.text .allow_optimizations .file "3" .section .text.__runCodelet_Pack0,"ax",@progbits .globl __runCodelet_Pack0 # -- Begin function __runCodelet_Pack0 .p2align 2 .type __runCodelet_Pack0,@function __runCodelet_Pack0: # @__runCodelet_Pack0 .worker .Lpack0_func_begin0: # %bb.0: # %entry setzi $m6, 64 cmpult $m6, $m6, __worker_stack_max_growth_plus_one brz $m6, _stackoverflow add $m11, $m12, -64 get $m0, 1 ld32 $m1, $m13, $m15, 7 brz $m1, .Lpack0_BB0_11 # %bb.1: # %for.body.lr.ph.i mov $m6, $m15 and $m2, $m0, 7 ld32 $m7, $m13, $m15, 5 ld32 $m9, $m13, $m15, 2 ld32 $m3, $m13, $m15, 0 mul $m0, $m7, $m2 st32 $m3, $m11, $m15, 1 # 4-byte Folded Spill add $m3, $m3, $m0 ld32 $m0, $m13, $m15, 3 st32 $m0, $m11, $m15, 10 # 4-byte Folded Spill ld32 $m0, $m13, $m15, 6 st32 $m0, $m11, $m15, 15 # 4-byte Folded Spill mul $m4, $m7, $m9 ld32 $m0, $m13, $m15, 1 st32 $m0, $m11, $m15, 14 # 4-byte Folded Spill mul $m0, $m7, 6 st32 $m0, $m11, $m15, 5 # 4-byte Folded Spill add $m0, $m7, -1 st32 $m0, $m11, $m15, 6 # 4-byte Folded Spill st32 $m2, $m11, $m15, 2 # 4-byte Folded Spill st32 $m7, $m11, $m15, 8 # 4-byte Folded Spill st32 $m9, $m11, $m15, 7 # 4-byte Folded Spill st32 $m4, $m11, $m15, 0 # 4-byte Folded Spill bri .Lpack0_BB0_2 .Lpack0_BB0_9: # %for.cond.cleanup6.loopexit.i # in Loop: Header=BB0_2 Depth=1 ld32 $m1, $m13, $m15, 7 ld32 $m2, $m11, $m15, 2 # 4-byte Folded Reload ld32 $m3, $m11, $m15, 3 # 4-byte Folded Reload ld32 $m4, $m11, $m15, 0 # 4-byte Folded Reload .Lpack0_BB0_10: # %for.cond.cleanup6.i # in Loop: Header=BB0_2 Depth=1 add $m6, $m6, 1 cmpult $m0, $m6, $m1 add $m3, $m3, $m4 brz $m0, .Lpack0_BB0_11 .Lpack0_BB0_2: # %for.body.i # =>This Loop Header: Depth=1 # Child Loop BB0_4 Depth 2 # Child Loop BB0_6 Depth 3 ld32 $m0, $m11, $m15, 10 # 4-byte Folded Reload cmpult $m0, $m2, $m0 brz $m0, .Lpack0_BB0_10 # %bb.3: # in Loop: Header=BB0_2 Depth=1 mul $m1, $m4, $m6 ld32 $m0, $m11, $m15, 1 # 4-byte Folded Reload st32 $m1, $m11, $m15, 4 # 4-byte Folded Spill add $m0, $m0, $m1 st32 $m0, $m11, $m15, 9 # 4-byte Folded Spill st32 $m3, $m11, $m15, 3 # 4-byte Folded Spill st32 $m3, $m11, $m15, 12 # 4-byte Folded Spill mov $m1, $m2 ld32 $m2, $m11, $m15, 10 # 4-byte Folded Reload bri .Lpack0_BB0_4 .Lpack0_BB0_18: # %for.cond.cleanup10.i # in Loop: Header=BB0_4 Depth=2 add $m1, $m1, 6 cmpult $m0, $m1, $m2 ld32 $m3, $m11, $m15, 5 # 4-byte Folded Reload ld32 $m4, $m11, $m15, 12 # 4-byte Folded Reload add $m4, $m4, $m3 st32 $m4, $m11, $m15, 12 # 4-byte Folded Spill brz $m0, .Lpack0_BB0_9 .Lpack0_BB0_4: # %for.cond8.preheader.i # Parent Loop BB0_2 Depth=1 # => This Loop Header: Depth=2 # Child Loop BB0_6 Depth 3 ld32 $m0, $m11, $m15, 15 # 4-byte Folded Reload brz $m0, .Lpack0_BB0_18 # %bb.5: # %for.body11.lr.ph.i # in Loop: