Merge http://git.xiph.org/?p=opus.git;a=commitdiff;h=e70faf98b0465e4f278c72ce2d7b4ad10221a2f2

celt/arm/celt_pitch_xcorr_arm.s

 ; Copyright (c) 2007-2008 CSIRO
 ; Copyright (c) 2007-2009 Xiph.Org Foundation
 ; Copyright (c) 2013      Parrot
 ; Written by Aurélien Zanelli
 ;
 ; Redistribution and use in source and binary forms, with or without
 ; modification, are permitted provided that the following conditions
 ; are met:
 ;
 ; - Redistributions of source code must retain the above copyright
@@ skipping 291 matching lines @@
   SMLATT       r8, r14, r10, r8   ; sum[2] = MAC16_16(sum[2],x_3,y_5)
   SMLATB       r9, r14, r11, r9   ; sum[3] = MAC16_16(sum[3],x_3,y_6)
   BGT xcorr_kernel_edsp_process4
 xcorr_kernel_edsp_process4_done
   ADDS         r2, r2, #4
   BLE xcorr_kernel_edsp_done
   LDRH         r12, [r4], #2      ; r12 = *x++
   SUBS         r2, r2, #1         ; j--
   ; Stall
   SMLABB       r6, r12, r10, r6   ; sum[0] = MAC16_16(sum[0],x,y_0)
-  LDRGTH       r14, [r4], #2      ; r14 = *x++
+  LDRHGT       r14, [r4], #2      ; r14 = *x++
   SMLABT       r7, r12, r10, r7   ; sum[1] = MAC16_16(sum[1],x,y_1)
   SMLABB       r8, r12, r11, r8   ; sum[2] = MAC16_16(sum[2],x,y_2)
   SMLABT       r9, r12, r11, r9   ; sum[3] = MAC16_16(sum[3],x,y_3)
   BLE xcorr_kernel_edsp_done
   SMLABT       r6, r14, r10, r6   ; sum[0] = MAC16_16(sum[0],x,y_1)
   SUBS         r2, r2, #1         ; j--
   SMLABB       r7, r14, r11, r7   ; sum[1] = MAC16_16(sum[1],x,y_2)
   LDRH         r10, [r5], #2      ; r10 = y_4 = *y++
   SMLABT       r8, r14, r11, r8   ; sum[2] = MAC16_16(sum[2],x,y_3)
-  LDRGTH       r12, [r4], #2      ; r12 = *x++
+  LDRHGT       r12, [r4], #2      ; r12 = *x++
   SMLABB       r9, r14, r10, r9   ; sum[3] = MAC16_16(sum[3],x,y_4)
   BLE xcorr_kernel_edsp_done
   SMLABB       r6, r12, r11, r6   ; sum[0] = MAC16_16(sum[0],tmp,y_2)
   CMP          r2, #1             ; j--
   SMLABT       r7, r12, r11, r7   ; sum[1] = MAC16_16(sum[1],tmp,y_3)
   LDRH         r2, [r5], #2       ; r2 = y_5 = *y++
   SMLABB       r8, r12, r10, r8   ; sum[2] = MAC16_16(sum[2],tmp,y_4)
-  LDRGTH       r14, [r4]          ; r14 = *x
+  LDRHGT       r14, [r4]          ; r14 = *x
   SMLABB       r9, r12, r2, r9    ; sum[3] = MAC16_16(sum[3],tmp,y_5)
   BLE xcorr_kernel_edsp_done
   SMLABT       r6, r14, r11, r6   ; sum[0] = MAC16_16(sum[0],tmp,y_3)
   LDRH         r11, [r5]          ; r11 = y_6 = *y
   SMLABB       r7, r14, r10, r7   ; sum[1] = MAC16_16(sum[1],tmp,y_4)
   SMLABB       r8, r14, r2, r8    ; sum[2] = MAC16_16(sum[2],tmp,y_5)
   SMLABB       r9, r14, r11, r9   ; sum[3] = MAC16_16(sum[3],tmp,y_6)
 xcorr_kernel_edsp_done
   LDMFD        sp!, {r2,r4,r5,pc}
   ENDP
@@ skipping 39 matching lines @@
   LDR          r8, [r5], #4
