Apple M1 Microarchitecture Research by Dougall Johnson

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

SUBHN2 (vector, 4S)

Test 1: uops

Code:

  subhn2 v0.8h, v1.4s, v2.4s
  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)03080b18191e1f3a3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723000000061254825100010001000398313301830373037241532895100010003000303730371110011000000000073216112702100030383038303830383038
1004303722000000061254825100010001000398313301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
1004303722000000061254825100010001000398313301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
1004303723000000061254825100010001000398313301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
1004303723000000061254825100010001000398313301830373037241532895100010003000308430371110011000000000073116112630100030383038303830383038
1004303722000000061254825100010001000398313301830373037241532895100010003000303730371110011000000006073116112630100030383038303830383038
1004303723000000061254825100010001000398313301830373037241532895100010003000303730371110011000000003073116112630100030383038303830383038
1004303722000000061254825100010001000398313301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
1004303723000000061254825100010001000398313301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037230000360061254825100010001000398313301830373037241532895100010003000303730371110011000000003073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  subhn2 v0.8h, v1.4s, v2.4s
  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)031e3a3f4e51inst 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)9fa8cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710021622296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710021622296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710121622296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710121622296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010037710121622296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710121622296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710121622296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710121622296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710121622296340100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710121622296340100001003003830038300383003830038

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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003724100612954825100101010000101000050427731303001830037300372828732878810010201000020300003003730037111002110910101000010000000640916432963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000640316342963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000640316342963010000103003830038300383003830038
100243003722400612954825100101010000101000050427731313005430037300372828732876710010201000020300003008330037211002110910101000010000028700640316342963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020305163003730037111002110910101000010000000640316342963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000640416432963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000640316532963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000640316532963010000103003830038300383003830038
100243003722400612954825100101010000101000050427731303009030037300372828732876710010201000020300003003730037111002110910101000010000000728316332963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  subhn2 v0.8h, v0.4s, v1.4s
  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)03041e3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722510134295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500726295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500504295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500155295484910100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500812295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722400726295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500124295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500124295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500246295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500166295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03070a18191e1f3a3f4e51inst 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)9fa8acc5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722511002190268295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006441516101029630010000103003830038300383003830038
100243003722511003026829548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100300644101651029630010000103003830038300383003830038
100243003722511000026829548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000644101610829630010000103003830038300383003830038
1002430037225110030268295482510010101000010100005042773130300183003730037282873287671001020100002030000300373008211100211091010100001000006441016101029630010000103003830038300383003830038
10024300372411100210268295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006441116101029630010000103003830038300383003830038
10024300372251100180268295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006441016101029630010000103003830038300383003830038
10024300372251100144026829548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100001644816101029630010000103003830038300383003830038
10024300372251100420268295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006441016101029630010000103003830038300383003830038
100243003722511000024835295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006441016101029630010000103003830038300383003830038
1002430037225110030026829548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000644516101029630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  subhn2 v0.8h, v1.4s, v0.4s
  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)0308090a18191e3f4e51inst 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003727300000044029548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100026007103162229634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100059007102162229634100001003003830038300383003830038
102043003723200000036329548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000487102162229634100001003003830038300383003830038
1020430037245001000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010001007102162229634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100060157102162229634100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010001037102162229634100001003003830038300383003830038
1020430037225000000612954825101001041000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010001037102162229634100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010003037102162229634100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010002037102162229634100001003003830038300383003830038
1020430037224000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010001037102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250279929548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006424162229630010000103003830038300383003830038
10024300372250336129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250126129548251001010100001010000504277313030018300373003728287328767100122010000203000030037300371110021109101010000100016402162229630010000103003830038300383003830038
10024300372250126129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630210000103003830038300383003830038
10024300372250576129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722503036129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250186129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225036129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000604277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  subhn2 v0.8h, v8.4s, v9.4s
  movi v1.16b, 0
  subhn2 v1.8h, v8.4s, v9.4s
  movi v2.16b, 0
  subhn2 v2.8h, v8.4s, v9.4s
  movi v3.16b, 0
  subhn2 v3.8h, v8.4s, v9.4s
  movi v4.16b, 0
  subhn2 v4.8h, v8.4s, v9.4s
  movi v5.16b, 0
  subhn2 v5.8h, v8.4s, v9.4s
  movi v6.16b, 0
  subhn2 v6.8h, v8.4s, v9.4s
  movi v7.16b, 0
  subhn2 v7.8h, v8.4s, v9.4s
  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)03081e3f51inst 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)5f60696b6d6escheduler 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420089150003925801001008000010080000500640000002004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000012004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000012004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064151003925801001008000010080000500640000012004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500153925801001008000010080000500640000012004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000002004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000002004502006420064322801002008000020024000020064200642116020110099100100160000100001011115811200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000012004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000012004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000012004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b191e1f3f51inst 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)5f6061696d6escheduler 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)9fa0a1a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200741500000051278001212800001280000626400001152003220051200513228001220800002024000020051200511116002110910101600001000001002881172521155200482201160000102005220052200522005220052
160024200511500000045278001212800001280000626400001152003220051200513228001220800002024000020051200511116002110910101600001000091003081152521166200482201160000102005220052200522005220052
16002420132151003917645278001214805211380000626400001152003220051200513228001220800002024000020051200511116002110910101600001000001002981162521157200482201160000102005220056200522005220052
1600242005115000000452780012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010000010028811511621155202533201160000102013220134201342048220052
160024201311500000045278001212800001280000626400001152003220051200513228001220800002024000020051200511116002110910101600001000001002881152521155200482201160000102005220052200522005220052
16002420051150000007102780012128000012801056264000011520032200512005132280012208000020240000200512005111160021109101016000010003931002881172521175200482201160000102005220052200522005220052
160024200511520000045278001213800001280000626400001152003220051200513228001220800002024000020051200511116002110910101600001000001002981142521155200482201160000102005220052200522005220052
1600242005115000045045278001212800001280000626400001152003220051200513228001220800002024000020051200511116002110910101600001000201002981152521157200482201160000102005220052200522005220052
160024200511500000045278001212800001280000626400001152003220051200513228001220800002024000020051200511116002110910101600001000101002881172521156200482201160000102005220052200522005220052
1600242005115000000452780012128000012800006264000011520032200512005125228001220800002024000020051200511116002110910101600001000001002981162521177200482201160000102005220052200522005220052

