Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRDMLAH (by element, 2S)

Test 1: uops

Code:

  sqrdmlah v0.2s, v1.2s, v2.s[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)030b1e3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723008225482510001000100039831313018303730372415328951000100030003037303721100110000073116112630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220010325482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqrdmlah v0.2s, v1.2s, v2.s[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)03080b18193a3f4e51inst 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)9fa0a1a6a8a9acbranch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710131622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710121622296340100001003003830038300383003830038
102043003722500000646295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000200000710121632296340100001003003830038300383003830038
102043003722500000124295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710121642296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710121622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710121622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710121622296340100001003003830038300383003830038
10204300372250000082295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710121623296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710121632296340100001003003830038300383003830038
10204300372250000161295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710121622296340100001003003830038300383003830038

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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225021229548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
1002430037225010329548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722506129548251001012100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
1002430037225010329548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
1002430037225010629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
1002430037225059929548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
1002430037225051029548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383008530038
1002430037225014529548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316432963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
1002430037225025629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqrdmlah v0.2s, v0.2s, v1.s[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)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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372240000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000012071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265728762101002081000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296344100001003003830038300383003830038

1000 unrolls and 10 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)9fa0a6accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500007262954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722500002512954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722500001562954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722400003462954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722500004622954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722500001562954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722500007262954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqrdmlah v0.2s, v1.2s, v0.s[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)0307181e3f4e51inst 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)9fa8branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225105161295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
1020430037225003361295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500661295482510100100100001001000050042773131300183003730037282653287451025720010000200300003003730037111020110099100100100001001007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000107102162229634100001003003830038300383003830038
1020430037225001261295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
1020430037225002161295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
1020430037225001861295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007102162229634100001003003830038300383003830038

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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722406129548251002012100321010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
1002430037225044129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722536129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372253516129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
1002430037225276129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqrdmlah v0.2s, v8.2s, v9.s[1]
  movi v1.16b, 0
  sqrdmlah v1.2s, v8.2s, v9.s[1]
  movi v2.16b, 0
  sqrdmlah v2.2s, v8.2s, v9.s[1]
  movi v3.16b, 0
  sqrdmlah v3.2s, v8.2s, v9.s[1]
  movi v4.16b, 0
  sqrdmlah v4.2s, v8.2s, v9.s[1]
  movi v5.16b, 0
  sqrdmlah v5.2s, v8.2s, v9.s[1]
  movi v6.16b, 0
  sqrdmlah v6.2s, v8.2s, v9.s[1]
  movi v7.16b, 0
  sqrdmlah v7.2s, v8.2s, v9.s[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)030918191e1f3f51inst 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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042006515000000392580124100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
160204200641510000039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100020189010111116112006101600001002006520065200652006520065
1602042006415100000392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
16020420064152000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000000101111161120127141600001002022820065200652022820308
16020420224151043132176622580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
1602042006415000000392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000003010111116112006101600001002006520065200652006520065
1602042006415000000392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
1602042006415100000392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000100010111116112006101600001002006520065200652006520065
1602042006415100000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000203010111116112006101600001002006520065200652006520065
1602042006415000000392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b181e3f51inst 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)9fa0a1a6a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200701500000452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000010029311122021113620043215160000102011620047200472004720047
1600242004615000004525800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000004510033311102021110620043215160000102004720047200472004720047
16002420046150000045258001212800001280000626400001120027200462004632280012208000020240000200462004611160021109101016000010000075100333111020211101020043215160000102004720047200472004720047
16002420046150000045258001212800001280000626400001120027200462004632280012208000020240000200462004611160021109101016000010000001002931162021110620043215160000102004720047200472004720047
16002420046150000154525800121280000128000062640000212002720046200463228001220800002024000020050200501116002110910101600001000008410029311102021110620043215160000102004720047200472004720136
160024200461500000452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000010037311122021171020043215160000102004720051200472004720256
1600242004615000042452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000211002931162421110620043215160000102004720047200472004720047
160024200461500000452580012128000012800006264000011200272004620046102280012208000020240000200462004611160021109101016000010000012610029311102021110620043215160000102004720047200472004720047
160024200461500000452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000010033311102021110620047215160000102005120047200472004720051
160024200461500000452580012128000012800006264000011200272004620046322800122080000202400002004620050111600211091010160000100004010029311102041161020043215160000102004720047200472005120116

