Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMLAL (scalar, D)

Test 1: uops

Code:

  sqdmlal d0, s1, s2
  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)0308090b18191e1f3f4e51inst 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
10043037230000000612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037230000030612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037220000060612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037220000000612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037230000000612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
1004303723000003990612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037230000000612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
100430372300000120612548251000100010003983130301830373037241532895100010003000303730371110011000000003073116112630100030383038303830383038
10043037220000000612548251000100010003983130301830373037241532895100010003000303730371110011000000003073116112630100030383038303830383038
10043037230000000612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqdmlal d0, s1, s2
  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)03081e1f3a3f4e51inst 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)9fa0a1a8acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000063071202162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100004112071012162229634100001003003830038300813003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000340071012162229634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000330071012162329634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000033071012162229634100001003003830038300383003830038
102043003722600007882953925101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000413071012162229634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000087271012162229634100001003003830038300383003830038
1020430037225027626409432954825101001001000010010000522427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010002127471012162229634100001003003830038300383003830038
102043003722501590016629548251014610010000100100005004277313030018300853003728265328745101002001000020033477300373003711102011009910010010000100000135071012162229634100001003003830038300383013330134
102043003722502401612949425101001001000010010000500428002703001830085300372826572887011162200100002003000030037300371110201100991001001000010000436071212162229634100001003003830038300383003830038

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)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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100003530640316342963010000103003830038300383003830038
100243003722400000612954844100101010000101000050427731313001830037300372828703287671001020100002030000300373003711100211091010100001000001440640216232963010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100009120640316222963010000103003830038300383003830038
10024300372250000015629548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000630640316332963010000103003830038300383003830038
100243003722500000536295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100005300640316322963010000103003830038300383003830038
1002430037225000001038295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100003030640316332963010000103003830372302263003830038
100243008422500000726295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300841110021109101010000100003900640216322963010000103003830038300383003830038
1002430037225000007262954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000001140640316332963010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100222154640316742963010000103003830038300383003830038
10024300372250002405782954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000001020640316342963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqdmlal d0, s0, s1
  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)0308091e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240001278295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010048007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001002007101161129634100001003003830038300383003830038
102043003722400961295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430085225009131295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100071001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090b191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000010000640316222963010000103003830038300383003830230
100243003722500000061295482510010101000010101495042773133005430037300372828732876710010201000020300003003730037111002110910101000010000000300640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000000640216212963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000010001640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000020000640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000020000640216222963010000103003830038300383003830074
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000010000640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000000640216222963010000103003830038300383003830038
100243003722400000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000030000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313300183003730037282873288221001020100002030000300373003711100211091010100001044204022320640216242966810000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqdmlal d0, s1, s0
  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)0308191e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010003007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010002007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038301823003830038
1020430037224000612954825101001001000010010000594427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250425295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250124295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010216006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300543003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037224061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001010006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlal d0, s8, s9
  movi v1.16b, 0
  sqdmlal d1, s8, s9
  movi v2.16b, 0
  sqdmlal d2, s8, s9
  movi v3.16b, 0
  sqdmlal d3, s8, s9
  movi v4.16b, 0
  sqdmlal d4, s8, s9
  movi v5.16b, 0
  sqdmlal d5, s8, s9
  movi v6.16b, 0
  sqdmlal d6, s8, s9
  movi v7.16b, 0
  sqdmlal d7, s8, s9
  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)030b18191e3f51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420091151000060925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010019010112216222006101600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
16020420064150000039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100118010112216222006101600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000020045200642260532280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010060010112216222006101600001002006520065200652006520065
1602042006415100003925801001138000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010003010112216222006101600001002006520065200652006520065
1602042013315000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
16020420064150100070425801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b1e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f6061696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200721500104525800121280000128000062640000115200272004620046322800122080000202400002004620046111600211091010160000100000100418112220211191720043215160000102004720047200472004720047
16002420046150000452580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010001010041841172021115720043215160000102004720047200472004720047
16002420046150000452580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010002010041841172021117620043215160000102004720047200472004720047
16002420046150000452580012128000012800006264000011520027200462004636380012208000020240000200462004611160021109101016000010004310041841172021117720043215160000102004720047200472004720047
16002420046150000452580012128000012800006264000011520027200462004632280012208020920240000200462004611160021109101016000010001610041841172021171720043215160000102004720047200472004720047
160024200461500004525800121280000128000062640000115200272004620046385800122080000202400002004620046111600211091010160000100213100418411720211171720043215160000102004720047200472004720047
1600242004615000071025800121280000128000062640000115200272004620046322800122080000202400002004620046111600211091010160000100000100328411720211171720043215160000102004720047200472004720047
16002420046150000872580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010000010041841172021181820043215160000102004720047200472004720047
16002420046150000452580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010201010041841172021217620043215160000102004720047200472004720047
1600242004615010045258001212800001280000626400001152002720046200463228001220800002024000020046200461116002110910101600001000131003185172021171720043215160000102004720047200472004720047