Test 6: throughput

Count: 16

Code:

  subhn2 v0.8h, v16.4s, v17.4s
  subhn2 v1.8h, v16.4s, v17.4s
  subhn2 v2.8h, v16.4s, v17.4s
  subhn2 v3.8h, v16.4s, v17.4s
  subhn2 v4.8h, v16.4s, v17.4s
  subhn2 v5.8h, v16.4s, v17.4s
  subhn2 v6.8h, v16.4s, v17.4s
  subhn2 v7.8h, v16.4s, v17.4s
  subhn2 v8.8h, v16.4s, v17.4s
  subhn2 v9.8h, v16.4s, v17.4s
  subhn2 v10.8h, v16.4s, v17.4s
  subhn2 v11.8h, v16.4s, v17.4s
  subhn2 v12.8h, v16.4s, v17.4s
  subhn2 v13.8h, v16.4s, v17.4s
  subhn2 v14.8h, v16.4s, v17.4s
  subhn2 v15.8h, v16.4s, v17.4s
  movi v16.16b, 17
  movi v17.16b, 18

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2502

retire (01)cycle (02)0318191e373f4e51inst 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)60696b6d6edispatch 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)9fa6a8acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044006130000017410251601001001600001001600005002398999140020040048400391997332000716010020016000020048000040048400391116020110099100100160000100016600010110116114003601600001004004040049400864004040049
160204400393000001741025160117100160000100160000500239899904002004003940039199733199971601002001600002004800004003940039111602011009910010016000010000000010110116114004501600001004004940040400404004040040
160204400393000001741025160100100160000100160000500128000004002904003940048199733200061601002001600002004800004004840039111602011009910010016000010000000010110116114004501600001004004040040400404004040040
1602044004830000004102516011710016000010016000050017560470400290400484004819973320006160100200160000200480000400394003911160201100991001001600001002122800010110116114003601600001004004040040400404004040040
16020440052300000014602516010010016000010016000050012800000400200400394003919973319997160100200160000200480000400484004811160201100991001001600001000013200010110116114003601600001004004940040400404004040049
160204400393000000231025160117100160000100160000500128000004002904004840048199733200061601002001600002004800004003940048111602011009910010016000010000000010110116114003601600001004004040049400404004040040
16020440039300000050025160118100160000100160000500128000014002004004940039199733199971601002001600002004800004003940048111602011009910010016000010000000010110116114003601600001004004040040400404004040040
1602044005230000004102516010010016000010016000050012800001400200400484004819973320007160100200160000200480000400394007511160201100991001001600001000021300010110116114003601600001004004940040400494004940040
16020440039300000041025160100100160000100160000500128000014002904003940048199733199971601002001600002004800004003940039111602011009910010016000010000000010110116114003601600001004005040049400404004040049
16020440039300000041025160117100160000100160000500128000004002904003940048199733199971601002001600002004800004003940039111602011009910010016000010000900010110116114003601600001004004040050400494004040049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b191e373f4e51inst 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)5f6061696d6edispatch 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)9fa1a8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440048310000060176702511615241516052814161835602193680115400294004840039199963200191600102016000020480000400484003911160021109101016000010000010022841191621120224006801550160000104004040049400724004940040
16002440048300000000460251600101016001710160000505387188115400214003940048199963200191600102016000020480000400494004811160021109101016000010000010022841191621120224003601550160000104004040040400494004940049
160024400483000000017560251600271016000010160000501280000115400294003940319199963200511600102016000020480000400714003931160021109101016000010000010022841191621119214004501550160000104004040049400404004940040
160024400393000000120460481600101016001712160000501280000115400674003940172199963201061600102016000020480000400484003911160021109101016000010000010022841191621110234003601550160000104004040049400404004940040
1600244007130000000614602516001010160000101600005012800001154002040039400481999632001916001020160000204800004003940048111600211091010160000100000100228418162111994013601550160000104004940040400494015740049
16002440049300000001767025160010101600171016000050538718811540020400484003919996320075160118201600002048000040071400481116002110910101600001021444981002284182842111994004501550160000104004040040400404005040040
16002440039300000001746025160010101600001016000050239899911540020400394003919996320019160010201600002048000040048400481116002110910101600001000001002284119162118214016001550160000104022740267401324004140040
1600244003930011112136940831603381216016910160000501280000115400294018440092200051120106160010201601072048029740039400391116002110910101600001000001002284191611119214006801550160000104004940040400494004040049
1600244004830000000179725251600111016000110160000502398999115400294003940048199963200661600102016021020484086409664039711160021109101016000010202010022841192921116214014201550160000104007240049400404004940040
1600244003930000000175502516002710160017101600005012800001154005240039400391999632002816001020160000204800004004840039111600211091010160000100100100228418162111994003601550160000104004940072400404004040049