Apple M1 Microarchitecture Research by Dougall Johnson

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

SHA512SU1

Test 1: uops

Code:

  sha512su1 v0.2d, v1.2d, v2.2d
  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
1004203715082937251000100010006898412018203720371788318951000100030002037203711100110003073116111969100020382038203820382038
1004203715061937251000100010006898412018203720371788318951000100030002037203711100110004073116111969100020382038203820382038
10042037150103937251000100010006898412018203720371788318951000100030002037203711100110000073116111969100020382038203820382038
1004203716061937251000100010006898412018203720371788318951000100030002037203711100110000073116111969100020382038203820382038
1004203715361937251000100010006898412018203720371788318951000100030002037203711100110000073116111969100020382038203820382038
1004203715061937251000100010006898412018203720371788318951000100030002037203711100110001073116111969100020382038203820382038
1004203716061937251000100010006898402018203720371788318951000100030002037203711100110002073116111969100020382038203820382038
1004203715061937251000100010006898412018203720371788318951000100030002037203711100110000073116111969100020382038203820382038
1004203715061937251000100010006898402018203720371788318951000100030002037203711100110000673116111969100020382038203820382038
1004203715061937251000100010006898402018203720371788318951000100030002037203711100110000073116111969100020382038203820382038

Test 2: Latency 1->1

Code:

  sha512su1 v0.2d, v1.2d, v2.2d
  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): 2.0037

retire (01)cycle (02)030b181e3a3f4e51inst 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)cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000006199372510100100100001001000050070798402001820037200371863831874510100200100002003000020037200371110201100991001001000010027117071012162219967100001002003820038200382003820038
102042003715000006199372510100100100001001000050070798402001820037200371863831874510100200100002003000020037200371110201100991001001000010000271012162219967100001002003820038200382003820038
102042003715000006199372510100100100001001000050070798412001820037200371863831874510100200100002003000020037200371110201100991001001000010000071012162319967100001002003820038200382003820038
102042003715000006199372510100100100001001000050070798402001820037200371863831874510100200100002003000020037200371110201100991001001000010000071012162219967100001002003820038200382003820038
1020420037150003061993725101001001000010010000500707984120018200372003718638318745101002001000020030000200372003711102011009910010010000100349071212162219967100001002003820038200382003820038
102042003715000006199372510100100100001001000050070798412001820037200371863831874510100200100002003000020037200371110201100991001001000010000071012162219967100001002003820038200382003820038
102042003715000006199372510100100100001131000050070798412001820037200371863831874510100200100002003000020037200371110201100991001001000010030071012162219967100001002003820038200382003820038
1020420037150000061993725101001001000010010000500707984120018200372003718638318745101002001000020030000200372003711102011009910010010000100027071012162219967100001002003820038200382003820038
10204200371500000631993725101001001000010010000500707984020018200372003718638318745101002001000020030000200372003711102011009910010010000100012071012162219967100001002003820038200382003820038
102042003715000006199372510100100100001001000050070798402001820037200371863831874510100200100002003000020037200371110201100991001001000010000071012162219967100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037149000072699372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000730640216221996910000102003820038200382003820038
100242003715000306199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010020100640216221996910000102003820038200382003820038
100242003715000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000600640216221996910000102003820038200382003820038
100242003715000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000400640216221996910000102003820038200382003820038
100242003715000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000900640316221996910000102003820038200382003820038
1002420037150000061993725100101010000101000050707984120018200372003718660318767100102010000203000020037200371110021109101010000100002130640216231996910000102003820038200382003820038
100242003715010008299372510010101000010100005070798412005420037200371866031876710010201005620301772003720037111002110910101000010002060640216321996910000102003820038200382003820038
100242003715000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000030640216221996910000102003820038200382003820038
100242003715000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000030640216221996910000102003820038200382003820038
100242003715000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000000640216231996910000102003820038200382003820038

Test 3: Latency 1->2

Code:

