Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

SQDMLSL (by element, 2D)

Test 1: uops

Code:

  sqdmlsl v0.2d, v1.2s, v2.s[1]
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372206125482510001000100039831303018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110003073216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
1004303722846125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
10043037222461254825100010001000398313130183037303724153289510001000300030373037111001100001573216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039967013018303730372419328951000100030003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000073216222630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqdmlsl v0.2d, v1.2s, v2.s[1]
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020030501300373008621102011009910010010000100000071014162229634100001003003830038300383003830038
10204300372250000612954825101001001000010010148500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
102043003722500180612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
10204300372240030612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012163229634100001003003830038300383003830038
1020430037225001440612954825101001001000010010000500427731330018300373003728265328745101002001000020230000300373003721102011009910010010000100000071212172329634100001003003830038300383008530038
10204300372250012029772954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
102043003722500011032954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162329634100001003003830038300383003830038
10204300372250090612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071212162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9faccdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722451061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001090640216222963010000103003830038300383003830038
100243003722551061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722518061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216232963010000103003830038300383003830038
100243003722427061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722521061295482510010101000010100005042773130300183003730037282873287671001020100002030000300853008411100211091010100001000640216222963010000103003830038300383003830038
1002430037224270612954825100101010000101000050427731313001830037300372828723287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722515061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722433061295482510010101000010100005042773131300183003730037282873287881001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722539061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001001640216222963010000103003830038300383003830038
100243003722512061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqdmlsl v0.2d, v0.2s, v1.s[1]
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225156129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130053300373003728265828745101002001000020030000300373003711102011009910010010000100007101161129634100001003008330038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225044129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225053629548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129530251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)6061696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250006129548251001010100001010000504277313003001830037300372828732876710010201000020300003003730037111002110910101000010006400316332963010000103003830038300383003830038
10024300372250006129548251001011100081010000504277313003001830037300372828732876710010201000020300003003730037111002110910101000010006400316332963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130030018300373003728287328767100102010000203000030037300371110021109101010000100126400316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313003001830037300372828732876710010201000020300003003730037111002110910101000010006400316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313003001830037300372828732876710010201000020300003003730037111002110910101000010036400316332963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731300300183003730037282873287671001020100002030000300373003711100211091010100001001026400316332963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731300300183003730037282873287671001020100002030000300373003711100211091010100001001716400316332963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731300300183003730037282873287671001020100002030000300373003711100211091010100001001296400316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313003001830037300372828732876710010201000020300003003730037111002110910101000010096400316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313003001830037300372828732876710010201000020300003003730037111002110910101000010006400316322963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqdmlsl v0.2d, v1.2s, v0.s[1]
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b191e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000747295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250017461295482510100100100001001014850042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200309843008430037111020110099100100100001000007101161129667100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826526287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001001007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b1e3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000000006403163329630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000000006403163329630010000103003830038300383003830038
1002430037225006006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000000006403163329630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300843013028287328767100102010000203000030037300371110021109101010000100000000006403163329630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000000006403163329630010000103003830038300383003830038
100243003722400006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000000006403163329630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000000006403163329630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000000006403163329630010000103003830038300383003830038
1002430037225000063129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000000006403163329630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000000006403163329630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlsl v0.2d, v8.2s, v9.s[1]
  movi v1.16b, 0
  sqdmlsl v1.2d, v8.2s, v9.s[1]
  movi v2.16b, 0
  sqdmlsl v2.2d, v8.2s, v9.s[1]
  movi v3.16b, 0
  sqdmlsl v3.2d, v8.2s, v9.s[1]
  movi v4.16b, 0
  sqdmlsl v4.2d, v8.2s, v9.s[1]
  movi v5.16b, 0
  sqdmlsl v5.2d, v8.2s, v9.s[1]
  movi v6.16b, 0
  sqdmlsl v6.2d, v8.2s, v9.s[1]
  movi v7.16b, 0
  sqdmlsl v7.2d, v8.2s, v9.s[1]
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2508

retire (01)cycle (02)0318191e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042009115000002925801161008001610080028500640196120045200652006561280128200800282002400842006520065111602011009910010016000010000000011110119116002006201600001002006620066200662006620066
1602042006515000002925801161008001610080028500640196120045200652006561280128200800282002400842006520065111602011009910010016000010000000011110119016002006201600001002006620066200662006620066
1602042006515000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000000010111116112006101600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000000010111116112006101600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000000010111116112006101600001002006520065200652006520065
16020420064150000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000018000010111116112006101600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000000010111116112006101600001002015720065200652006520065
1602042006415000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000000010111116112006101600001002006520065200652006520065
16020420064151000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000015000010111116112006101600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000000010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)03041e1f3a3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f60696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8accfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420069150300174258001212800001280000626400001120029200482004832280012208000020240000200482004811160021109101016000010000001005531104222111243220045216160000102004920049200492004920049
16002420048150200174258001212800001280000626400001120029200482004832280012208000020240000200482004811160021109101016000010000001005962202622111311920045216160000102004920049200492004920049
16002420048150200145258001212800001280000626400001120029200482004832280012208000020240000200482004811160021109101016000010000101004631102222111312520045216160000102004920049200492004920049
1600242004815021501137258001212800001280000626400001120029200482004832280012208000020240000200482004811160021109101016000010000001005661103222111303020045216160000102004920049200492004920053
1600242004815021200353258001212800001280000626400001120033200462005232280012208000020240000200482004811160021109101016000010000001004331102022111322120045216160000102004920049200492004920049
16002420048150230045258001212800001280000626400001120029200482004832280012208000020240000200482004811160021109101016000010000001004331101922111322520045216160000102004920049200492004920049
16002420048150200045258001212800001280000626400001120029200482004832280012208000020240000200482004811160021109101016000010000001004431102422111322020045216160000102004920049200492004920049
16002420048150290045258001212800001280000626400001120029200482004832280012208000020240000200522005211160021109101016000010000001005531103122111313320045216160000102004920047200492004920049
16002420048150200145258001212800001280000626400001120029200482004832280012208000020240000200482004811160021109101016000010000001005331103222111183220045216160000102004920049200492004920049
16002420048150200174258001212800001280000626400001120029200482004832280012208000020240000200482004811160021109101016000010000001005431103122111183120045215160000102004920049200492004920049

