.text .allow_optimizations .file "3" .section .text.__runCodelet_Vertex_pack2_15,"ax",@progbits .globl __runCodelet_Vertex_pack2_15 # -- Begin function __runCodelet_Vertex_pack2_15 .p2align 2 .type __runCodelet_Vertex_pack2_15,@function __runCodelet_Vertex_pack2_15: # @__runCodelet_Vertex_pack2_15 .worker .Lpack2_15_func_begin0: # %bb.0: # %entry setzi $m6, 128 cmpult $m6, $m6, __worker_stack_max_growth_plus_one brz $m6, _stackoverflow add $m11, $m12, -128 get $m0, 1 ld32 $m1, $m13, $m15, 7 brz $m1, .Lpack2_15_BB0_8 # %bb.1: # %for.body.lr.ph.i mov $m1, $m13 mov $m5, $m15 ld32step $m2, $m15, $m1+=, 7 st32 $m1, $m11, $m15, 3 # 4-byte Folded Spill shl $m1, $m0, 2 and $m4, $m1, 28 and $m0, $m0, 7 mul $m0, $m0, 216 st32 $m2, $m11, $m15, 2 # 4-byte Folded Spill add $m6, $m2, $m0 max $m0, $m4, 8 sub $m1, $m0, $m4 cmpeq $m2, $m1, 0 setzi $m3, 1 movnz $m3, $m2, $m1 sub $m0, $m0, $m3 st32 $m4, $m11, $m15, 1 # 4-byte Folded Spill sub $m0, $m0, $m4 setzi $m1, 43691 sort4x16lo $m2, $m0, $m15 shr $m0, $m0, 16 mul $m4, $m2, $m1 mul $m1, $m0, $m1 shr $m4, $m4, 16 add $m1, $m1, $m4 setzi $m4, 43690 mul $m2, $m2, $m4 mul $m0, $m0, $m4 sort4x16lo $m4, $m1, $m15 shr $m1, $m1, 16 add $m2, $m2, $m4 add $m0, $m0, $m1 shr $m1, $m2, 16 add $m0, $m0, $m1 shr $m0, $m0, 4 setzi $m1, 983040 add $m0, $m3, $m0 or $m2, $m15, 4278190080 st32 $m2, $m11, $m15, 13 # 4-byte Folded Spill or $m1, $m1, 15728640 st32 $m1, $m11, $m15, 12 # 4-byte Folded Spill setzi $m1, 65280 st32 $m1, $m11, $m15, 11 # 4-byte Folded Spill ld32 $m1, $m13, $m15, 1 st32 $m1, $m11, $m15, 10 # 4-byte Folded Spill add $m0, $m0, 1 st32 $m0, $m11, $m15, 0 # 4-byte Folded Spill add $m2, $m6, 54 add $m3, $m6, 108 add $m4, $m6, 162 .Lpack2_15_BB0_2: # %for.body.i # =>This Loop Header: Depth=1 # Child Loop BB0_3 Depth 2 # Child Loop BB0_4 Depth 3 # Child Loop BB0_11 Depth 4 # Child Loop BB0_16 Depth 4 st32 $m4, $m11, $m15, 14 # 4-byte Folded Spill st32 $m3, $m11, $m15, 15 # 4-byte Folded Spill st32 $m2, $m11, $m15, 16 # 4-byte Folded Spill ld32 $m7, $m11, $m15, 0 # 4-byte Folded Reload mul $m0, $m5, 1728 ld32 $m1, $m11, $m15, 2 # 4-byte Folded Reload add $m0, $m1, $m0 st32 $m0, $m11, $m15, 8 # 4-byte Folded Spill st32 $m5, $m11, $m15, 5 # 4-byte Folded Spill shl $m0, $m5, 11 st32 $m0, $m11, $m15, 6 # 4-byte Folded Spill mov $m5, $m4 mov $m8, $m3 mov $m9, $m2 st32 $m6, $m11, $m15, 4 # 4-byte Folded Spill ld32 $m10, $m11, $m15, 1 # 4-byte Folded Reload st32 $m7, $m11, $m15, 7 # 4-byte Folded Spill .Lpack2_15_BB0_3: # %for.cond9.preheader.i # Parent