.text .allow_optimizations .file "3" .section .text.__runCodelet_Vertex_pack2_9,"ax",@progbits .globl __runCodelet_Vertex_pack2_9 # -- Begin function __runCodelet_Vertex_pack2_9 .p2align 2 .type __runCodelet_Vertex_pack2_9,@function __runCodelet_Vertex_pack2_9: # @__runCodelet_Vertex_pack2_9 .worker .Lpack2_9_func_begin0: # %bb.0: # %entry setzi $m6, 40 cmpult $m6, $m6, __worker_stack_max_growth_plus_one brz $m6, _stackoverflow add $m11, $m12, -40 get $m0, 1 ld32 $m1, $m13, $m15, 7 brz $m1, .Lpack2_9_BB0_17 # %bb.1: # %for.cond3.preheader.i.preheader mov $m4, $m15 and $m5, $m0, 7 sub $m0, 25, $m5 setzi $m1, 43691 setzi $m2, 43690 mul $m1, $m0, $m1 mul $m0, $m0, $m2 shr $m1, $m1, 16 add $m0, $m0, $m1 setzi $m1, 983040 shr $m0, $m0, 18 ld32 $m2, $m13, $m15, 0 st32 $m2, $m11, $m15, 7 # 4-byte Folded Spill ld32 $m3, $m13, $m15, 1 or $m1, $m1, 4293918720 st32 $m1, $m11, $m15, 6 # 4-byte Folded Spill setzi $m1, 65535 st32 $m1, $m11, $m15, 9 # 4-byte Folded Spill shl $m1, $m5, 1 st32 $m1, $m11, $m15, 3 # 4-byte Folded Spill st32 $m5, $m11, $m15, 4 # 4-byte Folded Spill shl $m1, $m5, 5 st32 $m1, $m11, $m15, 2 # 4-byte Folded Spill add $m0, $m0, 2 st32 $m0, $m11, $m15, 1 # 4-byte Folded Spill add $m0, $m13, 28 st32 $m0, $m11, $m15, 0 # 4-byte Folded Spill .Lpack2_9_BB0_2: # %for.cond3.preheader.i # =>This Loop Header: Depth=1 # Child Loop BB0_3 Depth 2 st32 $m4, $m11, $m15, 5 # 4-byte Folded Spill ld32 $m10, $m11, $m15, 1 # 4-byte Folded Reload ld32 $m7, $m11, $m15, 2 # 4-byte Folded Reload ld32 $m0, $m11, $m15, 3 # 4-byte Folded Reload st32 $m0, $m11, $m15, 8 # 4-byte Folded Spill ld32 $m1, $m11, $m15, 4 # 4-byte Folded Reload add $m10, $m10, -1 .Lpack2_9_BB0_3: # %for.body6.i # Parent Loop BB0_2 Depth=1 # => This Inner Loop Header: Depth=2 setzi $m0, 19 cmpult $m9, $m0, $m1 brnz $m9, .Lpack2_9_BB0_4 # %bb.5: # %if.then.i # in Loop: Header=BB0_3 Depth=2 ld32 $m0, $m11, $m15, 7 # 4-byte Folded Reload ld32 $m8, $m0, $m7, 0 ld32 $m0, $m0, $m7, 4 bri .Lpack2_9_BB0_6 .Lpack2_9_BB0_4: # in Loop: Header=BB0_3 Depth=2 mov $m8, $m15 mov $m0, $m15 .Lpack2_9_BB0_6: # %if.end19.i # in Loop: Header=BB0_3 Depth=2 setzi $m4, 1048320 or $m4, $m4, 2146435072 and $m4, $m7, $m4 ld32 $m2, $m11, $m15, 8 # 4-byte Folded Reload and $m5, $m2, 14 or $m4, $m4, $m5 ld32 $m2, $m11, $m15, 9 # 4-byte Folded Reload and $m5, $m8, $m2 shl $m2, $m0, 16 shr $m6, $m8, 16 ld32 $m8, $m11, $m15, 6 # 4-byte Folded Reload and $m0, $m0, $m8 shl $m8, $m4, 1 or $m2, $m2, $m5 or $m0, $m0, $m6 or $m4, $m8, 32 st32 $m2, $m3, $m8, 0 st32 $m0, $m3, $m4, 0 brnz $m9, .Lpack2_9_BB0_7 # %bb.8: # %if.then.i.1 # in Loop: Header=BB0_3 Depth=2 ld32 $m2, $m11, $m15, 7 # 4-byte Folded Reload ld32 $m0, $m2, $m7, 1 ld32 $m4, $m2, $m7, 5 bri .Lpack2_9_BB0_9 .Lpack2_9_BB0_7: # in Loop: Header=BB0_3 