Test 6: throughput

Count: 16

Code:

  sqdmlal d0, s16, s17
  sqdmlal d1, s16, s17
  sqdmlal d2, s16, s17
  sqdmlal d3, s16, s17
  sqdmlal d4, s16, s17
  sqdmlal d5, s16, s17
  sqdmlal d6, s16, s17
  sqdmlal d7, s16, s17
  sqdmlal d8, s16, s17
  sqdmlal d9, s16, s17
  sqdmlal d10, s16, s17
  sqdmlal d11, s16, s17
  sqdmlal d12, s16, s17
  sqdmlal d13, s16, s17
  sqdmlal d14, s16, s17
  sqdmlal d15, s16, s17
  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)03080b18191e373a3f51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400602990000150041251601001001600171001600005001280000040029400394003919973319997160100200160000200480000400394003911160201100991001001600001000000101101161140036251600001004004040040400404004040040
1602044003930000000004125160100100160000100160000500128000004002040039400391997332000616010020016000020048000040039401194116020110099100100160000100000010110216114003601600001004004940040400404004040040
160204400393000000541714125160100100160000100160000500128000004002040039400391997331999716010020016000020048000040039400391116020110099100100160000100042010110116114003601600001004004040049400404004040040
160204400392990000132004125160117100160017100160000500128000014002040039400391997331999716010020016000020048000040039400391116020110099100100160000100000010110116114003601600001004004040040400404004040040
1602044003929900000004125160100100160000100160000500128000004002040039400391997331999616012520016000020048000040039400391116020110099100100160000100000310110116114003601600001004004940040400404004040040
1602044004830000000004125160100100160017100160000500128000004002040039400391997332000616010020216000020048000040048400481116020110099100100160000100000010110116114003601600001004004040040400404004040040
1602044003930000000004125160117100160000100160000500128000004002040048400491997331999716010020016000020048000040048400391116020110099100100160000100000010110116114003601600001004004040040400404004040049
16020440039300000001705025160100100160000100160000500128000014002040039400391997331999716010020016000020048000040039400391116020110099100100160000100000010110116124003601600001004004040040400404004040040
1602044003929900000004125160117100160000100160000500239899904002040039400391997332000616010020016000020048000040048400391116020110099100100160000100000010110116114003601600001004004040040400404004940040
16020440039300000001704125160100100160000100160000500128000004002940039400391997331999716010020016000020048000040048400391116020110099100100160000100000010110116114003601600001004004040040400404004040049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e1f373f51inst 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)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024400503000001746251600101016000010160000501280000115400204003940039199963200191600102016000020480000400394003911160021109101016000010000100228114162115640036155160000104004040040400404004040050
1600244003930000004625160010101600001016000050131999701540020400394003919996320019160010201600002048000040049400491116002110910101600001000010024115271642269400363010160000104004040040400404004040050
1600244004930000005225160010101600001016000060128000001540020400494003919996320019160010201600002048000040039400391116002110910101600001000010024115251642264400363012160000104004040040400404004040040
160024400393000001522516001010160000101600005012800000154002040049400391999632002016001020160000204800004003940039111600211091010160000100097010024115281642264400453010160000104004140049400404004040049
1600244003930000005225160010101600001016000050128000001540084400484004819996320019160010201600002048000040049400391116002110910101600001030010024115261642266400363010160000104004040040401404004040040
16002440039299000035625160010101600181016000050128000001540020400394003919996320019160010201600002048000040048400481116002110910101600001001010024115241642288400363010160000104004040040400404004040040
1600244004930000005225160028101600001016000050243886501540020400394004919996320019160010201600002048000040039400391116002110910101600001000010024115291642264400363010160000104004040040400494004940193
1600244003930000005225160010101600001016000050128000001540029400484004819996320029160010201600002048000040039400391116002110910101600001000010024115261642258400463010160000104005040040400404004040091
1600244003930011711925760425160028101600001016000050239902701540020400394003919996320019160010201600002048000040049400481116002110910101600001000010024115261642258400363010160000104004040040400404004040040
160024400393000120052251600111016000010160000501280000015400204003940039199963200191600102016000020480000400404004811160021109101016000010000100241152816422109400363010160000104004040040400404004040040