Apple M1 Microarchitecture Research by Dougall Johnson

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

UABAL2 (vector, 2D)

Test 1: uops

Code:

  uabal2 v0.2d, 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)03181e3f4e51inst 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)a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230061254825100010001000398313301830373037241532895100010003000303730731110011000000073116112630100030383038303830383038
10043037230061254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037220061254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037230061254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037220061254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037220061254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037220061254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
100430372301261254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037230661254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037220061254825100010001000398313301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  uabal2 v0.2d, 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)031e1f3a3f4e51inst 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)9fa6a8accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121623296340100001003003830038300383003830038
102043003722400010329548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002021000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
10204300372240006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296930100001003003830038300383003830038
10204300372240006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121632296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710103022296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000443710121622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622297060100001003003830038300383003830038

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)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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722508929548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216322963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037224186129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
100243003722536129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225216129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216322963010000103003830038300383003830038
1002430037225156129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216232963010000103003830038300383003830038
10024300372252191829548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372252761295482510010101000010100005042773131300183003730037282872328786100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  uabal2 v0.2d, 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)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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000024006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071021611296340100001003003830038300383003830038
102043003722500003306129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500001806129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500001506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000500071011611296340100001003003830038300383003830038
102043003722500002106129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000306129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500001806129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500002706129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500001506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500002407629548251010010010000102100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722442612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010100640316332963010000103003830038300383003830038
1002430037224061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
1002430037225361295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
100243003722529761295482510010101000010102985042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300853008630038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003721100211091010100001000640316332963010000103003830038300383003830038
10024300372252761295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010240640316332963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  uabal2 v0.2d, 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)9fa0a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000001236129548251010010010000100100005004277313030018300373008428265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000010112017101162129634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383018130038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250000406129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129701100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000037101161129634100001003003830038300383003830038
102043003722400000156129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100001207101162129667100001003003830038300383003830038

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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225276129548251001010100001010000504277313130022300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722496129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130022300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300653003730037282873287671001020100002030000300373003711100211091010100001000486402162229630010000103003830038300383003830038
1002430037225456129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225053629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  uabal2 v0.2d, v8.4s, v9.4s
  movi v1.16b, 0
  uabal2 v1.2d, v8.4s, v9.4s
  movi v2.16b, 0
  uabal2 v2.2d, v8.4s, v9.4s
  movi v3.16b, 0
  uabal2 v3.2d, v8.4s, v9.4s
  movi v4.16b, 0
  uabal2 v4.2d, v8.4s, v9.4s
  movi v5.16b, 0
  uabal2 v5.2d, v8.4s, v9.4s
  movi v6.16b, 0
  uabal2 v6.2d, v8.4s, v9.4s
  movi v7.16b, 0
  uabal2 v7.2d, 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)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)5f6061696b6d6e74scheduler 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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420091150039258010010080000100800005006400000102004502006420064032280100200800002002400002006420064111602011009910010016000010000101115111611200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400000002004502006420064032280100200800002002400002006420064111602011009910010016000010009101110011611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000001020045020064200640322801002008000020024000020064200641116020110099100100160000100078101115011611200611600001002006520065200652006520065
160204200641500320258012410080000124800005006400000152004502006420064032280100200800002002400002006420069111602011009910010016000010000101110011611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000001020045020064200640322801002008000020024000020064200641116020110099100100160000100084101115011611200611600001002006520065200652006520065
16020420064150123925801001008000010080000500640000000200450200642006403228010020080000200240000200642006411160201100991001001600001000141101110011611200611600001002006520065200652006520065
1602042006415103925801001008000010080000500640000000200450200642006403228010020080000200240000200642006411160201100991001001600001000120101110011611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000011020045020064200640322801002008000020024000020064200641116020110099100100160000100087101110111611200611600001002006520065200652006520065
160204200641500229258010010080000100800005006400000002004502006420064032280100200800002002400002006420064111602011009910010016000010000101110011611200611600001002006520065200652006520065
160204200641502739258010010080000100800005006400000002004502006420064032280100200800002002400002006420064111602011009910010016000010000101110011611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090a0b18191e1f3a3f51inst 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)5f60696b6d6edispatch 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)9fa0a1a7a8a9acc2cfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200521500000000000457480012128000012800006264000011200290200482004803228001220800002024000020049200491116002110910101600001000010001004431101422111212120043215160000102004720047200472004720047
16002420046150000000000045788001212800001280000626400001120027020046200460322800122080000202400002004620046111600211091010160000100002205101004231102122211202020045216160000102004920049200472004720049
160024200461500000000000458680012128000012800006264000011200270200462004603228001220800002024000020048200461116002110910101600001000031012901004431102020211202020043215160000102004720047200472004720047
160024200461500000000000457480012128000012800006264000011200270200462004603228001220800002024000020046200461116002110910101600001000000001004631202020211202020043215160000102004720047200472004720047
1600242004615100000000004512980012128000012800006264000001200270200522004803228001220800002024000020048200481116002110910101600001000024000100443110202021192020043215160000102004720051200492004720051
160024200461500000000000458680012128000012800006264000011200270200462005003228001220800002024000020048200461116002110910101600001000000001004531102024111202020045216160000102005320047200472004720049
160024200481500000000000457480012128000012800006264000011200270200462004603228001220800002024000020046200461116002110910101600001000037030100443110202021192020043215160000102005120047200472004720047
1600242004615100000000004575800121280000128000062640000112002702004620046032280012208000020240000200462004611160021109101016000010000380301004461102020211202020043215160000102004720047200472004720047
160024200461511001000000458180012128000012800006264000011200270200462004603228001220800002024000020046200461116002110910101600001000024000100443110202021192020043215160000102004720047200472004720047
160024200461500000000000457080012128000012800006264000011200270200462004603228001220800002024000020046200461116002110910101600001000018012010031311095221120920043215160000102004720047200472004720047