  sha512su1 v0.2d, v0.2d, v1.2d
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b1e3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000619937251010010010000102100445007079840200182003720037186383187451010020010000200300002003720037211020110099100100100001000107101161119967100001002003820038200382003820038
1020420037150000619937251010010010000100100005007079841200182003720037186383187451010020010000200300002003720037111020110099100100100001000107101161119967100001002003820038200382003820038
1020420037150000619937251010010010000100100005007079840200182003720037186383187451010020010000200300002003720037111020110099100100100001002107101161119967100001002003820038200382003820038
10204200371500007269937251010010010000100101325007079840200182003720037186383187451010020010000200300002003720037111020110099100100100001000467101161119967100001002003820038200382018120038
1020420037150000619937251010010010000100100006267079840200182003720037186383187451010020010000200300002003720037111020110099100100100001000107101161119967100001002003820038200382003820038
1020420037150000619937251010010010000100100005007079840200182003720037186383187451010020010000200300002003720037111020110099100100100001000137101161119967100001002003820038200382003820038
1020420037150000619937251010010010000100100005007079840200182003720037186383187451010020010000200300002013320085111020110099100100100001000137101161119967100001002003820038200382003820038
10204200371490005959937251010010010000100100005007079840200182003720037186383187451010020010000200300002003720037111020110099100100100001000137101161219967100001002003820038200382003820038
1020420037150010619937251010010010000100100005007079840200182003720037186383187451010020010000200300002003720037111020110099100100100001000137101161119967100001002003820038200382003820038
10204200371500012619937251010010010000100100005007079841200182003720037186383187451010020010000200300002003720178111020110099100100100001000037101161119967100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006199372510010101000010100005070798402001820037200371866031876710010201000020300002003720037111002110910101000010309640216221996910000102003820038200382003820038
100242003715006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000640216221996910000102003820038200382003820038
100242003715006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000640216221996910000102003820038200382003820132
100242003715006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010100640216221996910000102003820038200382003820038
10024200371500619937251001010100001010000507079841200182003720037186603187671001020100002030000200372003711100211091010100001035081640216221996910000102003820038200382003820038
100242003715006199372510010101000010100005070798402001820037200371866031876710010201000020300002003720037111002110910101000010000640216221996910000102003820038200382003820038
100242003715006199372510010101000010100005070798402001820037200371866031876710010201000020300002003720037111002110910101000010000640216221996910000102003820038200382003820038
1002420037150061993725100101010000101000050707984020018200372003718660318767100102010000203000020037200371110021109101010000102403640316221996910000102003820038200382003820038
100242003715006199372510010101000010100005070798402001820037200371866031876710010201000020301772003720037111002110910101000010000640216221996910000102003820038200382003820038
10024200371500372199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000640216221996910000102003820038200382003820038

Test 4: Latency 1->3

Code:

  sha512su1 v0.2d, v1.2d, v0.2d
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0304181e1f3f4e51inst 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)9fa6a7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715010001996993725101001001000010010000500707984020018200372003718638318745101002001000020030000200372003711102011009910010010000100000071021611199670100001002003820038200382003820038
1020420037149000061993725101001001000010010000500707984020018200372003718638318745101002001000020030000200372003711102011009910010010000100000371011611199670100001002003820038200382003820038
1020420037150000061993725101001001000010010000500707984020018200372003718638318745101002001000020030000200372003711102011009910010010000100001071011611199670100001002003820038200382003820038
1020420037150000061993725101001001000010010000500707984120018200372003718638318745101002001000020030000200372003711102011009910010010000100007294071011611199670100001002003820038200382003820038
1020420037149000061993725101001001000010010000500707984120018200372003718638318745101002001000020030000200372003711102011009910010010000100000071011611199670100001002003820038200382003820038
1020420037150000061993725101001001000010010000500707984020018200372003718638318745101002001000020030000200372003711102011009910010010000100000071011611199670100001002003820038200382003820038
1020420037150000061993725101001001000010010000500707984020018200372003718638318745101002001000020030000200372003711102011009910010010000100000071011611199670100001002003820038200382003820038
102042003715000001249937251010010010000120100005007079840200182003720037186383187451010020010000200300002003720037111020110099100100100001000027371011611199670100001002003820038200382003820038
1020420037150000061993725101001001000010010000500707984020018200372003718638318745101002001000020030000200372003711102011009910010010000100001071011611199670100001002003820038200382003820038
1020420037150000061993725101001001000010010000500707984020018200372003718638318745101002001000020030000200372003711102011009910010010000100000071011611199670100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03090b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000000006402162219969010000102003820038200382003820038
10024200371550000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000000006402162219969010000102003820038200382003820038
10024200371500000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000300006402162219969010000102003820038200382003820038
10024200371500000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000100006402162219969010000102003820038200382003820038
10024200371500000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010003500006402162219969010000102003820038200382003820038
10024200371500000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000000006402162219969010000102003820038200382003820038
1002420037150000000619937251001010100001010000507079841200182003720037186603187671001020100002030000200372003711100211091010100001000038090006402162219969010000102003820038200382003820038
10024200371500000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000000006402162219969010000102003820038200382003820038
10024200371500000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000000006402162219969010000102003820038200382003820038
10024200371500000006199372510010101000010100005070798412001820037200371866031876710010201000020300002003720037111002110910101000010000000006402162219969010000102003820038200382003820038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sha512su1 v0.2d, v8.2d, v9.2d
  movi v1.16b, 0
  sha512su1 v1.2d, v8.2d, v9.2d
  movi v2.16b, 0
  sha512su1 v2.2d, v8.2d, v9.2d
  movi v3.16b, 0
  sha512su1 v3.2d, v8.2d, v9.2d
  movi v4.16b, 0
  sha512su1 v4.2d, v8.2d, v9.2d
  movi v5.16b, 0
  sha512su1 v5.2d, v8.2d, v9.2d
  movi v6.16b, 0
  sha512su1 v6.2d, v8.2d, v9.2d
  movi v7.16b, 0
  sha512su1 v7.2d, v8.2d, v9.2d
  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): 1.0005

