Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRDMLSH (scalar, S)

Test 1: uops

Code:

  sqrdmlsh s0, 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)033f4e51inst 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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372312825482510001000100039831330183037303724153289510001000300030373037111001100073116112630100030383038303830383038
10043037238225482510001000100039831330183037303724153289510001000300030373037111001100073116112630100030383038303830383038
10043037226125482510001000100039831330183037303724153289510001000300030373037111001100073116112630100030383038303830383038
10043037236125482510001000100039831330183037303724153289510001000300030373037111001100073116112630100030383038303830383038
10043037236125482510001000100039831330183037303724153289510001000300030373037111001100073116112630100030383038303830383038
10043037226125482510001000100039831330183037303724153289510001000300030373037111001100073116112630100030383038303830383038
10043037226125482510001000100039831330183037303724153289510001000300030373037111001100073116112630100030383038303830383038
10043037226125482510001000100039831330183037303724153289510001000300030373037111001100073116112630100030383038303830383038
10043037236125482510001000100039831330183037303724153289510001000300030373037111001100073116112630100030383038303830383038
10043037226125482510001000100039831330183037303724153289510001000300030373037111001100073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqrdmlsh s0, 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)0308090b18191e1f3a3f4e51inst 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)9fa0a1acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038
1020430037224000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728293328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071013163429634100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006403160222963010000103003830038300383003830038
1002430037224000000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402160222963010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402160222963010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402160222963010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402160222963010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402160222963010000103003830038300383003830038
1002430037225000000084295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402160222963010000103003830038300383003830038
10024300372250000000346295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402160222963010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403160222963010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402160222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqrdmlsh s0, 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)0318191e1f3f4e51inst 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)9fa1a6a7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000061295482510100100100001001000050042773130300183003730037282657287451010020010000200300003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
1020430037225009061295482510100100100241001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071021622296340100001003008530038300383003830038

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)9facbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295482510010101000010100005042773130300183003730037282877287671001020103272230483300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828725287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037224061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001001640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqrdmlsh s0, 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)0318191e1f3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330027061295482510100100100001001000050042773133001830037300372826532874510100200101742003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037224000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000371011611296340100001003003830038300383003830038
10204300372250412061295482510100100100001001000050042773133001830037300372826532874510100200100002043049230084300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037224000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000726295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722502405061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000726295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500210726295484510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640316222963010000103003830038300383003830038
1002430037225002461295484510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300813003830038
100243003722400061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001010640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010111000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243008422500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqrdmlsh s0, s8, s9
  movi v1.16b, 0
  sqrdmlsh s1, s8, s9
  movi v2.16b, 0
  sqrdmlsh s2, s8, s9
  movi v3.16b, 0
  sqrdmlsh s3, s8, s9
  movi v4.16b, 0
  sqrdmlsh s4, s8, s9
  movi v5.16b, 0
  sqrdmlsh s5, s8, s9
  movi v6.16b, 0
  sqrdmlsh s6, s8, s9
  movi v7.16b, 0
  sqrdmlsh s7, 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)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)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)9fa0a8accfd2d5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200651504563925801001008000010080000500640000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011101160112006101600001002006520065200652006520065
1602042006415003925801001008000010080000500640000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011101160112006101600001002006520065200652006520065
160204200641500392580100100800001008000050064000001200452006420064322801002008000020024000020064200641116020110099100100160000100001141011101160112006101600001002006520065200652006520065
16020420064150087125801001008000010080000500640000002004520064200643228010020080000200240000200642006411160201100991001001600001000031011101160112006101600001002006520065200652006520065
1602042006415003925801001008000010080000500640000002004520064200643228010020080000200240000200642006411160201100991001001600001004031011101160112006101600001002006520065200652006520065
16020420064150183925801001008000010080000500640000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011101160112006101600001002006520065200652006520065
1602042006415093925801001008000010080000500640000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011101160112006101600001002006520065200652006520065
1602042006415007425801001008000010080000500640000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011101160112006101600001002006520065200652006520065
1602042006415003925801001008000010080000500640000012004520064200643228010020080000200240000200642006411160201100991001001600001000031011101160112006101600001002006520065200652006520065
16020420064151039258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010002191011121160112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3a3f51inst 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)5f6061696b6d6escheduler 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)9facc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200621500000018005129800121280000128000062640000010200410200602006032280012208000020240000200602006011160021109101016000010001002662253422153200572402160000102006120061200612005220061
16002420060150010001526415129800121280000128000062640000010200320200602006032280012208000020240000200602006011160021109101016000010001002762243442234200572201160000102005220061200612006120052
16002420060150000009005127800121280000128000062640000010200320200602006032280012208000020240000200602006011160021109101016000010001002662243442243200572402160000102006120052200522005220061
16002420060150000003005127800121280000128000062640000110200320200602006032280012208000020240000200602005111160021109101016000010301002962252542133200572201160000102006120061200612006120061
16002420060150000000005129800121280000128000062640000010200320200602006032280012208000020240000200602006011160021109101016000010001002861233422233200482402160000102006120052200522006120061
160024200601500000012004529800121280000128000062640000010200320200602006032280012208000020240000200602006011160021109101016000010001002961243442243200572402160000102005220061200612006120061
16002420060150000000005129800121280000128000062640000110200320200602006032280012208000020240000200512006011160021109101016000010001003062242542244200572402160000102005220061200612005220052
160024200601500000030005129800121280000128000062640000010200320200602005132280012208000020240000200512005111160021109101016000010001002962242542144200572402160000102006120061200612006120052
16002420051150000006005129800121280000128000062640000010200320200602006032280012208000020240000200602006011160021109101016000010001003131233441153200572402160000102006120061200612006120061
160024200601510000060027427800121280000128000062640000110200410200602005132280012208000020240000200512005111160021109101016000010001002662243422244200572402160000102013220061200612006120061

