Apple M1 Microarchitecture Research by Dougall Johnson

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

SABAL2 (vector, 8H)

Test 1: uops

Code:

  sabal2 v0.8h, v1.16b, v2.16b
  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
1004303722020225482510001000100039831313018303730372415328951000100030003037303711100110000073216112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110000073116122630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
1004303724019225482510001000100039831313018303730372415328951000100030003037303711100110006073216222630100030383038303830383038
100430372508225482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110000373216222630100030383038303830383038
1004303722015625482510001000100039831313018303730372415328951000100030003037303711100110000373116112630100030383038303830383038
100430372306125482510081000100039831313018303730372415328951000100030003037303711100110000073216212630100030383038303830383038

Test 2: Latency 1->1

Code:

  sabal2 v0.8h, v1.16b, v2.16b
  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)0308090b18191e1f3a3f4e51inst 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)9fa1a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000270061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
102043003722500000300061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
1020430037225000005280061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
102043003722400100330061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
102043003722500000150061295482510100100100001001000051142773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
102043003722500000240061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
102043003722500000420061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710131622296340100001003003830038300383003830038
102043003722500000120061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
102043003722500000180061295484410100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
1020430037225000002910061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa1a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640416342963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640316342963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000001640316432963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671015920100002030000300373003711100211091010100001000000640416432963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640316342963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640416432963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640416432963010000103003830038300383003830038
10024300372250082295482510010101000010100005042773130300183008430037282873287671001020100002030000300373003711100211091010100001000000640416432963010000103003830038300383003830038
100243003722501561295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640316332963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sabal2 v0.8h, v0.16b, v1.16b
  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)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722400000000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731330018300373003728265328745101002001000020030522300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000561427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722400000000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000004412954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722400000000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500100000612954825101001001000010010000500427867030018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308191e3f4e51inst 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)9fa8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500061295482510010101000010100005042773131300183003730037282878287861001020100002030000300373003711100211091010100001000016405162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500084295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003723300061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722400061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225000282295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sabal2 v0.8h, v1.16b, v0.16b
  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)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)9fa8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372240726295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722513261295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372240251295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250726295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250548295482510100100100001001000050042773133001830037300372826532874510100200100002003000030085300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250251295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250726295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372240536295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010010007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b181e3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500007262954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000393612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10025300372250100822954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010003640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sabal2 v0.8h, v8.16b, v9.16b
  movi v1.16b, 0
  sabal2 v1.8h, v8.16b, v9.16b
  movi v2.16b, 0
  sabal2 v2.8h, v8.16b, v9.16b
  movi v3.16b, 0
  sabal2 v3.8h, v8.16b, v9.16b
  movi v4.16b, 0
  sabal2 v4.8h, v8.16b, v9.16b
  movi v5.16b, 0
  sabal2 v5.8h, v8.16b, v9.16b
  movi v6.16b, 0
  sabal2 v6.8h, v8.16b, v9.16b
  movi v7.16b, 0
  sabal2 v7.8h, v8.16b, v9.16b
  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)030a0b1e1f3f51inst 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)9fa0a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420088150000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000001011121611200611600001002006520065200652006520065
16020420064150000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100020001011111611200611600001002006520065200652006520065
16020420064151003039258010010080000106800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002006520065200652006520065
16020420064150000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002006520065200652006520065
16020420064150000039258010010080000100800005006400001201112006420064322801002008000020024000020064200641116020110099100100160000100040001011111611200611600001002006520065200652006520065
16020420064151000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100030001011111611200611600001002006520065200652006520065
16020420064150000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002006520065200652006520065
160204200641500000812580100100800001008000050064000012004520064200641022801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002006520065200652006520065
160204200641500000251258010010080000100800005006400001200452006420064322801002008000020024000020064200644116020110099100100160000100033001011111611200611600001002006520065200652006520065
16020420064150000039258010010080000100800005006400001200452006420064322801002008000020024000020064200642116020110099100100160000100000001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2507

retire (01)cycle (02)0304091e3a3f51inst 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)9fa1a6a8accfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420093150000011192780012128000012800006264000011520034200532005332280012208000020240000200532005311160021109101016000010000010050831121271112615200502211160000102005420054200542005420054
1600242005315011013252780012128000012800006264000011520034200532005332280012208000020240000200532005311160021109101016000010000010045851127271112626200502211160000102005420054200542005420054
16002420053150116303732780012128000012800006264000011520034200532005332280012208000020240000200532005311160021109101016000010000010045861121271112515200502211160000102005420054200542005420054
1600242005315011013202780012128000012800006264000011520034200532005332280012208000020240000200532005311160021109101016000010000010045861120271112618200502411160000102005420054200542005420054
1600242005315011003202780012128000012800006264000011520034200532005332280012208000020240000200532005311160021109101016000010000010049861125271112626200502211160000102005420054203542005420054
1600242005315011013212780012128000012800006264000011520034200532005332280012208000020240312200532015611160021109101016000010000010040861121271112621200502412160000102006320063200632006320063
16002420062150110132329800121280000128000062640000115200342006220053322800122080000202400002005320062111600211091010160000100000100401172015363222923200592412160000102006320063200632006320063
16002420062151110134429800121280000128000062640000015200432006220062322800122080000202400002006420062111600211091010160000100000100431172116363222516200592411160000102006320063200632005420063
16002420062150110032629800121280000128000062640000015200432006220062322800122080000202400002006220062111600211091010160000100000100531172126363222026200592412160000102006320063200632006320063
16002420062150110133229800121280000128000062640000015200432006220062322800122080000202400002006220062111600211091010160000100000100481172120363222521200592412160000102006320063200632006320063