Loop BB0_2 Depth=1 # => This Loop Header: Depth=2 # Child Loop BB0_4 Depth 3 # Child Loop BB0_11 Depth 4 # Child Loop BB0_16 Depth 4 st32 $m10, $m11, $m15, 18 # 4-byte Folded Spill st32 $m6, $m11, $m15, 19 # 4-byte Folded Spill st32 $m9, $m11, $m15, 20 # 4-byte Folded Spill st32 $m8, $m11, $m15, 21 # 4-byte Folded Spill st32 $m5, $m11, $m15, 22 # 4-byte Folded Spill st32 $m15, $m11, $m15, 27 # 4-byte Folded Spill mov $m7, $m15 setzi $m2, 16 and $m0, $m10, 28 ld32 $m1, $m11, $m15, 6 # 4-byte Folded Reload or $m0, $m0, $m1 st32 $m0, $m11, $m15, 17 # 4-byte Folded Spill mul $m0, $m10, 54 st32 $m0, $m11, $m15, 9 # 4-byte Folded Spill st32 $m5, $m11, $m15, 26 # 4-byte Folded Spill st32 $m8, $m11, $m15, 29 # 4-byte Folded Spill st32 $m9, $m11, $m15, 30 # 4-byte Folded Spill st32 $m6, $m11, $m15, 28 # 4-byte Folded Spill st32 $m2, $m11, $m15, 31 # 4-byte Folded Spill .Lpack2_15_BB0_4: # %for.body12.i # Parent Loop BB0_2 Depth=1 # Parent Loop BB0_3 Depth=2 # => This Loop Header: Depth=3 # Child Loop BB0_11 Depth 4 # Child Loop BB0_16 Depth 4 setzi $m0, 53 cmpult $m0, $m0, $m7 mov $m9, $m7 brz $m0, .Lpack2_15_BB0_9 # %bb.5: # in Loop: Header=BB0_4 Depth=3 mov $m8, $m15 mov $m5, $m15 mov $m6, $m15 mov $m0, $m15 ld32 $m2, $m11, $m15, 27 # 4-byte Folded Reload ld32 $m1, $m11, $m15, 26 # 4-byte Folded Reload bri .Lpack2_15_BB0_19 .Lpack2_15_BB0_9: # %if.end.i.i # in Loop: Header=BB0_4 Depth=3 cmpult $m4, $m9, 51 ld32 $m0, $m11, $m15, 9 # 4-byte Folded Reload add $m1, $m9, $m0 st32 $m1, $m11, $m15, 25 # 4-byte Folded Spill brz $m4, .Lpack2_15_BB0_10 # %bb.20: # %if.then9.i.i # in Loop: Header=BB0_4 Depth=3 ld32 $m0, $m11, $m15, 8 # 4-byte Folded Reload ld32 $m5, $m0, $m1, 0 sub $m8, 53, $m9 ld32 $m2, $m11, $m15, 27 # 4-byte Folded Reload bri .Lpack2_15_BB0_12 .Lpack2_15_BB0_10: # %for.body.lr.ph.i.i # in Loop: Header=BB0_4 Depth=3 mov $m0, $m15 mov $m5, $m15 ld32 $m2, $m11, $m15, 27 # 4-byte Folded Reload shl $m3, $m2, 2 sub $m3, 54, $m3 add $m3, $m3, -1 sub $m8, 53, $m9 ld32 $m6, $m11, $m15, 28 # 4-byte Folded Reload .Lpack2_15_BB0_11: # %for.body.i.i # Parent Loop BB0_2 Depth=1 # Parent Loop BB0_3 Depth=2 # Parent Loop BB0_4 Depth=3 # => This Inner Loop Header: Depth=4 ldz8step $m7, $m15, $m6+=, 1 shl $m7, $m7, $m0 or $m5, $m7, $m5 add $m0, $m0, 8 brnzdec $m3, .Lpack2_15_BB0_11 .Lpack2_15_BB0_12: # %if.end.i92.i # in Loop: Header=BB0_4 Depth=3 mov $m0, $m15 mov $m6, $m15 cmpult $m3, $m8, 3 setzi $m7, 3 mov $m1, $m8 movnz $m7, $m3, $m8 add $m7, $m7, 1 mov $m3, $m7 ld32 $m10, $m11, $m15, 