Test 6: throughput

Count: 16

Code:

  sqrdmlsh s0, s16, s17
  sqrdmlsh s1, s16, s17
  sqrdmlsh s2, s16, s17
  sqrdmlsh s3, s16, s17
  sqrdmlsh s4, s16, s17
  sqrdmlsh s5, s16, s17
  sqrdmlsh s6, s16, s17
  sqrdmlsh s7, s16, s17
  sqrdmlsh s8, s16, s17
  sqrdmlsh s9, s16, s17
  sqrdmlsh s10, s16, s17
  sqrdmlsh s11, s16, s17
  sqrdmlsh s12, s16, s17
  sqrdmlsh s13, s16, s17
  sqrdmlsh s14, s16, s17
  sqrdmlsh s15, 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)03181e373f51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400723260603025160100100160000100160000500131999914002104003940039199733199971601002001600002004800004004040048111602011009910010016000010000110110316114003601600001004004940040400534004940040
1602044008930000175025160100100160017100160000500128000014002004004840039199733200061601002001600002004800004004840048111602011009910010016000010000010110116114004501600001004004940040400404004940049
1602044003930000152525160101100160000100160000500239899914002004004840048199733199971601002001600002004800004003940039111602011009910010016000010030010110116114003601600001004004040040400404004940049
1602044004829900175025160100100160017100160000500128000014002004003940039199733199971601002001600002004800004004840039111602011009910010016000010030010110116114003601600001004004940040400404004040049
160204400393000005025160100100160000100160000500239902714002004004840039199733199971601002001600002004800004004840039111602011009910010016000010040010110116114004501600001004004040040400534004940040
16020440039300001741251601851001600001001601045991280000140029040039400391997331999716010020016000020048000040039400481116020110099100100160000100212010110116114003601600001004004040040400404004040040
160204400483000905025160117100160000119160000500128000014002004003940048199733199981601002001600002004800004003940040111602011009910010016000010020010110116114003601600001004004940049400404004940040
160204400492990004125160100100160110100160000500239899914002004003940040199733199971601002001600002004800004003940039111602011009910010016000010020010110116114003601600001004004940049401004004940040
16020440039299001732625160100100160017100160000500128000014002904004840039199733199971601002001600002004800004004840048111602011009910010016000010010010110116114003601600001004004040040400494004940040
160204400393000004125160117100160000100160000500239899914002004003940039199733200061601002001600002004800004004840039111602011009910010016000010010010110116114004501600001004004040049400404004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e373f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f6061696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244003929900462516001010160000101600005012800001104002004003940039199963200291600102016000020480000400394003911160021109101016000010200100223126162125440036406160000104004940040400404005340040
1600244003930000462516001010160000101600005023989991104002904004040039199963200191600102016000020480000400394003911160021109101016000010000100243115164225440036206160000104004040049400404004140050
16002440040300001212516001010160000101600005024388651104002004003940039199963200191600102016000020480000400394003911160021109101016000010100100223113162113440036206160000104004040040400404004140049
1600244003930000462516002810160000101600005012800001104002104004840039199963200191600102016000020480000400484003911160021109101016000010200100223114162213540036206160000104004040040400404004140040
1600244003929960522516002810160000101600005012800001104002004003940039199963200191600102016000020480000400394003911160021109101016000010200100223124162113440087386160000104004040040400404005340040
16002440039299004625160011101600001016000050128000011040020040039400391999632001916001020160000204800004003940039111600211091010160000105760100223114162114440036206160000104004040040400404005340050
1600244003930000672516001010160000101600005012800001104002004003940039199963200191600102016000020480000400394003911160021109101016000010100100223213162215540036206160000104004040040400404004940040
160024400392990071225160028101600001016000050128000011540020040039400391999632001916001020160000204800004003940039211600211091010160000102001002282251621164400364012160000104004040040400404004140049
1600244003930000462516001010160000101600005024388651154002004003940039199963200191600102016000020480000400394003911160021109101016000010100100228214162114540036206160000104004040040400404004140040
16002440039300014625160010101600001016000050128000011540020040039400391999632001916001020160000204800004003940049111600211091010160000103301002211214162114540037206160000104004040040400404005340040