Test 6: throughput

Count: 16

Code:

  uabal2 v0.2d, v16.4s, v17.4s
  uabal2 v1.2d, v16.4s, v17.4s
  uabal2 v2.2d, v16.4s, v17.4s
  uabal2 v3.2d, v16.4s, v17.4s
  uabal2 v4.2d, v16.4s, v17.4s
  uabal2 v5.2d, v16.4s, v17.4s
  uabal2 v6.2d, v16.4s, v17.4s
  uabal2 v7.2d, v16.4s, v17.4s
  uabal2 v8.2d, v16.4s, v17.4s
  uabal2 v9.2d, v16.4s, v17.4s
  uabal2 v10.2d, v16.4s, v17.4s
  uabal2 v11.2d, v16.4s, v17.4s
  uabal2 v12.2d, v16.4s, v17.4s
  uabal2 v13.2d, v16.4s, v17.4s
  uabal2 v14.2d, v16.4s, v17.4s
  uabal2 v15.2d, 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)03191e1f373f51inst 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)9fa0a8acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020440061300000051251601171001600001001600005002438865040020040049400391997331999816010020016000020048000040039400391116020110099100100160000100060000101102162240036001600001004004040040400494004040040
160204400493000001841251601001001600001001600005002438865040030040039400391997331999716010020016000020048000040090400481116020110099100100160000100070000101102162240036001600001004004040050400404004040040
16020440039300000042251601171001600001001600005001280000040020040039400391997331999716010020016000020048000040039400491116020110099100100160000100060000101102162240045001600001004004040040400404005040049
1602044003930000004125160100100160000100160000500128000004002004003940039199733199971601002001600002004800004003940039111602011009910010016000010002135000101102162240036001600001004004040040400404004140040
16020440049300000041251601001001600001001600005002438865040020040039400391997331999716010020016000020048000040039400491116020110099100100160000100099000101102162240046001600001004004040050400404004040040
1602044003930000018412516011710016000010016000050024388650400300400394003919973319997160100200160000200480000400484003911160201100991001001600001000370000101102162240036001600001004004940040400404005040040
16020440039300000041251601001001600171001600005002398999040030040039400391997381999716010020016000020048000040049400391116020110099100100160000100010000101102162240046001600001004004040040400404004040040
160204400483000000412516010110016000010016000050012800000400300400394003919973319997160100200160000200480000400394003911160201100991001001600001000360000101102162240036001600001004004040050400404004040041
1602044003929900018716251601171001600001001600005002438865040020040039400491997331999716010020016000020048000040039400491116020110099100100160000100060000101102162240036001600001004004040040400404004040049
160204400393000001841251601171001600001001600005002438865040020040039400391997332000616010020016000020048000040049400391116020110099100100160000100093000101102162240036001600001004005040040400404013140040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e373a3f51inst 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)9fa6a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440058300000170562516001010160000101600005012800001104002040039400391999632001916001020160000204800004004040039111600211091010160000100191002483220162221516400450409160000104004140040400404004040040
1600244003929900017061251600101016001710160000501280000015400294003940039199963200281601222016000020480000400494003911160021109101016000010039910024112217164111516400360409160000104004940040400494004540041
1600244004930000017071125160027101600171016000050239899900040029400394003919996320019160010201600002048000040048400391116002110910101600001000010024622171622116154004602014160000104004040040400414004140050
16002440049299000008425160010101600171016000050128000000040020400484004919996320028160010201600002048000040039400481116002110910101600001002010024114110164111717400360209160000104004040040400504004040040
16002440048300000170612516001010160001101600005012800000054002040039400481999632001916001020160000204800004004840039111600211091010160000100301002484214162211610400360406160000104004040049400494004940040
160024400483000001705525160010101600171016000050131999811040029400494004819996320019160010201600002048000040039400481116002110910101600001001910024112216164211516400450406160000104005040129400404004140040
160024400492990000052251600101016001710160000501280000115400304004840039199963200201600102016000020480000400394003911160021109101016000010030100511132171642210174004502012160000104004040041400494005040040
16002440039299000005272516001010160000101600005012800000154002040039400481999632001916001020160000204800004003940039111600211091010160000100401002432110162211615400450409160000104004040090400404004040040
16002440039299000006125160010101600001016000050128000000040029400484004819996320028160010201600002048000040040400491116002110910101600001001010022831161642116164004504012160000104004940040400504004040049
1600244004929900017062251600111016000010160000502398999010400204004940049199963200291600102016000020480000400394004011160021109101016000010030100241142181642215154003604012160000104004040049400404004040040