Apple M1 Microarchitecture Research by Dougall Johnson

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

UMLAL2 (by element, 4S)

Test 1: uops

Code:

  umlal2 v0.4s, v1.8h, v2.h[1]
  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)03080b18191e1f3f4e51inst 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)a0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043084230011135885022548441008100811493983130301830853085241532906114911603489308430842110011000240002763273116112630100030383038303830383038
10043037230000007132548431008100011493996700305430843083242072913114911633486308430842110011000000002793281140112692100030853085308630843086
10043084230011141887162548451008100811493983130305430843085241782914114611633417308430842110011000402021998094116112682100030843084308530853085
10043084230111132887092539451008100811493996700305430843084242372914105711683504308530842110011000240020073116112630100030383038303830383038
1004303723000000822548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
100430372200000010325482510001000100039831313018303730372415122910114911683483308530842110011000002022720493124112666100030853086308630853085
100430852300111321327092539441008100811493996700305430843085243182915114911683489308530842110011000220022765094124112662100030853084308530863086
10043084231101144886922539441008100811493996700305430843120241932898114911683480308330842110011000000002820194124112696100030853038303830383038
1004303723000000612548251000100010003983130301830373037241532895100010003000303730371110011000000400073116112630100030383038303830383038
10043037230000001452548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  umlal2 v0.4s, v1.8h, v2.h[1]
  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)030b191e1f3a3f4e51inst 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)9fa6a8acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225001200124295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710021622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710021622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
102043003722400000980295482510100100100001001000050042773130300183003730037282653287451010020010000200305223003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250012176061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000712121622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038

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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000105930640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010100640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  umlal2 v0.4s, v0.8h, v1.h[1]
  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)030818191e1f3a3f4e51inst 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
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071021622296340100001003003830085300853008630038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
10204300372240000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)9fa1a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300852250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  umlal2 v0.4s, v1.8h, v0.h[1]
  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)0307080b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000001253295482510125125100001251000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000003103071011611296970100001003003830038300383003830038
10204300372250100000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000000822954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710116112963425100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611297080100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372259061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001046006403163329630010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006403163329630010000103003830038300383003830038
1002530037225006129548251001010100001010000504277313030018300373003728290328767100102010000203000030037300371110021109101010000100006403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100055566403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000101006403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006403163329630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001010156403163329630010000103003830038300383003830038
10024300372241206129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000101006403163329630010000103003830038300383003830038
100243003722501086129548251001010100001010149504278670030018300373003728287328767100102010000203000030037300371110021109101010000100006403163329630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  umlal2 v0.4s, v8.8h, v9.h[1]
  movi v1.16b, 0
  umlal2 v1.4s, v8.8h, v9.h[1]
  movi v2.16b, 0
  umlal2 v2.4s, v8.8h, v9.h[1]
  movi v3.16b, 0
  umlal2 v3.4s, v8.8h, v9.h[1]
  movi v4.16b, 0
  umlal2 v4.4s, v8.8h, v9.h[1]
  movi v5.16b, 0
  umlal2 v5.4s, v8.8h, v9.h[1]
  movi v6.16b, 0
  umlal2 v6.4s, v8.8h, v9.h[1]
  movi v7.16b, 0
  umlal2 v7.4s, v8.8h, v9.h[1]
  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)03191e3f51inst 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)5f60696d6escheduler 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200651500039258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
160204200641510039258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
160204200641510039258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000361011221622200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400000120045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
160204200641510039258010010080000100800005006400000120045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
1602042006415000229258010010080000100800005006400001120045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
160204200641510039258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)033f51inst 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)9fa0a8accdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200871504527800121280000128000062640000111020032200532005332280012208000020240000200512005111160021109101016000010000010040134120252111721200502201160000102005220052200542005420052
16002420053150373227800121280000128000062640000111020032200512005132280012208000020240000200532005111160021109101016000010000010040136116251112219200482201160000102005420054200542005220052
160024200531504527800121280000128000062640000111020032200532005132280012208000020240000200532005111160021109101016000010010010043135116251111818200482211160000102006320061200632006320061
160024200601504527800121280000128000062640000111020034200512005132280012208000020240000200512005111160021109101016000010000010043135119362121818200482401160000102005420054200542005220054
160024200511504529800121280000128000062640000111020032200512005132280012208000020240000200512005111160021109101016000010000010042135121342111921200502201160000102005420052200522005220054
160024200511504527800121280000128000062640000111020034200512005132280012208000020240000200512005111160021109101016000010000010040135119252112317200482201160000102006120061200522005220054
160024200531504529800121280000128000062640000011020043200622005332280012208000020240000200602006011160021109101016000010000010041166117344222117200572212160000102005220052200522005220052
160024200511504527800121280000128000062640000111020032200532006232280012208000020240000200512021911160021109101016000010019010045166218252121920200482212160000102005220052200632005420052
160024200531504527800121280000128000062640000011020034200532005332280012208000020240000200532006011160021109101016000010000010040135218252112319200502201160000102005220054200542005420063
160024200511504529800121280000128000062640000111020043200602005132280012208000020240000200532005111160021109101016000010000110046167219343222218200572401160000102006120061200612006320052

