Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRDMLSH (vector, 4H)

Test 1: uops

Code:

  sqrdmlsh v0.4h, v1.4h, v2.4h
  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)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)a1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722061254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
1004303723061254825100010001000398313301830373037241532895100010003000303730371110011000010073116112630100030383038303830383038
1004307323061254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
1004303722061254825100010001000398313301830373037241532895100011613000308430371110011000000073116112630100030383038303830383038
1004303722061254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037230708254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
1004303722361254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
1004303723061254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
1004303723061254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
1004303723961254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqrdmlsh v0.4h, v1.4h, v2.4h
  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)03191e3a3f4e51inst 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)9fa0a1a8acc2cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000739021622296340100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000710021622296340100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000710021622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000710021622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100002000710021622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100001000710021622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000710121622296340100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000710131622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000710121622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042786700300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000710121622296340100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240007232954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000203000030178300371110021109101010000102036404162229630010000103003830038300383003830038
100243003722410127472954825100101010000101029850427731330018300373003728287328767100102010000203000030037300371110021109101010000100206402162229630010000103003830038300383008530038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250001032954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250006312954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100106402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001004936402162229630010000103003830038300383003830226
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100106402163229630110000103003830038300383003830038
10024300372240006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001005106402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqrdmlsh v0.4h, v0.4h, v1.4h
  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)03181e1f3a3f4e51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372240000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372240000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011610296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003008530038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100010371011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100010071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e1f3f4e51inst 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)9fa1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224090612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006403162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103022830038300383003830038
1002430037224000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103008130038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103013230038300383003830038

Test 4: Latency 1->3

Code:

  sqrdmlsh v0.4h, v1.4h, v0.4h
  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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020430037225351612954825101001001000010010149500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427778103001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954825100101010000101000050427731313001830037300372828703287671001020100002030000300373003711100211091010100001001836402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287032876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287032878510010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287032876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722406129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287032876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722406129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010106402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287032876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqrdmlsh v0.4h, v8.4h, v9.4h
  movi v1.16b, 0
  sqrdmlsh v1.4h, v8.4h, v9.4h
  movi v2.16b, 0
  sqrdmlsh v2.4h, v8.4h, v9.4h
  movi v3.16b, 0
  sqrdmlsh v3.4h, v8.4h, v9.4h
  movi v4.16b, 0
  sqrdmlsh v4.4h, v8.4h, v9.4h
  movi v5.16b, 0
  sqrdmlsh v5.4h, v8.4h, v9.4h
  movi v6.16b, 0
  sqrdmlsh v6.4h, v8.4h, v9.4h
  movi v7.16b, 0
  sqrdmlsh v7.4h, v8.4h, v9.4h
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042009115011032602258010010080000100800005006408400200452006420064322801002008000020024000020064200641116020110099100100160000100031013511611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500062258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111612200611600001002006520065200652006520065
1602042006415000125258010010080000100800005006400000200452006420133322801002008000020024000020064200641116020110099100100160000100001011111621200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111612200611600001002006520308200652006520065
160204200641510039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100031011111621200611600001002006520065200652006520065
1602042006415000128258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111622200611600001002006520065200652006520065
160204200641510039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400001200452013220064322801002008000020024000020064200641116020110099100100160000100001011111621200611600001002006520282201482006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)033a3f51inst 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)5f6061696d6e74scheduler 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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200581500512580012128000012800006264000011520027200462004603228001220800002024000020046200461116002110910101600001010100298216202117420043215880160000102004720047200472004720047
160024200501500682580012128000012800006264000011520027200462004603858001220800002024000020046200461116002110910101600001006100298316202116520043215800160000102004720047200472004720047
160024200461501452580012128000012800006264000011520027200462004603228001220800002024000020046200461116002110910101600001000100278414202114320043215670160000102004720047200472004720047
1600242004615004525800121280000128000062640000115200272004620046032280012208000020240000200462004611160021109101016000010051100268414202114320043215670160000102004720047200472004720047
1600242004615004525800121280000128000062640000115200312004620046032280012208010420240000200462004611160021109101016000010390100288414202117720043215670160000102004720047200472005120051
160024200461500452580012128000012800006264000011520027200462004603228001220800002024000020046200461116002110910101600001000100308516202116420043215800160000102004720047200472005620047
160024200461500452580012128000012800006264000011520027200462004603228001220800002024000020046200461116002110910101600001000100278513202114320043215800160000102004720047200472004720047
160024200461510452580012128000012800006264000011520027200462004603228001220800002024000020046200461116002110910101600001000100338524204116620043215800160000102004720047200472004720047
160024200461500452580012128000012800006264000011520027200462004603228001220800002024000020046200461116002110910101600001000100278516202113620043215800160000102004720047200472004720047
1600242004615004525800121280000128000062640000115200272004620046034480012208000020240000200462004611160021109101016000010063100298516202116420043215670160000102004720048200472004720047