retire (01)cycle (02)0308191e1f3f51inst 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)6066696d6edispatch 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204800386000000239258010010080000100800005006400001080019800388003859964359996801002008000020024000080038800381116020110099100100160000100000010110216118003501600001008003980039800398003980039
160204800385990000714258010010080000100800005006400001080019800388003859964359996801002008000020024000080038800381116020110099100100160000100000010110116118003501600001008003980039800398003980039
160204800386000000714258010010080000100800005006400001080019800388003859964359996801002008000020024000080038800381116020110099100100160000100000010110116118003501600001008003980039800398003980039
160204800385990000714258010010080000100800005006400001080019800388003859964359996801002008000020024000080038800381116020110099100100160000100000010110116118003501600001008003980039800398003980039
16020480038600000049258010010080000100800005006400001080019800388003859964359996801002008000020024000080038800381116020110099100100160000100000010110116118003501600001008003980039800398003980039
16020480038599000049258010010080000100800005006400001080019800388003859964359996801002008000020024000080038800381116020110099100100160000100020010110216118003501600001008003980039800398003980039
16020480038600000049258010010080000100800005006400001080019800388003859964359996801002008000020024000080038800381116020110099100100160000100000010110116118003501600001008003980039800398003980039
16020480038599000049258010010080000100800005006400001080019800388003859964359996801002008000020024000080038800381116020110099100100160000100000010110116118003501600001008003980039800398003980039
16020480038599000049258010010080000100800005006400001080019800388003859964359996801002008000020024000080038800381116020110099100100160000100000010110116118003501600001008003980039800398003980039
16020480038600000049258010010080000100800005006400001080019800388003859964359996801002008000020024000080038800961116020110099100100160000100000010110116118003501600001008003980039800398003980039

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)031e3f51inst 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)5f6061696b6d6edispatch 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)9fa0a6a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600248003860005525800101080000108000050640000111080019080038800385998636001880010208000020240000800388003811160021109101016000010000010022133110164113888003501510160000108003980097800398003980039
160024800385990552580010108000010800005064000001108001908003880038599863600188001020800002024000080038800381116002110910101600001000001002213711016211611128003501510160000108003980039800398003980039
1600248003860005525800101080000108000050640000111080019080038800385998636001880010208000020240000800388003811160021109101016000010000010024168261642171068003501520160000108003980039800398003980039
1600248003860005525800101080000108000050640000111080019080038800385998636001880010208000020240000800388003811160021109101016000010000010022137151622156128003501510160000108003980039800398003980039
160024800385990552580010108000010800005064000001108001908003880038599863600188001020800002024000080038800381116002110910101600001000001002213714162114668003501520160000108003980039800398003980039
160024800386000552580010108000010800005064000011108001908003880038599863600188001020800002024000080038800381116002110910101600001000001002213714162114648003501520160000108003980039800398003980039
160024800386000720258001010800001080000506400001110800190800388003859986360018800102080000202400008003880038111600211091010160000100000100221671101621155108003501510160000108003980039800398003980039
1600248003860005525800101080000108000050640000111080019080038800385998636001880010208000020240000800388003811160021109101016000010000010022137141621156118003503010160000108003980039800398003980039
160024800385990612580010108000010800005064000011108001908003880038599863600188001020800002024000080038800381116002110910101600001000001002216818162119688003501520160000108003980039800398003980039
1600248003860005525800101080000108000050640000111080019080038800385998636001880010208000020240000800388003811160021109101016000010000010022137141622141068003501510160000108003980039800398003980039

