	ldd	[SRC + 0x20], %f8
1607 	ldd	[SRC + 0x28], %f10
1609 	ldd	[SRC + 0x30], %f12
1611 	ldd	[SRC + 0x38], %f14
1615 	add	SRC, VIS_BLOCKSIZE, SRC
1861 	add	%o0, 4, %o0		! advance SRC by 4
1898 	add	%o0, 8, %o0		! update SRC
1912 	add	%o0, 2, %o0		! advance SRC by 2
1982 	add	%o0, 4, %o0		! advance SRC by 4
2000 	add	%o0, 32, %o0		! advance SRC by 32
2017 	add	%o0, 8, %o0		! advance SRC by 8
2055 	add	%o0, 16, %o0		! advance SRC by 16
2072 	add	%o0, 4, %o0		! advance SRC by 4
2108 	add	%o0, 8, %o0		! advance SRC by 8
2200 	! Using SRC as a tmp here
2206 	ldub	[REALSRC], SRC		! move 4 bytes per loop iteration
2207 	stba	SRC, [DST]%asi
2209 	ldub	[REALSRC + 1], SRC
2211 	stba	SRC, [DST + 1]%asi
2212 	ldub	[REALSRC - 2], SRC
2214 	stba	SRC, [DST - 2]%asi
2215 	ldub	[REALSRC - 1], SRC
2217 	  stba	SRC, [DST - 1]%asi
2222 1:	ldub	[REALSRC], SRC
2227 	  stba	SRC, [DST - 1]%asi
2231 	andn	REALSRC, 0x7, SRC
2233 	! SRC - 8-byte aligned
2235 	ldd	[SRC], %f16
2236 	prefetch [SRC + (1 * VIS_BLOCKSIZE)], #n_reads
2238 	ldd	[SRC + 0x08], %f18
2239 	prefetch [SRC + (2 * VIS_BLOCKSIZE)], #n_reads
2241 	ldd	[SRC + 0x10], %f20
2242 	prefetch [SRC + (3 * VIS_BLOCKSIZE)], #n_reads
2244 	ldd	[SRC + 0x18], %f22
2245 	prefetch [SRC + (4 * VIS_BLOCKSIZE)], #one_read
2247 	ldd	[SRC + 0x20], %f24
2248 	prefetch [SRC + (8 * VIS_BLOCKSIZE)], #one_read
2250 	ldd	[SRC + 0x28], %f26
2251 	prefetch [SRC + (12 * VIS_BLOCKSIZE)], #one_read
2253 	ldd	[SRC + 0x30], %f28
2254 	prefetch [SRC + (16 * VIS_BLOCKSIZE)], #one_read
2256 	ldd	[SRC + 0x38], %f30
2257 	ldd	[SRC + VIS_BLOCKSIZE], %f16
2259 	add	SRC, VIS_BLOCKSIZE, SRC
2260 	prefetch [SRC + (19 * VIS_BLOCKSIZE)], #one_read
2263 	prefetch [SRC + (23 * VIS_BLOCKSIZE)], #one_read
2266 	ldd	[SRC + 0x08], %f18
2268 	ldd	[SRC + 0x10], %f20
2271 	ldd	[SRC + 0x18], %f22
2273 	ldd	[SRC + 0x20], %f24
2275 	ldd	[SRC + 0x28], %f26
2277 	ldd	[SRC + 0x30], %f28
2280 	ldd	[SRC + 0x38], %f30
2283 	ldd	[SRC + VIS_BLOCKSIZE], %f16
2286 	prefetch [SRC + (3 * VIS_BLOCKSIZE)], #n_reads
2287 	add	SRC, VIS_BLOCKSIZE, SRC
2288 	prefetch [SRC + ((OLYMPUS_C_PREFETCH) * VIS_BLOCKSIZE)], #one_read
2291 	  prefetch [SRC + ((OLYMPUS_C_2ND_PREFETCH) * VIS_BLOCKSIZE)], #one_read
2307 	ldd	[SRC + 0x08], %f18
2309 	ldd	[SRC + 0x10], %f20
2312 	ldd	[SRC + 0x18], %f22
2314 	ldd	[SRC + 0x20], %f24
2316 	ldd	[SRC + 0x28], %f26
2318 	ldd	[SRC + 0x30], %f28
2320 	ldd	[SRC + 0x38], %f30
2324 	add	SRC, VIS_BLOCKSIZE, SRC
2645 	add	%o0, 1, %o0		! advance SRC by 1
2647 	add	%o0, 1, %o0		! advance SRC by 1
2651 	add	%o0, 1, %o0		! advance SRC by 1
2654 	add	%o0, 1, %o0		! advance SRC by 1
2684 	add	%o0, 4, %o0		! update SRC
2687 	add	%o0, 4, %o0		! update SRC
2698 	add	%o0, 2, %o0		! advance SRC by 2
2768 	add	%o0, 4, %o0		! advance SRC by 4
