diff options
author | The Android Open Source Project <initial-contribution@android.com> | 2008-10-21 07:00:00 -0700 |
---|---|---|
committer | The Android Open Source Project <initial-contribution@android.com> | 2008-10-21 07:00:00 -0700 |
commit | 4f6e8d7a00cbeda1e70cc15be9c4af1018bdad53 (patch) | |
tree | 54fd1b2695a591d2306d41264df67c53077b752c /libpixelflinger/rotate90CW_4x4_16v6.S | |
download | system_core-4f6e8d7a00cbeda1e70cc15be9c4af1018bdad53.zip system_core-4f6e8d7a00cbeda1e70cc15be9c4af1018bdad53.tar.gz system_core-4f6e8d7a00cbeda1e70cc15be9c4af1018bdad53.tar.bz2 |
Initial Contribution
Diffstat (limited to 'libpixelflinger/rotate90CW_4x4_16v6.S')
-rw-r--r-- | libpixelflinger/rotate90CW_4x4_16v6.S | 62 |
1 files changed, 62 insertions, 0 deletions
diff --git a/libpixelflinger/rotate90CW_4x4_16v6.S b/libpixelflinger/rotate90CW_4x4_16v6.S new file mode 100644 index 0000000..8e3e142 --- /dev/null +++ b/libpixelflinger/rotate90CW_4x4_16v6.S @@ -0,0 +1,62 @@ +/* +** +** Copyright 2006, The Android Open Source Project +** +** Licensed under the Apache License, Version 2.0 (the "License"); +** you may not use this file except in compliance with the License. +** You may obtain a copy of the License at +** +** http://www.apache.org/licenses/LICENSE-2.0 +** +** Unless required by applicable law or agreed to in writing, software +** distributed under the License is distributed on an "AS IS" BASIS, +** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +** See the License for the specific language governing permissions and +** limitations under the License. +*/ + + + .text + .align + + .global rotate90CW_4x4_16v6 + +// Rotates 90deg CW a 4x4 block of 16bpp pixels using ARMv6 +// src and dst must be 4 pixels-aligned (2-pixels aligned might +// actually work) +// +// The code below is complicated by ARM's little endianness. + +rotate90CW_4x4_16v6: + // r0 = dst + // r1 = src + // r2 = dst stride in pixels + // r3 = src stride in pixels + + stmfd sp!, {r4,r5, r6,r7, r8,r9, r10,r11, lr} + add r14, r3, r3 + add r12, r2, r2 + + ldrd r2, r3, [r1], r14 + ldrd r4, r5, [r1], r14 + ldrd r6, r7, [r1], r14 + ldrd r8, r9, [r1] + + pkhbt r10, r8, r6, lsl #16 + pkhbt r11, r4, r2, lsl #16 + strd r10, r11, [r0], r12 + + pkhtb r10, r6, r8, asr #16 + pkhtb r11, r2, r4, asr #16 + + strd r10, r11, [r0], r12 + pkhbt r10, r9, r7, lsl #16 + pkhbt r11, r5, r3, lsl #16 + + strd r10, r11, [r0], r12 + + pkhtb r10, r7, r9, asr #16 + pkhtb r11, r3, r5, asr #16 + strd r10, r11, [r0] + + ldmfd sp!, {r4,r5, r6,r7, r8,r9, r10,r11, pc} |