Test 6: throughput

Count: 16

Code:

  sha512su1 v0.2d, v16.2d, v17.2d
  sha512su1 v1.2d, v16.2d, v17.2d
  sha512su1 v2.2d, v16.2d, v17.2d
  sha512su1 v3.2d, v16.2d, v17.2d
  sha512su1 v4.2d, v16.2d, v17.2d
  sha512su1 v5.2d, v16.2d, v17.2d
  sha512su1 v6.2d, v16.2d, v17.2d
  sha512su1 v7.2d, v16.2d, v17.2d
  sha512su1 v8.2d, v16.2d, v17.2d
  sha512su1 v9.2d, v16.2d, v17.2d
  sha512su1 v10.2d, v16.2d, v17.2d
  sha512su1 v11.2d, v16.2d, v17.2d
  sha512su1 v12.2d, v16.2d, v17.2d
  sha512su1 v13.2d, v16.2d, v17.2d
  sha512su1 v14.2d, v16.2d, v17.2d
  sha512su1 v15.2d, v16.2d, v17.2d
  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): 1.0002

retire (01)cycle (02)03081e1f3a3f51inst 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)72scheduler 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)9fa0a1a8acc2c5branch mispredict (cb)cdcfd5d6d9ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602041600381199000038251601001001600001001600005001280000116001916003816003813997106139992160100200160008200480024160038160038111602011009910010016000010000000111101171162001600350160000100160039160039160039160039160039
1602041600381199000038251601001001600001001600005001280000116001916003816003813997106139992160100200160008200480024160038160038111602011009910010016000010000000111101170160001600350160000100160039160039160039160039160039
1602041600381198000070251601001001600001001600005001280000116001916003816003813996403139996160100200160000200480000160038160038111602011009910010016000010000000000101311160111600350160000100160039160039160039160039160039
1602041600381199000049251601001001600001001600005001280000116001916003816003813996403139996160100200160000200480000160038160038111602011009910010016000010000000000101101160111600350160000100160039160039160039160039160039
1602041600381199000049251601001001600001001600005001280000116001916003816003813996403139996160100200160000200480000160038160038111602011009910010016000010000000000101101162111600350160000100160039160039160039160039160039
1602041600381198000049251601001001600001001600005001280000116001916003816003813996403139996160100200160000200480000160038160038111602011009910010016000010000000002101101160111600350160000100160039160039160039160039160039
1602041600381199000049251601001001600001001600005001280000116001916003816003813996403139996160100200160000200480000160038160038111602021009910010016000010000000000101101160111600350160000100160039160039160039160039160039
16020416003811990000232251601001001600001001600005001280000116001916003816003813996403139996160100200160000200480000160038160038111602011009910010016000010000000000101101160111600350160000100160039160039160039160039160039
16020416003811990000334251601001001600001001600005001280000116001916003816003813996403139996160100200160000200480000160038160038111602011009910010016000010000000010101101160111600350160000100160039160039160039160039160039
16020416003811980000135251601001001600001001600005001280000116001916003816003813999503139996160100200160000200480000160038160038111602011009910010016000010000000000101101160111600350160000100160039160039160039160039160039

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0002

retire (01)cycle (02)0304191e3f51inst 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)5f6061696b6d6edispatch stall (70)72scheduler 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)9fa8acc5branch mispredict (cb)cdcfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600241600381199100552516001010160000101600005012800001151600190160038160038139986031400181600102016000020480000160038160038111600211091010160000102000010023841145161112737160033211716000010160039160039160039160039160039
1600241600381199000782516001010160000101600005012800001151600190160038160038139986031400181600102016000020480000160086160038111600211091010160000100000010023851139161113237160033211716000010160039160039160039160039160039
1600241600381199100782516001010160000101600005012800001151600190160038160038139986031400181600102016000020480000160038160038111600221091010160000100000010023851134161112237160033211716000010160039160039160039160039160039
1600251600381199100782516001010160000101600005012800001151600190160038160038139986031400181600102016000020480000160038160038111600211091010160000100000010023851137161112440160033211716000010160039160039160039160039160085
16002416003811991007432516001010160000101600005012800001151600190160038160038139986031400181600102016000020480000160038160038111600211091010160000100000010023851141161113931160033211716000010160087160039160039160039160039
1600241600381199100782516001010160000101600005012800001151600190160038160038139986031400181600102016000020480000160038160038111600211091010160000101000010023851138161112539160033211716000010160039160039160039160039160039
16002416003811991009522516001010160000101600005012800001151600190160038160038139986331400181600102016004420480000160038160038111600211091010160000100000010023851139161114040160033211716000010160039160039160039160039160039
1600241600381199100782516001010160000101600005012800001151600190160038160038139986031400181600102016000020480000160038160038111600211091010160000100000010023851133161123837160033211716000010160039160039160039160039160039
1600241600381199100782516001010160000101600005012800001151600190160038160038139986031400181600102016000020480000160038160038111600211091010160000100000010023852138163214028160033213316000010160039160039160039160039160233
1600241600381199137897844160058101600001016000050128000011516001901600381600381399860314001816001020160000204800001600381600381116002110910101600001003000100361152139161114040160255211716000010160039160039160039160039160039