Apple M1 Microarchitecture Research by Dougall Johnson

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

SMLSL (vector, 4S)

Test 1: uops

Code:

  smlsl v0.4s, v1.4h, v2.4h
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e1f3f4e51inst 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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723240612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
100430372200612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
1004303723001452548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
100430372300612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
1004303723210612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
1004303723001892548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
100430372300612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
1004303723180612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
100430372200612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
100430372300612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  smlsl v0.4s, v1.4h, v2.4h
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e3a3f4e51inst 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)9fa8acc5cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240306129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100100733122423296341100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100100710121622296340100001003003830038300383003830038
102043003722501206129548251010010010000100100005004277313030018300373003728273328745101002001000020030000300373018111102011009910010010000100130710121622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
10204300372250016129548251010010010000100100005004277313130018300853013228265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
102043008422410010329548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100030710121622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100030710121622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100060710101622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100060710101622296340100001003003830038300383003830038
10204300372250006129548451010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225072629548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
1002430037225025129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
100243003722516129548251001010100001010000504277313300183003730037282873287861001020100002030000300373003711100211091010100001010640416332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001003640316332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001009640316332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001003640316332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001010640316332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001006640316332963010000103008630038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  smlsl v0.4s, v0.4h, v1.4h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8a9cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225061295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383008530038
1020430037224061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100107101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037224061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100107101161129634100001003003830038300383003830038
10204300372256661295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282657328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03070a1e3a3f4e51inst 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)9fa0a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372251102682954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000644816582963010000103003830038300383003830038
10024300372251102682954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000644101610102963010000103003830038300383003830038
1002430037225110268295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000064410165102963010000103003830038300383003830038
10024300372251102682954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000644111610102963010000103003830038300383003830038
10024300372241102682954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010410000644111611102963010000103003830038300383003830038
1002430037225110268295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000064451610102963010000103003830038300383003830038
1002430037225110268295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000064410165102963010000103003830038300383003830038
10024300372241102682954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000644111610102963010000103003830038300383003830038
1002430037225110268295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000064410165102963010000103003830038300383003830038
10024300372251102682954825100101010000101000050427731303001830037300372828732876710010201017220300003003730037111002110910101000010400000644101610102970210000103003830038300383003830038

Test 4: Latency 1->3

Code:

  smlsl v0.4s, v1.4h, v0.4h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3f4e51inst 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)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)9fa1a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101001001000010010000500427731330018300373003728272062874110100200100082003002430037300371110201100991001001000010002001117170160029647100001003003830038300383003830038
102043003722400612954825101001001000010010000500427731330018300373003728272062874110100200100082003002430037300371110201100991001001000010000001117180160029647100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728272062874110100200100082003002430037300371110201100991001001000010020000007101161129634100001003003830038300383003830038
1020430037225018612954825101001001000010010000500427731330018300373008328265032874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265032874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265032874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722503612954825101001001000010010000500427731330018300373003728265032874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265032874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265032874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265032874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b181e3f4e51inst 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250006129548251001010100001010148504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000064021622296300010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000104020964021622296300010000103003830038300383003830038
100243003722500336129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000064021622296300010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000064021622296300010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000064021622296300010000103003830038300383003830038
10024300372250008229548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000064021622296300010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000064021622296300010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000064021622296300010000103003830038300383003830038
10024300372240006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000064021622296300010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000064021622296300010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  smlsl v0.4s, v8.4h, v9.4h
  movi v1.16b, 0
  smlsl v1.4s, v8.4h, v9.4h
  movi v2.16b, 0
  smlsl v2.4s, v8.4h, v9.4h
  movi v3.16b, 0
  smlsl v3.4s, v8.4h, v9.4h
  movi v4.16b, 0
  smlsl v4.4s, v8.4h, v9.4h
  movi v5.16b, 0
  smlsl v5.4s, v8.4h, v9.4h
  movi v6.16b, 0
  smlsl v6.4s, v8.4h, v9.4h
  movi v7.16b, 0
  smlsl v7.4s, v8.4h, v9.4h
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2508

retire (01)cycle (02)0318191e3f51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420065150000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000101011121611200611600001002006520065200652006520065
16020420064150000602580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000231011111611200611600001002006520065200652006520065
16020420064151000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001002101011111611200611600001002006520065200652006520065
160204200641510001442580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
16020420064150000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
16020420064150000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000101011111611200611600001002006520065200652006520065
160204200641500005802580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000131011111611200611600001002006520065200652006520065
160204200641500001672580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
16020420064151000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
16020420064150000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000101011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2507

retire (01)cycle (02)030b1e1f3f51inst 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)9fa0a8accdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200691510009982780012128000012800006264000011200322005120051322800122080000202400002005120051111600211091010160000100000100313111225211911200482201160000102005220052200522005220061
16002420051150000452780012128000012800006264000011200322005120051322800122080000202400002005120060111600211091010160000100800100353129252111010200482401160000102006120052200612005220052
1600242006015006015429800121280000128000062640000112003220051200513228001220800002024000020051200511116002110910101600001002300100333111125211913200482201160000102005220052200522005220052
16002420051151000109827800121280000128000062640000112003220051200513228001220800002024000020051200511116002110910101600001001001003231111252111212200572201160000102005220052200612006120052
160024200511500004527800121280000128000062640000112003220060200513228001220800002024000020051200511116002110910101600001000001003131110342111212200482201160000102005220052200522005220052
1600242005115000011192780012128000012800006264000011200412005120051322800122080000202400002005120051111600211091010160000100000100353111025411811200482401160000102005220052200522005220052
1600242005115006045258001212800001280000626400001120032200512005132280012208000020240000200512005111160021109101016000010000010036622934422910200572402160000102006120061200612006120052
1600242006015000051298001212800001280000626400000120041200602006032280012208000020240000200602005111160021109101016000010000010037622834412810200572402160000102006120061200612006120061
160024200601500009712980012128009612800006264000001200412006220060322800122080000202400002006020060111600211091010160000100190010035622934422811200572402160000102006120061200612006120061
1600242006015000017629800121280000128000062640000012003220060200513228001220800002024000020060200601116002110910101600001000011003732210344121112200572402160000102006120061200612005220052