Test 6: throughput

Count: 12

Code:

  umlal2 v0.4s, v12.8h, v13.h[1]
  umlal2 v1.4s, v12.8h, v13.h[1]
  umlal2 v2.4s, v12.8h, v13.h[1]
  umlal2 v3.4s, v12.8h, v13.h[1]
  umlal2 v4.4s, v12.8h, v13.h[1]
  umlal2 v5.4s, v12.8h, v13.h[1]
  umlal2 v6.4s, v12.8h, v13.h[1]
  umlal2 v7.4s, v12.8h, v13.h[1]
  umlal2 v8.4s, v12.8h, v13.h[1]
  umlal2 v9.4s, v12.8h, v13.h[1]
  umlal2 v10.4s, v12.8h, v13.h[1]
  umlal2 v11.4s, v12.8h, v13.h[1]
  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)030b1e373f4e51inst 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)9fa7a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12020430060225000150025120101100120017100120000500990000030020300423003914973314997120100200120000200360000300393003911120201100991001001200001000000761021622300391200001003004330040300403004030043
1202043003922500141025120101100120000100120000500990000130020300393004214973314997120100200120000200360000300393004211120201100991001001200001000000761021622300361200001003004030043300403004030040
1202043003922500044025120100100120000100120000500960000130903300393004214973315000120100200120000200360000300423003911120201100991001001200001000000761021622300391200001003004330040300403004330923
1202043003922500044025120100100120000100120000500960000030020300393003914973314997120100200120000200360000300393004211120201100991001001200001000000761021622300361200001003004030043300403004330040
1202043094322500041025120100100120017100120000500990000030903300393003914973314997120100200120000200360000300393003911120201100991001001200001000000761021622300361200001003004030040300433004030040
1202043003922500041025120100100120000100120000500960000130020300393004214973314997120100200120000200360000300393004211120201100991001001200001000000761021622300361200001003004030043300403004030043
1202043003922500041025120100100120001100120000500960000030023300393003914973314997120100200120000200360000300393003911120201100991001001200001000000761021622317451200001003004030040300433004030043
1202043003922500083025120100100120000100120000500960000130020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000761021622300361200001003004030040300403004030043
12020430039225000421025120100100120000100120000500960000030020300393004214973314997120100200120000200360000300393004211120201100991001001200001000000761021622300361200001003004030040300433004030944
12020430039225000706025120101100120000100120000500990000130020300423003914973315000120100200120000200360000300423003911120201100991001001200001000000761021622300361200001003004330040300403004330040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b191e1f373f4e51inst 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)9fa8a9accfd5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12002430039225000008202512001010120000101200005096000003002030039300391499631501912001020120000203600003003930922111200211091010120000100007520201601818300360120000103004030040300403004030040
12002430039225000014002512001010120000101200005096000013002030039300391499631501912001020120000203600003003930039111200211091010120000100007520181601717300360120000103004030040300403004030040
12002430922225000014002512001010120000101200005096000003002030039300391499631501912001020120000203600003003930039111200211091010120000100007520171601813300360120000103004030040300403004030040
12002430039225000018202512001010120000101200005096000003002030039300391499631501912001020120000203600003003930039111200211091010120000100007520171601219300360120000103004030040300403004030040
12002430039225000014002512001010120000101200005096000003002030039300391499631501912001020120000203600003003930039111200211091010120000100007520181601722300360120000103004030040300403004030040
12002430039224000004002512009010120000101200005096000003002030039300391499631501912001020120000203600003003930039111200211091010120000100007520131601619300360120000103004030040300403004030040
12002430039225000004002512001010120000101200005096000013002030039300391499631501912001020120000203600003003930039111200211091010120000100007520161601616300360120000103004030040300403004030040
1200243003922500000124025120010101200001012000050428362203002030039300391499631501912001020120000203600003003930039111200211091010120000100007520161601511300360120000103004030040300403004030040
12002430039224000014002512001010120000101200005096000013002030039300391499631501912001020120000203600003003930039111200211091010120000100007520171601718300360120000103004030040300403004030040
12002430039225000004002512001010120000101200005096000003002030039300391499631501912001020120000203600003003930039111200211091010120000100007520161601716300360120000103004030040300403004030040