30 # 4-byte Folded Reload # %bb.13: # %for.body.i105.i # in Loop: Header=BB0_4 Depth=3 { rpt $m3, 3 fnop } { ldz8step $m8, $m15, $m10+=, 1 fnop } { shl $m8, $m8, $m0 fnop } { or $m6, $m8, $m6 fnop } { add $m0, $m0, 8 fnop } # %bb.14: # %if.end.i117.i # in Loop: Header=BB0_4 Depth=3 brz $m4, .Lpack2_15_BB0_15 # %bb.21: # %if.then9.i121.i # in Loop: Header=BB0_4 Depth=3 ld32 $m0, $m11, $m15, 25 # 4-byte Folded Reload add $m0, $m0, 108 ld32 $m1, $m11, $m15, 8 # 4-byte Folded Reload ld32 $m8, $m1, $m0, 0 ld32 $m1, $m11, $m15, 26 # 4-byte Folded Reload bri .Lpack2_15_BB0_17 .Lpack2_15_BB0_15: # %for.body.i132.i.preheader # in Loop: Header=BB0_4 Depth=3 mov $m0, $m15 mov $m8, $m15 add $m3, $m1, 1 add $m3, $m3, -1 ld32 $m10, $m11, $m15, 29 # 4-byte Folded Reload ld32 $m1, $m11, $m15, 26 # 4-byte Folded Reload .Lpack2_15_BB0_16: # %for.body.i132.i # Parent Loop BB0_2 Depth=1 # Parent Loop BB0_3 Depth=2 # Parent Loop BB0_4 Depth=3 # => This Inner Loop Header: Depth=4 ldz8step $m4, $m15, $m10+=, 1 shl $m4, $m4, $m0 or $m8, $m4, $m8 add $m0, $m0, 8 brnzdec $m3, .Lpack2_15_BB0_16 .Lpack2_15_BB0_17: # %if.end.i142.i # in Loop: Header=BB0_4 Depth=3 mov $m3, $m15 mov $m0, $m15 mov $m10, $m1 # %bb.18: # %for.body.i155.i # in Loop: Header=BB0_4 Depth=3 { rpt $m7, 3 fnop } { ldz8step $m4, $m15, $m10+=, 1 fnop } { shl $m4, $m4, $m3 fnop } { or $m0, $m4, $m0 fnop } { add $m3, $m3, 8 fnop } .Lpack2_15_BB0_19: # %_ZZN15Vertex_pack2_157computeEjENKUljjE_clEjj.exit157.i # in Loop: Header=BB0_4 Depth=3 ld32 $m3, $m11, $m15, 31 # 4-byte Folded Reload add $m3, $m3, -1 st32 $m3, $m11, $m15, 31 # 4-byte Folded Spill ld32 $m3, $m11, $m15, 28 # 4-byte Folded Reload add $m3, $m3, 4 st32 $m3, $m11, $m15, 28 # 4-byte Folded Spill ld32 $m3, $m11, $m15, 30 # 4-byte Folded Reload add $m3, $m3, 4 st32 $m3, $m11, $m15, 30 # 4-byte Folded Spill ld32 $m3, $m11, $m15, 29 # 4-byte Folded Reload add $m3, $m3, 4 st32 $m3, $m11, $m15, 29 # 4-byte Folded Spill add $m1, $m1, 4 st32 $m1, $m11, $m15, 26 # 4-byte Folded Spill add $m2, $m2, 1 st32 $m2, $m11, $m15, 27 # 4-byte Folded Spill shl $m3, $m9, 5 add $m9, $m9, 4 st32 $m9, $m11, $m15, 25 # 4-byte Folded Spill shr $m4, $m5, 8 and $m4, $m4, 255 shl $m7, $m8, 8 ld32 $m9, $m11, $m15, 12 # 4-byte Folded Reload and $m7, $m7, $m9 or $m1, $m4, $m7 st32 $m1, $m11, $m15, 23 # 4-byte Folded Spill shr $m7, $m5, 16 and $m7, $m7, 255 shr $m10, $m8, 8 and $m10, $m10, $m9 andc $m1, $m3, 511 ld32 $m2, $m11, $m15, 17 # 4-byte Folded Reload add $m1, $m2, $m1 and $m3, $m3, 384 or $m4, $m1, $m3 and $m3, $m5, 255 shr $m5, $m5, 24 or $m1, $m10, $m5 st32 $m1, $m11, $m15, 24 # 4-byte Folded Spill shl $m10, $m6, 8 ld32 $m1, $m11, $m15, 11 # 4-byte Folded Reload and $m10, $m10, $m1 shl $m2, $m0, 24 or $m2, $m2, $m3 shr $m3, $m6, 8 and $m3, $m3, $m1 or $m2, $m2, $m10 and $m10, $m8, $m9 shl $m8, $m8, 16 or $m7, $m7, $m10 and $m10, $m6, $m1 shr $m6, $m6, 16 and $m8, $m8, $m9 ld32 $m5, $m11, $m15, 23 # 4-byte Folded Reload or $m5, $m5, $m10 shl $m10, $m0, 16 ld32 $m9, $m11, $m15, 13 # 4-byte Folded Reload and $m10, $m10, $m9 or $m3, $m7, $m3 shl $m7, $m0, 8 and $m0, $m0, $m9 and $m7, $m7, $m9 and $m6, $m6, $m1 ld32 $m1, $m11, $m15, 24 # 4-byte Folded Reload or $m0, $m1, $m0 or $m2, $m2, $m8 or $m1, $m5, $m10 or $m8, $m4, 32 or $m3, $m3, $m7 or $m7, $m4, 64 or $m0, $m0, $m6 or $m5, $m4, 96 ld32 $m6, $m11, $m15, 10 # 4-byte Folded Reload st32 $m2, $m6, $m4, 0 st32 $m1, $m6, $m8, 0 st32 $m3, $m6, $m7, 0 ld32 $m7, $m11, $m15, 25 # 4-byte Folded Reload st32 $m0, $m6, $m5, 0 ld32 $m2, $m11, $m15, 16 # 4-byte Folded Reload ld32 $m3, $m11, $m15, 15 # 4-byte Folded Reload ld32 $m4, $m11, $m15, 14 # 4-byte Folded Reload ld32 $m5, $m11, $m15, 22 # 4-byte Folded Reload ld32 $m8, $m11, $m15, 21 # 4-byte Folded Reload ld32 $m9, $m11, $m15, 20 # 4-byte Folded Reload ld32 $m6, $m11, $m15, 19 # 4-byte Folded Reload ld32 $m10, $m11, $m15, 18 # 4-byte Folded Reload ld32 $m0, $m11, $m15, 31 # 4-byte Folded Reload brnz $m0, .Lpack2_15_BB0_4 # %bb.6: # %for.cond.cleanup11.i # in Loop: Header=BB0_3 Depth=2 ld32 $m0, $m11, $m15, 7 # 4-byte Folded Reload add $m0, $m0, -1 add $m10, $m10, 24 add $m6, $m6, 1296 add $m9, $m9, 1296 add $m8, $m8, 1296 add $m5, $m5, 1296 st32 $m0, $m11, $m15, 7 # 4-byte Folded Spill brnz $m0, .Lpack2_15_BB0_3 # %bb.7: # %for.cond.cleanup7.loopexit.i # in Loop: Header=BB0_2 Depth=1 ld32 $m0, $m11, $m15, 3 # 4-byte Folded Reload ld32 $m0, $m0, $m15, 0 ld32 $m5, $m11, $m15, 5 # 4-byte Folded Reload add $m5, $m5, 1 cmpult $m0, $m5, $m0 ld32 $m6, $m11, $m15, 4 # 4-byte Folded Reload add $m6, $m6, 1728 add $m2, $m2, 1728 add $m3, $m3, 1728 add $m4, $m4, 1728 brnz $m0, .Lpack2_15_BB0_2 .Lpack2_15_BB0_8: # %_ZN15Vertex_pack2_157computeEj.exit exitz $m15 .Lpack2_15_func_end0: .size __runCodelet_Vertex_pack2_15, .Lpack2_15_func_end0-__runCodelet_Vertex_pack2_15 .section .stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack2_15 .long .Lpack2_15_func_begin0 .ascii "\200\001" .section .text.__runCodelet_Vertex_pack2_15,"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