Test 6: throughput

Count: 12

Code:

  sqdmlsl v0.2d, v12.2s, v13.s[1]
  sqdmlsl v1.2d, v12.2s, v13.s[1]
  sqdmlsl v2.2d, v12.2s, v13.s[1]
  sqdmlsl v3.2d, v12.2s, v13.s[1]
  sqdmlsl v4.2d, v12.2s, v13.s[1]
  sqdmlsl v5.2d, v12.2s, v13.s[1]
  sqdmlsl v6.2d, v12.2s, v13.s[1]
  sqdmlsl v7.2d, v12.2s, v13.s[1]
  sqdmlsl v8.2d, v12.2s, v13.s[1]
  sqdmlsl v9.2d, v12.2s, v13.s[1]
  sqdmlsl v10.2d, v12.2s, v13.s[1]
  sqdmlsl v11.2d, v12.2s, v13.s[1]
  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2503

retire (01)cycle (02)0308090b18191e1f373f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12020430922225001000004167132512011810012000110012000050042836221300203174830039149733149971201002001200002003600003003930040111202011009910010012000010000000007610116113003601200001003004031749300403174930040
12020431748225000000006202512010010012001710012000050043995241317293004130041166533149971201002001200002003600003004030039111202011009910010012000010000000007610116113003601200001003004031749300403174930040
1202043003923800000000610251201001001200021001200005009600001300203003931748174613167061201002001200002003600003003931748111202011009910010012000010000000007610116113003601200001003004030041300403174930040
12020430039238000000004102512010010012000010012000050096000013002131748300391591631499712010020012000020036000030039317481112020110099100100120000100000009627610116113174501200001003004030923300413004031749
120204300392380000000184167132512010110012000010012000050043995241300213174830039149733149971201002001200002003600003003930040111202011009910010012000010000000007610116113003601200001003174930040317493004031749
120204317482250000000041025120101100120000100120000500960000130020300393004016653314998120100200120000200360000300403003911120201100991001001200001002000013807610116113174501200001003004031749300403174930041
1202043003922500000000416713251201181001200001001200005009900001317293004030039149733149971201002001200002003600003094330041111202011009910010012000010000001007610116113003601200001003004130040300413004031749
12020431748225000000004630251201001001200001001200005009900001300203003930040166533167061201002001200002003600003003931748111202011009910010012000010000000307610116123003601200001003004031749300403174930040
12020430039237000000018410251201001001200011001200005009900001300203003931748166533149981201002001203162003600003003931748111202011009910010012000010000011047610116113003601200001003004130040317513004030041
120204317482250000003520610251201001001200001001200005009600001300203003930040149733167061201002001200002003600003003931748111202011009910010012000010000000007610116113174501200001003004031749300403004130040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2503

retire (01)cycle (02)03041e373a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc2c5cfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1200243068122819102570251200111012003510120000509600001130021300393003914996315019120010201200002036000030039300391112002110910101200001001590075256520271632221253003603110120000103004030040300403004030040
120024300392250001580251200101012000010120000509600000130020300393003914996315019120010201200002036000030039300391112002110910101200001009007525652028163224523300360155120000103004030040300403004030040
120024300392250001580251200101012001710120000509600000130020300393003914996315019120010201200002036000030039300391112002110910101200001001024075246520281632216253003603110120000103004030040300403004030040
1200243003922500015202512001010120017101200005096000001300203003930039149963150191200102012000020360000300393003911120021109101012000010030075246520261632221253003603110120000103004030040300403004030040
1200243003922500015202512001010120017101200005096000001300203003930039149963150191200102012000020360000300393003911120021109101012000010030075246521261632229283003603110120000103004030040300403004030040
1200243003922500015202512001010120000101200005096000001300203003930039149963150191200102012000020360000300393003911120021109101012000010030075246520161632228213003603110120000103004030040300403004030040
1200243003922500015202512001010120000101200005096000001300203003930039149963150191200102012000020360000300393003911120021109101012000010030075256520281632228283003603110120000103004030040300403004030040
12002430922225000158025120010101200171012000050102196401300203003930039149963150191200102012000020360000300393003911120021109101012000010000075256520271632213293003603110120000103004030040300403009030040
1200243003922500005802512001010120000101200005096000001300203003930039149963150191200102012000020360000300393003911120021109101012000010060075256520271632222273003603110120000103004030040300403004030040
1200243003922500015802512001010120017101200005096000001300203003930039149963150191200102012000020360000300393003911120021109101012000010030075256520261632217283003603110120000103004030040300403004030040