| /* |
| * Copyright (C) 2007-2008 ARM Limited |
| * |
| * 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. |
| * |
| */ |
| /* |
| * |
| */ |
| |
| .eabi_attribute 24, 1 |
| .eabi_attribute 25, 1 |
| |
| .arm |
| .fpu neon |
| .text |
| |
| .global armVCM4P10_InvTransformDequantLumaDC4x4 |
| armVCM4P10_InvTransformDequantLumaDC4x4: |
| PUSH {r4-r6,lr} |
| VPUSH {d8-d13} |
| VLD4.16 {d0,d1,d2,d3},[r0] |
| LDR r2, .LarmVCM4P10_QPDivTable |
| P0: ADD r2, pc |
| LDR r3, .LarmVCM4P10_VMatrixQPModTable |
| P1: ADD r3, pc |
| VADD.I16 d4,d0,d1 |
| VADD.I16 d5,d2,d3 |
| VSUB.I16 d6,d0,d1 |
| LDRSB r4,[r2,r1] |
| VSUB.I16 d7,d2,d3 |
| LDRSB r5,[r3,r1] |
| VADD.I16 d0,d4,d5 |
| VSUB.I16 d1,d4,d5 |
| VSUB.I16 d2,d6,d7 |
| LSL r5,r5,r4 |
| VADD.I16 d3,d6,d7 |
| VTRN.16 d0,d1 |
| VTRN.16 d2,d3 |
| VTRN.32 q0,q1 |
| VADD.I16 d4,d0,d1 |
| VADD.I16 d5,d2,d3 |
| VSUB.I16 d6,d0,d1 |
| VSUB.I16 d7,d2,d3 |
| VADD.I16 d0,d4,d5 |
| VSUB.I16 d1,d4,d5 |
| VSUB.I16 d2,d6,d7 |
| VADD.I16 d3,d6,d7 |
| VDUP.16 d5,r5 |
| VMOV.I32 q3,#0x2 |
| VMOV.I32 q4,#0x2 |
| VMOV.I32 q5,#0x2 |
| VMOV.I32 q6,#0x2 |
| VMLAL.S16 q3,d0,d5 |
| VMLAL.S16 q4,d1,d5 |
| VMLAL.S16 q5,d2,d5 |
| VMLAL.S16 q6,d3,d5 |
| VSHRN.I32 d0,q3,#2 |
| VSHRN.I32 d1,q4,#2 |
| VSHRN.I32 d2,q5,#2 |
| VSHRN.I32 d3,q6,#2 |
| VST1.16 {d0,d1,d2,d3},[r0] |
| VPOP {d8-d13} |
| POP {r4-r6,pc} |
| |
| .LarmVCM4P10_QPDivTable: |
| .word armVCM4P10_QPDivTable-(P0+8) |
| .LarmVCM4P10_VMatrixQPModTable: |
| .word armVCM4P10_VMatrixQPModTable-(P1+8) |
| |
| .global omxVCM4P10_TransformDequantLumaDCFromPair |
| omxVCM4P10_TransformDequantLumaDCFromPair: |
| PUSH {r4-r6,lr} |
| MOV r4,r1 |
| MOV r5,r2 |
| BL armVCM4P10_UnpackBlock4x4 |
| MOV r0,r4 |
| MOV r1,r5 |
| BL armVCM4P10_InvTransformDequantLumaDC4x4 |
| MOV r0,#0 |
| POP {r4-r6,pc} |
| |
| .end |
| |