Header=BB0_4 Depth=2 mov $m8, $m15 mul $m3, $m1, $m7 ld32 $m0, $m11, $m15, 4 # 4-byte Folded Reload st32 $m3, $m11, $m15, 11 # 4-byte Folded Spill add $m0, $m3, $m0 and $m0, $m0, 3 st32 $m0, $m11, $m15, 13 # 4-byte Folded Spill bri .Lpack0_BB0_6 .Lpack0_BB0_8: # %for.body11._ZZN5Pack07computeEjENKUljjE_clEjj.exit_crit_edge.i # in Loop: Header=BB0_6 Depth=3 mov $m4, $m15 add $m5, $m8, 4 .Lpack0_BB0_17: # %_ZZN5Pack07computeEjENKUljjE_clEjj.exit.i # in Loop: Header=BB0_6 Depth=3 shr $m0, $m8, 5 mul $m0, $m10, $m0 add $m0, $m0, $m6 mul $m0, $m0, $m2 add $m0, $m0, $m1 shl $m0, $m0, 5 and $m3, $m8, 28 or $m0, $m0, $m3 ld32 $m3, $m11, $m15, 15 # 4-byte Folded Reload cmpult $m3, $m5, $m3 ld32 $m8, $m11, $m15, 14 # 4-byte Folded Reload st32 $m4, $m8, $m0, 0 mov $m8, $m5 brz $m3, .Lpack0_BB0_18 .Lpack0_BB0_6: # %for.body11.i # Parent Loop BB0_2 Depth=1 # Parent Loop BB0_4 Depth=2 # => This Inner Loop Header: Depth=3 cmpult $m0, $m1, $m9 ld32 $m10, $m13, $m15, 7 brz $m0, .Lpack0_BB0_8 # %bb.7: # %for.body11.i # in Loop: Header=BB0_6 Depth=3 cmpult $m0, $m8, $m7 brz $m0, .Lpack0_BB0_8 # %bb.12: # %if.end.i.i # in Loop: Header=BB0_6 Depth=3 add $m5, $m8, 4 ld32 $m0, $m11, $m15, 13 # 4-byte Folded Reload brnz $m0, .Lpack0_BB0_14 # %bb.13: # %if.end.i.i # in Loop: Header=BB0_6 Depth=3 cmpult $m0, $m7, $m5 brnz $m0, .Lpack0_BB0_14 # %bb.19: # %if.then9.i.i # in Loop: Header=BB0_6 Depth=3 ld32 $m0, $m11, $m15, 11 # 4-byte Folded Reload add $m0, $m8, $m0 ld32 $m3, $m11, $m15, 9 # 4-byte Folded Reload ld32 $m4, $m3, $m0, 0 bri .Lpack0_BB0_17 .Lpack0_BB0_14: # %for.body.i.i.preheader # in Loop: Header=BB0_6 Depth=3 mov $m2, $m6 mov $m3, $m15 mov $m0, $m15 mov $m4, $m15 ld32 $m6, $m11, $m15, 6 # 4-byte Folded Reload sub $m6, $m6, $m8 cmpult $m9, $m6, 3 setzi $m7, 3 movnz $m7, $m9, $m6 add $m9, $m7, 1 ld32 $m6, $m11, $m15, 12 # 4-byte Folded Reload add $m6, $m6, $m8 # %bb.15: # %for.body.i.i # in Loop: Header=BB0_6 Depth=3 { rpt $m9, 3 fnop } { ldz8step $m7, $m6, $m0+=, 1 fnop } { shl $m7, $m7, $m3 fnop } { or $m4, $m7, $m4 fnop } { add $m3, $m3, 8 fnop } # %bb.16: # in Loop: Header=BB0_6 Depth=3 mov $m6, $m2 ld32 $m7, $m11, $m15, 8 # 4-byte Folded Reload ld32 $m9, $m11, $m15, 7 # 4-byte Folded Reload ld32 $m2, $m11, $m15, 10 # 4-byte Folded Reload bri .Lpack0_BB0_17 .Lpack0_BB0_11: # %_ZN5Pack07computeEj.exit exitz $m15 .Lpack0_func_end0: .size __runCodelet_Pack0, .Lpack0_func_end0-__runCodelet_Pack0 .section .stack_sizes,"o",@progbits,.text.__runCodelet_Pack0 .long .Lpack0_func_begin0 .byte 64 .section .text.__runCodelet_Pack0,"ax",@progbits # -- End function .ident "clang version 16.0.0 (git@github.com:Software-GCAI/llvm-project.git 6343a843cd5af31429c62a83b6ba249a74d36969)" .section ".note.GNU-stack","",@progbits .addrsig