Test 6: throughput

Count: 12

Code:

  sqrdmlah v0.2s, v12.2s, v13.s[1]
  sqrdmlah v1.2s, v12.2s, v13.s[1]
  sqrdmlah v2.2s, v12.2s, v13.s[1]
  sqrdmlah v3.2s, v12.2s, v13.s[1]
  sqrdmlah v4.2s, v12.2s, v13.s[1]
  sqrdmlah v5.2s, v12.2s, v13.s[1]
  sqrdmlah v6.2s, v12.2s, v13.s[1]
  sqrdmlah v7.2s, v12.2s, v13.s[1]
  sqrdmlah v8.2s, v12.2s, v13.s[1]
  sqrdmlah v9.2s, v12.2s, v13.s[1]
  sqrdmlah v10.2s, v12.2s, v13.s[1]
  sqrdmlah v11.2s, v12.2s, v13.s[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)0318191e1f373f4e51inst 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202043030222500000410251201001001200001001200005009600000300203003930039149730314997120100200120000200360000300393003911120201100991001001200001002230007610216113003601200001003004030040300403004030040
1202043003922500000410251201001001200001001200005009600001300203003930039149730314997120100200120000200360000300393003911120201100991001001200001000000007610116113003601200001003094330040300403004030040
1202043003922500000410251201001001200001001200005009600000300203003930039149730314997120100200120000200360000300393003911120201100991001001200001000000007610116113003601200001003004030040300403004030040
1202043003922500000430251201001001200001001200005009600001300203003930039149737314997120100200120000200360000300393003911120201100991001001200001000010607610116113003601200001003004030040300403004130040
1202043003922500000410251201001001200001001200005009600000300203003930039149730314997120100200120000200360000300393003911120201100991001001200001000000007610116113003601200001003004030040300403004130040
12020430039225000014102512010010012000010012000050096000003002030039300391497303149971201002001200002003600003017830039211202011009910010012000010000560607610116113003601200001003004030040300403258230040
12020430039225000004102512010010012000010012000050096000013002030039300391497303149971201002001200002003600003003930039111202011009910010012000010000420347610116113076101200001003065430040300403175430040
12020430039225000008302512010010012000010012000050096000003002030039300391497303149971201002001200002003603183003930039111202011009910010012000010000240307610116113003601200001003004030040300403175430042
120204300392240012004102512010010012000010012000050096000003002030039300391497303149971201002001200002003600003004130039111202021009910010012000010000120307610116113003601200001003004030040300403004130040
120204300392250000061025120100100120000100120000500960000130020300393003914973031499712010020012000020036000030039300391112020110099100100120000100001009607610116113003601200001003004030040300403176130040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03071e373f4e51inst 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1200243059522500041025120013101200001012000050960000030020300393004014996315019120010201200002036000030040300391112002110910101200001020752001416141530037120000103004130040300403004130042
1200243003922400040025120046101200351012000050960000130020300393003914996315019120010201200002036000030039300391112002110910101200001030752001716151630036120000103004030040300403004030040
120024300392320004002512001410120000101200005096000013002030039300391499631501912001020120000203600003003930039111200211091010120000100102752001516151730036120000103004030040300413004030742
120024300402380004067132512004610120000101200005096000013002030039300401499631501912001020120000203600003003930039111200211091010120000100105752001716171730036120000103004130040300403004030040
120024300392250004002512001410120001101200005096000013002130039300401499631502012001020120000203600003003930039111200211091010120000102111752001716141630036120000103004030040300403004031751
1200243003922500040025120013101200001012000050960000130020300393003914996315020120010201200002036000030039300391112002110910101200001006752001316151630036120000103004030040300403004130040
12002430039225000400251200131012000010120000509600001300203003930039149963167301200102012000020360000300393004011120021109101012000010090752001316151430036120000103004030923300403004130040
12002430039225000610251200461012000010120000509600001300203003930040149963150191200102012000020360000300393003911120021109101012000010090752001416141530036120000103004030040300403004030040
12002430039225000410251200161012000010120000509900001300203003931750149963150191200102012000020360000300393003911120021109101012000010093752001316141330036120000103004030040300403004030040
12002430039225000820251200131012000010120000509600001309033004030039149963150191200102012000020360000300393004011120021109101012000010090752001416151430036120000103092330040300413004030040