   SMLABT       r14, r7, r9, r14     ; sum = MAC16_16(sum, x_2, y_2)
   SUBS         r12, r12, #4         ; j-=4
   SMLATB       r14, r7, r8, r14     ; sum = MAC16_16(sum, x_3, y_3)
   LDRGT        r6, [r4], #4
   BGT celt_pitch_xcorr_edsp_process1u_loop4
   MOV          r8, r8, LSR #16
 celt_pitch_xcorr_edsp_process1u_loop4_done
   ADDS         r12, r12, #4
 celt_pitch_xcorr_edsp_process1u_loop1
-  LDRGEH       r6, [r4], #2
+  LDRHGE       r6, [r4], #2
   ; Stall
   SMLABBGE     r14, r6, r8, r14    ; sum = MAC16_16(sum, *x, *y)
-  SUBGES       r12, r12, #1
-  LDRGTH       r8, [r5], #2
+  SUBSGE       r12, r12, #1
+  LDRHGT       r8, [r5], #2
   BGT celt_pitch_xcorr_edsp_process1u_loop1
   ; Restore _x
   SUB          r4, r4, r3, LSL #1
   ; Restore and advance _y
   SUB          r5, r5, r3, LSL #1
   ; maxcorr = max(maxcorr, sum)
   CMP          r0, r14
   ADD          r5, r5, #2
   MOVLT        r0, r14
   SUBS         r1, r1, #1
@@ skipping 62 matching lines @@
   SMLABT       r11, r6, r8, r11     ; sum1 = MAC16_16(sum1, x_0, y_1)
   SUB          r12, r12, #2
   SMLATT       r10, r6, r8, r10     ; sum0 = MAC16_16(sum0, x_1, y_1)
   MOV          r8, r9
   SMLATB       r11, r6, r9, r11     ; sum1 = MAC16_16(sum1, x_1, y_2)
 celt_pitch_xcorr_edsp_process2_1
   LDRH         r6, [r4], #2
   ADDS         r12, r12, #1
   ; Stall
   SMLABB       r10, r6, r8, r10     ; sum0 = MAC16_16(sum0, x_0, y_0)
-  LDRGTH       r7, [r4], #2
+  LDRHGT       r7, [r4], #2
   SMLABT       r11, r6, r8, r11     ; sum1 = MAC16_16(sum1, x_0, y_1)
   BLE celt_pitch_xcorr_edsp_process2_done
   LDRH         r9, [r5], #2
   SMLABT       r10, r7, r8, r10     ; sum0 = MAC16_16(sum0, x_0, y_1)
   SMLABB       r11, r7, r9, r11     ; sum1 = MAC16_16(sum1, x_0, y_2)
 celt_pitch_xcorr_edsp_process2_done
   ; Restore _x
   SUB          r4, r4, r3, LSL #1
   ; Restore and advance _y
   SUB          r5, r5, r3, LSL #1
@@ skipping 32 matching lines @@
   BGE celt_pitch_xcorr_edsp_process1a_loop4
 celt_pitch_xcorr_edsp_process1a_loop_done
   ADDS         r12, r12, #2
   LDRGE        r6, [r4], #4
   LDRGE        r8, [r5], #4
   ; Stall
   SMLABBGE     r14, r6, r8, r14     ; sum = MAC16_16(sum, x_0, y_0)
   SUBGE        r12, r12, #2
   SMLATTGE     r14, r6, r8, r14     ; sum = MAC16_16(sum, x_1, y_1)
   ADDS         r12, r12, #1
-  LDRGEH       r6, [r4], #2
-  LDRGEH       r8, [r5], #2
+  LDRHGE       r6, [r4], #2
+  LDRHGE       r8, [r5], #2
   ; Stall
   SMLABBGE     r14, r6, r8, r14     ; sum = MAC16_16(sum, *x, *y)
   ; maxcorr = max(maxcorr, sum)
   CMP          r0, r14
   ; xcorr[i] = sum
   STR          r14, [r2], #4
   MOVLT        r0, r14
 celt_pitch_xcorr_edsp_done
   LDMFD        sp!, {r4-r11, pc}
   ENDP
 
 ENDIF
 
 END