Test 6: throughput

Count: 16

Code:

  smlsl v0.4s, v16.4h, v17.4h
  smlsl v1.4s, v16.4h, v17.4h
  smlsl v2.4s, v16.4h, v17.4h
  smlsl v3.4s, v16.4h, v17.4h
  smlsl v4.4s, v16.4h, v17.4h
  smlsl v5.4s, v16.4h, v17.4h
  smlsl v6.4s, v16.4h, v17.4h
  smlsl v7.4s, v16.4h, v17.4h
  smlsl v8.4s, v16.4h, v17.4h
  smlsl v9.4s, v16.4h, v17.4h
  smlsl v10.4s, v16.4h, v17.4h
  smlsl v11.4s, v16.4h, v17.4h
  smlsl v12.4s, v16.4h, v17.4h
  smlsl v13.4s, v16.4h, v17.4h
  smlsl v14.4s, v16.4h, v17.4h
  smlsl v15.4s, v16.4h, v17.4h
  movi v16.16b, 17
  movi v17.16b, 18

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

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)6061696d6edispatch 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)9fa1a6a8a9accfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020440058300000150251601001001600001001600005001617680004002940048400481997332000616010020016000020048000040048400391116020110099100100160000100000001011000116114004501600001004004940049400404004040040
160204400393000543017335251601001001600001001600005001280000104002940049400391997332002416010020016000020048156340039400481116020110099100100160000100000001011000116114004901600001004004940040400494004040049
160204400482990001742251601171001603361001600005001319997104002940039400481997331999716010020016000020048000040039400481116020110099100100160000100000031011000116114004901600001004004040049400404004940049
16020440048300000041251601171001600171001600005001280000004002040039400481997332000616010020016000020048000040039400481116020110099100100160000100000001011000116114003601600001004005040049400494004040049
1602044004830001201750251601171001600001001600005001280000104002940039400481997325200061601002001600002004800004003940048111602011009910010016000010000005410110001161140045251600001004004040049400494004040049
160204400483000001750251601171001600171001600005002398999104002040039400481997331999716010020016000020048000040048400391116020110099100100160000100000001011000116114003601600001004004940040400404004940040
16020440039299000083251601171001600171001600005001319998104002940048400391997331999716010020016000020048128740039400481116020110099100100160000100000001011000116114004501600001004004940040400494004040049
160204400483000210183251601001001600001001600005002399055004002940048401151997331999716010020016000020048000040169403051116020110099100100160000100000001013200116114004501600001004004940040400494027340040
160204400393000120050251601171001600171001600005001280000104002040039400481997332000616010020016000020048000040039402201116020110099100100160000100000001011000116114004501600001004004040049400404004940040
160204400393000001741251601171001600171001600005001280000004002140039400481997331999716010020016000020048000040039400481116020110099100100160000100001016881011000116114004901600001004004940040400494004040049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03071e373f51inst 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)9fa8a9cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024400573000017141251600271016000010160000502399082115400294003940048199963200281600102016000020480000400484003911160021109101016000010000100228118162115340045155160000104004940049400404004940049
160024400393000017141251600271016001710160000501280000115400204004840039199963200281600102016000020480000400484003911160021109101016000010000100228315162115340036155160000104004940049400494004940049
160024400483000017206251600101016000010160000502398999115400204003940048199963200281600102016000020480000400484003911160021109101016000010000100228415162115540045155160000104004940049400494004040040
16002440039300000264251600271016001710160000502398999115400294004840048199963200191600102016000020480000400484004811160021109101016000010000100228518162113540036155160000104004040049400404004940040
160024400483000017162251600271016001710160000501280000115400294004840039199963200191600102016000020480000400404003911160021109101016000010000100228413162115340045155160000104004940040400494004940049
160024400483000017197251600101016000010160000502398999115400294004840039199963200291600102016000020480000400394004811160021109101016000010000100228415162115540036155160000104004940049400404004940040
16002440039300000820251600271016001710160000502398999115400294004840039199963200281601242016000020480000400394004811160021109101016000010000100228413162113540046155160000104004940050400494004040049
16002440048299000206251600271016000010160000501280000115400294004840048199963200281600102016000020480000400484004811160021109101016000010000100228415162115340036155160000104004940040400494004040049
160024400483000017208251600111016001710160000502398999115400294004840048199963200281600102016000020480000400484003911160021109101016000010000100228513162113540036315160000104004040049400404004940040
160024400483000017143251600271016001710160000502398999115400294004840048199963200281600102016000020480000400484003911160021109101016000010000100228413162115540045156160000104004040049400494004940049