Depth=2 mov $m0, $m15 mov $m4, $m15 .Lpack2_9_BB0_9: # %if.end19.i.1 # in Loop: Header=BB0_3 Depth=2 ld32 $m6, $m11, $m15, 6 # 4-byte Folded Reload ld32 $m2, $m11, $m15, 9 # 4-byte Folded Reload and $m2, $m0, $m2 shl $m5, $m4, 16 shr $m0, $m0, 16 and $m4, $m4, $m6 or $m2, $m5, $m2 or $m0, $m4, $m0 or $m4, $m8, 64 or $m5, $m8, 96 st32 $m2, $m3, $m4, 0 st32 $m0, $m3, $m5, 0 brnz $m9, .Lpack2_9_BB0_10 # %bb.11: # %if.then.i.2 # in Loop: Header=BB0_3 Depth=2 ld32 $m2, $m11, $m15, 7 # 4-byte Folded Reload ld32 $m0, $m2, $m7, 2 ld32 $m4, $m2, $m7, 6 bri .Lpack2_9_BB0_12 .Lpack2_9_BB0_10: # in Loop: Header=BB0_3 Depth=2 mov $m0, $m15 mov $m4, $m15 .Lpack2_9_BB0_12: # %if.end19.i.2 # in Loop: Header=BB0_3 Depth=2 ld32 $m2, $m11, $m15, 9 # 4-byte Folded Reload and $m2, $m0, $m2 shl $m5, $m4, 16 shr $m0, $m0, 16 and $m4, $m4, $m6 or $m2, $m5, $m2 or $m0, $m4, $m0 or $m4, $m8, 128 or $m5, $m8, 160 st32 $m2, $m3, $m4, 0 st32 $m0, $m3, $m5, 0 brnz $m9, .Lpack2_9_BB0_13 # %bb.14: # %if.then.i.3 # in Loop: Header=BB0_3 Depth=2 ld32 $m2, $m11, $m15, 7 # 4-byte Folded Reload ld32 $m0, $m2, $m7, 3 ld32 $m4, $m2, $m7, 7 bri .Lpack2_9_BB0_15 .Lpack2_9_BB0_13: # in Loop: Header=BB0_3 Depth=2 mov $m0, $m15 mov $m4, $m15 .Lpack2_9_BB0_15: # %if.end19.i.7 # in Loop: Header=BB0_3 Depth=2 add $m1, $m1, 6 ld32 $m2, $m11, $m15, 8 # 4-byte Folded Reload add $m2, $m2, 12 st32 $m2, $m11, $m15, 8 # 4-byte Folded Spill add $m7, $m7, 192 ld32 $m2, $m11, $m15, 9 # 4-byte Folded Reload and $m2, $m0, $m2 shr $m0, $m0, 16 shl $m5, $m4, 16 and $m4, $m4, $m6 or $m2, $m5, $m2 or $m0, $m4, $m0 or $m4, $m8, 192 or $m5, $m8, 224 st32 $m2, $m3, $m4, 0 or $m2, $m8, 256 or $m4, $m8, 288 st32 $m0, $m3, $m5, 0 or $m0, $m8, 320 or $m5, $m8, 352 st32 $azero, $m3, $m2, 0 or $m2, $m8, 384 st32 $azero, $m3, $m4, 0 or $m4, $m8, 416 st32 $azero, $m3, $m0, 0 or $m0, $m8, 448 or $m6, $m8, 480 st32 $azero, $m3, $m5, 0 st32 $azero, $m3, $m2, 0 st32 $azero, $m3, $m4, 0 st32 $azero, $m3, $m0, 0 st32 $azero, $m3, $m6, 0 brnzdec $m10, .Lpack2_9_BB0_3 # %bb.16: # %for.cond.cleanup5.loopexit.i # in Loop: Header=BB0_2 Depth=1 ld32 $m0, $m11, $m15, 0 # 4-byte Folded Reload ld32 $m0, $m0, $m15, 0 ld32 $m4, $m11, $m15, 5 # 4-byte Folded Reload add $m4, $m4, 1 cmpult $m0, $m4, $m0 ld32 $m1, $m11, $m15, 7 # 4-byte Folded Reload add $m1, $m1, 640 st32 $m1, $m11, $m15, 7 # 4-byte Folded Spill add $m3, $m3, 2048 brnz $m0, .Lpack2_9_BB0_2 .Lpack2_9_BB0_17: # %_ZN14Vertex_pack2_97computeEj.exit exitz $m15 .Lpack2_9_func_end0: .size __runCodelet_Vertex_pack2_9, .Lpack2_9_func_end0-__runCodelet_Vertex_pack2_9 .section .stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack2_9 .long .Lpack2_9_func_begin0 .byte 40 .section .text.__runCodelet_Vertex_pack2_9,"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