2781 	add	%o0, 8, %o0		! advance SRC by 8
2783 	add	%o0, 8, %o0		! advance SRC by 8
2787 	add	%o0, 8, %o0		! advance SRC by 8
2790 	add	%o0, 8, %o0		! advance SRC by 8
2800 	add	%o0, 8, %o0		! advance SRC by 8
2836 	add	%o0, 4, %o0		! advance SRC by 4
2838 	add	%o0, 4, %o0		! advance SRC by 4
2842 	add	%o0, 4, %o0		! advance SRC by 4
2845 	add	%o0, 4, %o0		! advance SRC by 4
2855 	add	%o0, 4, %o0		! advance SRC by 4
2888 	add	%o0, 2, %o0		! advance SRC by 2
2890 	add	%o0, 2, %o0		! advance SRC by 2
2894 	add	%o0, 2, %o0		! advance SRC by 2
2897 	add	%o0, 2, %o0		! advance SRC by 2
2979 	! Using SRC as a tmp here
2985 	lduba	[REALSRC]%asi, SRC	! move 4 bytes per loop iteration
2986 	stb	SRC, [DST]
2988 	lduba	[REALSRC + 1]%asi, SRC
2990 	stb	SRC, [DST + 1]
2991 	lduba	[REALSRC - 2]%asi, SRC
2993 	stb	SRC, [DST - 2]
2994 	lduba	[REALSRC - 1]%asi, SRC
2996 	  stb	SRC, [DST - 1]
3001 1:	lduba	[REALSRC]%asi, SRC
3006 	  stb	SRC, [DST - 1]
3010 	andn	REALSRC, 0x7, SRC
3012 	! SRC - 8-byte aligned
3014 	ldda	[SRC]%asi, %f16
3015 	prefetcha [SRC + (1 * VIS_BLOCKSIZE)]%asi, #n_reads
3017 	ldda	[SRC + 0x08]%asi, %f18
3018 	prefetcha [SRC + (2 * VIS_BLOCKSIZE)]%asi, #n_reads
3020 	ldda	[SRC + 0x10]%asi, %f20
3021 	prefetcha [SRC + (3 * VIS_BLOCKSIZE)]%asi, #n_reads
3023 	ldda	[SRC + 0x18]%asi, %f22
3024 	prefetcha [SRC + (4 * VIS_BLOCKSIZE)]%asi, #one_read
3026 	ldda	[SRC + 0x20]%asi, %f24
3027 	prefetcha [SRC + (8 * VIS_BLOCKSIZE)]%asi, #one_read
3029 	ldda	[SRC + 0x28]%asi, %f26
3030 	prefetcha [SRC + (12 * VIS_BLOCKSIZE)]%asi, #one_read
3032 	ldda	[SRC + 0x30]%asi, %f28
3033 	prefetcha [SRC + (16 * VIS_BLOCKSIZE)]%asi, #one_read
3035 	ldda	[SRC + 0x38]%asi, %f30
3036 	ldda	[SRC + VIS_BLOCKSIZE]%asi, %f16
3038 	add	SRC, VIS_BLOCKSIZE, SRC
3039 	prefetcha [SRC + (19 * VIS_BLOCKSIZE)]%asi, #one_read
3042 	prefetcha [SRC + (23 * VIS_BLOCKSIZE)]%asi, #one_read
3045 	ldda	[SRC + 0x08]%asi, %f18
3047 	ldda	[SRC + 0x10]%asi, %f20
3050 	ldda	[SRC + 0x18]%asi, %f22
3052 	ldda	[SRC + 0x20]%asi, %f24
3054 	ldda	[SRC + 0x28]%asi, %f26
3056 	ldda	[SRC + 0x30]%asi, %f28
3059 	ldda	[SRC + 0x38]%asi, %f30
3062 	ldda	[SRC + VIS_BLOCKSIZE]%asi, %f16
3065 	prefetcha [SRC + (3 * VIS_BLOCKSIZE)]%asi, #n_reads
3066 	add	SRC, VIS_BLOCKSIZE, SRC
3067 	prefetcha [SRC + ((OLYMPUS_C_PREFETCH) * VIS_BLOCKSIZE)]%asi, #one_read
3070 	  prefetcha [SRC + ((OLYMPUS_C_2ND_PREFETCH) * VIS_BLOCKSIZE)]%asi, #one_read
3086 	ldda	[SRC + 0x08]%asi, %f18
3088 	ldda	[SRC + 0x10]%asi, %f20
3091 	ldda	[SRC + 0x18]%asi, %f22
3093 	ldda	[SRC + 0x20]%asi, %f24
3095 	ldda	[SRC + 0x28]%asi, %f26
3097 	ldda	[SRC + 0x30]%asi, %f28
3099 	ldda	[SRC + 0x38]%asi, %f30
3103 	add	SRC, VIS_BLOCKSIZE, SRC

Indexes created Tue Jul 24 14:28:13 CEST 2018