112     PUSH    {r4-r9}  in dct_IV_func1()
121     SMULWT  r9, r5, r8      // accuX = accu2*val_tw.l  in dct_IV_func1()
123     RSB     r9, r9, #0      // accuX =-accu2*val_tw.l  in dct_IV_func1()
125     SMLAWB  r4, r4, r8, r9  // accu1 = accu1*val_tw.h - accu2*val_tw.l  in dct_IV_func1()
131     SMULWB  r9, r7, r8      // accuX = accu4*val_tw.h  in dct_IV_func1()
133     RSB     r9, r9, #0      // accuX =-accu4*val_tw.h  in dct_IV_func1()
135     SMLAWT  r6, r6, r8, r9  // accu3 = accu3*val_tw.l-accu4*val_tw.h  in dct_IV_func1()
147     SMULWT  r9, r5, r8      // accuX = accu2*val_tw.l  in dct_IV_func1()
149     RSB     r9, r9, #0      // accuX =-accu2*val_tw.l  in dct_IV_func1()
151     SMLAWB  r4, r4, r8, r9  // accu1 = accu1*val_tw.h - accu2*val_tw.l  in dct_IV_func1()
157     SMULWB  r9, r7, r8      // accuX = accu4*val_tw.h  in dct_IV_func1()
159     RSB     r9, r9, #0      // accuX =-accu4*val_tw.h  in dct_IV_func1()
161     SMLAWT  r6, r6, r8, r9  // accu3 = accu3*val_tw.l-accu4*val_tw.h  in dct_IV_func1()
171     POP     {r4-r9}  in dct_IV_func1()
291     PUSH    {r4-r9}  in dst_IV_func1()
298     SMULWT  r9, r5, r8                 // accuX = (-accu2)*val_tw.l  in dst_IV_func1()
300     RSB     r9, r9, #0                 // accuX = -(-accu2)*val_tw.l  in dst_IV_func1()
301     SMLAWB  r9, r4, r8, r9             // accuX = accu1*val_tw.h-(-accu2)*val_tw.l  in dst_IV_func1()
307     STR     r9, [r2], #4               // *pDat_0++ = accu1 (accuX)  in dst_IV_func1()
321     SMULWT  r9, r5, r8                 // accuX = (-accu2)*val_tw.l  in dst_IV_func1()
323     RSB     r9, r9, #0                 // accuX = -(-accu2)*val_tw.l  in dst_IV_func1()
324     SMLAWB  r9, r4, r8, r9             // accuX = accu1*val_tw.h-(-accu2)*val_tw.l  in dst_IV_func1()
330     STR     r9, [r2], #4               // *pDat_0++ = accu1 (accuX)  in dst_IV_func1()
343     POP     {r4-r9}  in dst_IV_func1()