Test 6: throughput

Count: 16

Code:

  sabal2 v0.8h, v16.16b, v17.16b
  sabal2 v1.8h, v16.16b, v17.16b
  sabal2 v2.8h, v16.16b, v17.16b
  sabal2 v3.8h, v16.16b, v17.16b
  sabal2 v4.8h, v16.16b, v17.16b
  sabal2 v5.8h, v16.16b, v17.16b
  sabal2 v6.8h, v16.16b, v17.16b
  sabal2 v7.8h, v16.16b, v17.16b
  sabal2 v8.8h, v16.16b, v17.16b
  sabal2 v9.8h, v16.16b, v17.16b
  sabal2 v10.8h, v16.16b, v17.16b
  sabal2 v11.8h, v16.16b, v17.16b
  sabal2 v12.8h, v16.16b, v17.16b
  sabal2 v13.8h, v16.16b, v17.16b
  sabal2 v14.8h, v16.16b, v17.16b
  sabal2 v15.8h, v16.16b, v17.16b
  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)031e373f4e51inst 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
1602044005829900630251601171001600001001600005001280000140030400714003919973319997160100200160000200480000400394003911160201100991001001600001000011011011611400461600001004004040050400404007240050
160204400483000172720251601171001600171001600005005387188140029400404003919973319997160100200160000200480000400404003911160201100991001001600001000001011011613400361600001004005040040400404005040040
160204400403000118600251601611001600611001600005001280000140020400394003919973319997160100200160000200480000400394003911160201100991001001600001000001011011611400461600001004005040040400724004940050
16020440039300017142825251601001001600171001600005001280000140029400494003919973320006160100200160000200480000400394003911160201100991001001600001000001011011611400361600001004004040050400494004040040
160204400482990175402516010010016000010016000050053871881400294004040039199731220034160100200160000200480000400394003911160201100991001001600001001601015213741400361600001004004940040401104011740181
1602044010730001410251601001001600001001600005001280000140029400484003919973320006160100200160000200480000400394004811160201100991001001600001000301011011611400361600001004004040040400504004040041
1602044007129901718700251601001001600011001600005001320000140020400394004019973319997160100200160000200480000400404004811160201100991001001600001000001011011611400681600001004004040040400504004040049
1602044003929900420251601001001600001001600005001320000140020400394003919973319998160223200160000200480000400714004821160201100991001001600001000001011011611401071600001004007240040400404004140050
16020440039300120410251601001001600001001600005002398999140029400394004019973319997160100200160000200480000400494003911160201100991001001600001000001011011611400361600001004004040040400404004040040
16020440039300007260251601171001600011001600005002399027140020400404003919973320007160100200160000200480000400494003911160201100991001001600001003001011031611400361600001004005040040400724025540041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e373f51inst 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)9fa6a8accdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244004930000762516001010160000101600006012800001154002040048400391999632001916001220160000204800004004840040111600211091010160000100000100221121916211844004602060160000104004040040400404004040040
1600244003930000344251600101016000010160000502399055115400304003940039199963200281600102016000020480000400394004811160021109101016000010000010022821716211744003602070160000104005040049400404004140040
16002440039300917889591600101316009810160000501280000115400204003940048199963200191600102016000020480000400484003911160021109101016000010010010022822616411864003722070160000104004040040400494004940040
1600244004830001775251600101016000010160000602438903115400204004840048199963200281600102016000020480000400394004811160021109101016000010000010022821716211744004504070160000104005040050400404004940040
16002440049300017140251600271016001710160000502398999015400204003940039199963200201600122016000020480000400394004811160021109101016000010000010025822516411764003604060160000104004040040400494004040049
1600244004829900111251600101016000010160000501280000115400294004840039199963200281600102016000020480000400394003921160021109101016000010000010044832716211554004504090160000104004940040400404004940049
1600244004830001869251600101016000010160000501280000115400204004840039199963200191600102016000020480000400394004811160021109101016000010000010022821416211744003702090160000104004940040400494004040049
1600244003930000204251600101016000010160000502398999115400204004940048199963200191600102016000020480000400494003911160021109101016000010000010022821716211464003702060160000104004940096400544005040041
1600244003930001229251600271016000010160000501280000115400204003940048199963200281600122016000020480000400494004811160021109101016000010000010022821716211744003602090160000104004040040400504005040040
160024400392990171872516001010160000101600005013199981154002040039400401999632002816001020160000204800004004040039111600211091010160000100000100228216162114640036020140160000104004040041400404004040040