+
+GLOBAL_ENTRY(csum_ipv6_magic)
+ ld4 r20=[in0],4
+ ld4 r21=[in1],4
+ dep r15=in3,in2,32,16
+ ;;
+ ld4 r22=[in0],4
+ ld4 r23=[in1],4
+ mux1 r15=r15,@rev
+ ;;
+ ld4 r24=[in0],4
+ ld4 r25=[in1],4
+ shr.u r15=r15,16
+ add r16=r20,r21
+ add r17=r22,r23
+ ;;
+ ld4 r26=[in0],4
+ ld4 r27=[in1],4
+ add r18=r24,r25
+ add r8=r16,r17
+ ;;
+ add r19=r26,r27
+ add r8=r8,r18
+ ;;
+ add r8=r8,r19
+ add r15=r15,in4
+ ;;
+ add r8=r8,r15
+ ;;
+ shr.u r10=r8,32 // now fold sum into short
+ zxt4 r11=r8
+ ;;
+ add r8=r10,r11
+ ;;
+ shr.u r10=r8,16 // yeah, keep it rolling
+ zxt2 r11=r8
+ ;;
+ add r8=r10,r11
+ ;;
+ shr.u r10=r8,16 // three times lucky
+ zxt2 r11=r8
+ ;;
+ add r8=r10,r11
+ mov r9=0xffff
+ ;;
+ andcm r8=r9,r8
+ br.ret.sptk.many b0
+END(csum_ipv6_magic)