Test 6: throughput

Count: 16

Code:

  sqrdmlsh v0.4h, v16.4h, v17.4h
  sqrdmlsh v1.4h, v16.4h, v17.4h
  sqrdmlsh v2.4h, v16.4h, v17.4h
  sqrdmlsh v3.4h, v16.4h, v17.4h
  sqrdmlsh v4.4h, v16.4h, v17.4h
  sqrdmlsh v5.4h, v16.4h, v17.4h
  sqrdmlsh v6.4h, v16.4h, v17.4h
  sqrdmlsh v7.4h, v16.4h, v17.4h
  sqrdmlsh v8.4h, v16.4h, v17.4h
  sqrdmlsh v9.4h, v16.4h, v17.4h
  sqrdmlsh v10.4h, v16.4h, v17.4h
  sqrdmlsh v11.4h, v16.4h, v17.4h
  sqrdmlsh v12.4h, v16.4h, v17.4h
  sqrdmlsh v13.4h, v16.4h, v17.4h
  sqrdmlsh v14.4h, v16.4h, v17.4h
  sqrdmlsh v15.4h, v16.4h, v17.4h
  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)03080b18191e1f373f4e51inst 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)9fa0a1a6a7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044006030000000005102516010110016000010016000050012800001400524003940039199733199981601002001600002004800004003940048111602011009910010016000010000000010110316224003701600001004004040041400404004040040
1602044003930000000014102516010010016000010016000050012800001400214004840039199733199971601002001600002004800004003940039111602011009910010016000010000000010110216224003601600001004004040040400504005040040
160204400493000000001510761601011001600171001600005002399027140020400494003919973320007160100200160000200480000400394003911160201100991001001600001000431144681031681095440501241600001004075240599406474062940726
160204407103020011912008801038202122016130012716118812016123062519905391400674049440684201214920290161737200161144200483327406464056171160201100991001001600001006020050151029210134394040181600001004066440632406434069940595
160204405963021010101323880964102516011710016000010016000050023989991400304003940039199733199971601002001600002004800004004940039111602011009910010016000010000000010110216224004601600001004004940040400494004040040
1602044003930000000004102516010010016001710016000050012800001400524003940049199733199981601002001600002004800004003940049111602011009910010016000010000000010110216224003601600001004004940040400494004040050
160204400493000000001732602516010110016000010016000050023989991400294003940039199733200061601002001600002004800004004940049111602011009910010016000010000001310110216224003601600001004004040072400494004040049
16020440049300000000344102516011710016000010016000050023990271400304003940039199733199971601002001600002004800004003940048111602011009910010016000010000000010110216224003701600001004004040050400404007240050
1602044003930000000004102516010010016001710016000050053871881400204004940039199733200061601002001600002004800004007140048111602011009910010016000010000000010110216224006801600001004005040040400404004040040
16020440039299000060174102516011710016001710016000050024388651400204003940048199733199971601002001600002004800004004840039111602011009910010016000010000000010110216224004501600001004004040050400414004040050

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03040b18191e1f373a3f4e51inst 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)9fa8c5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244006030000000000136025160010101600171016000050128000011400204003940039199963200281600102016000020480000400394003911160021109101016000010001002231181621147400450155160000104004040040400404004040040
160024400393000000000046025160027101600181016000050128000011400204004840048199963200191600102016000020480000400394003911160021109101016000010001002231181621167400460155160000104004040040400404004040040
1600244003930000000000460251600101016000010160000502398999114002040039400491999632001916001020160000204800004003940039111600211091010160000100010022311816211119400360155160000104005040040400404004940040
160024400393000000000052025160010101600001016000050128000011400204003940049199963200191600102016000020480000400394003911160021109101016000010001002231181621177400360155160000104004040040400404004040040
160024400402990000000046025160028101600011016000050128000011400204004940039199963200191600102016000020480000400394003911160021109101016000010001002231181621156400360155160000104004040040400404004040040
160024400392990000000046025160010101600001016000050128000011400204003940039199963200191600102016000020480000400394003911160021109101016000010001002231191621166400360155160000104004040040400404004040040
160024400393000000000046025160010101600001016000050128000011400204003940039199963200191600102016000020480000400484004811160021109101016000010001002231171621144400360155160000104004040040400404004040050
1600244003930000000010711025160010101600001016000050128000011400204003940039199963200191600102016000020480000400394003911160021109101016000010101002231161621188400360155160000104004040040400404004040040
1600244004829900000018055025160027101600001016000050239899911400204003940039199963200191600102016000020480000400394003911160021109101016000010001002231151621168400460155160000104004040040400404004040040
160024400392990000001046025160028101600001016000050243886511400204003940039199963200191600102016000020480000400484004811160021109101016000010001002431141621156400360155160000104005040040400404004040049