Apple M1 Microarchitecture Research by Dougall Johnson

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

MLA (vector, 4S)

Test 1: uops

Code:

  mla v0.4s, v1.4s, v2.4s
  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)031e3f4e51inst 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)a8acc2c3cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230612548251000100010003983130301830373037241532895100010003000303730371110011000002073216222630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010003000303730371110011000000073216222630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010003000303730371110011000000073216222630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010003000303730371110011000000073216222630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010003000303730371110011000000073216222630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010003000303730371110011000000073216222630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010003000303730371110011000000073216222630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010003000303730371110011000000073216222630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010003000303730371110011000000073216222630100030383038303830383038
100430372378612548251000100010003983130301830373037241532895100010003000303730371110011000000073216222630100030383038303830383038

Test 2: Latency 1->1

Code:

  mla v0.4s, v1.4s, v2.4s
  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)03181e3a3f4e51inst 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)9fa8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100000710021623296340100001003003830038300383003830038
1020430037225000764295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100200710031622296340100001003003830038300383003830038
1020430037225000631295482510100100100001001000050042773131300180300373003728265328745101002041000020030000300373003711102011009910010010000100000710021622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100000710021622296340100001003003830038300383003830038
1020430037225000441295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100006710121622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
1020430037225000441295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa0a6a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640416332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372240061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300842250082295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372240061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722527617661295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722500103295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  mla v0.4s, v0.4s, v1.4s
  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)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)9fa8a9acc5cfd0d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722408229548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038
102043003722506129548361010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003008530038300383003830038
102043003722406129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038
102043003722566129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038

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)9fa0a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001001006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000306402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001020006402162229630010000103003830038300383003830038
10024300372250171295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000306402162229630010000103003830038300383003830038
1002430037225061295482510010101000012100005042773131300543003730073282877287671016020100002030000300853003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037232061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037224061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  mla v0.4s, v1.4s, v0.4s
  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)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)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)9fa0a1a6a7a8a9aaacc2c5cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000008229548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000000710011611296340100001003003830038300853003830038
1020430037225000000014929548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000000710011611296340100001003003830038300383003830038
1020430037224000000046529548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000000710011611296340100001003003830038300383003830038
102043003722500000008429548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000000710011611296340100001003003830038300383003830038
102043003722500000008429548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000000710011611296340100001003003830038300383003830038
102043003722500000008429548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000000710011611296340100001003003830038300383003830038
1020430037225000000023829548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000000710011611296340100001003003830038300383003830038
102043003722500000008429548251010010010000100100005004277313300183003730037282653287451025020010000200300003003730037111020110099100100100001000000000000710011611296340100001003003830038300383003830085
1020430037225000000014729548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000300710011610296340100001003003830038300383003830038
102043003722500000008429548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000000710011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa1a6a8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225009542954825100101010000101000050428138430018300373003728287328767100102010000203003630037300371110021109101010000100000007033162229630010000103003830038300383003830038
1002430037225003692954825100101010000101000050428138430018300373003728287328767100102010000223000030037300371110021109101010000100020006402162229630010000103003830038300383003830038
1002430037225004762954825100101010000101000050427867030018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630210000103003830038300383003830038
10024300372250023729548251001010100001010000504277313300183003730037282871128767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250124462954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722501216629548102100101010000101014850427731330018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225001452954825100101010000101000050427731330018300373003728287328767100102010000203000030037301331110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225003802954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225008422954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250123472954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  mla v0.4s, v8.4s, v9.4s
  movi v1.16b, 0
  mla v1.4s, v8.4s, v9.4s
  movi v2.16b, 0
  mla v2.4s, v8.4s, v9.4s
  movi v3.16b, 0
  mla v3.4s, v8.4s, v9.4s
  movi v4.16b, 0
  mla v4.4s, v8.4s, v9.4s
  movi v5.16b, 0
  mla v5.4s, v8.4s, v9.4s
  movi v6.16b, 0
  mla v6.4s, v8.4s, v9.4s
  movi v7.16b, 0
  mla v7.4s, v8.4s, v9.4s
  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)03071e3f51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420091150001042580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
16020420064150005202580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
1602042006415000392580100100800001258000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
1602042006415100392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001003001011111611200611600001002006520065200652006520065
1602042006415000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
160204200641510012392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
16020420064150004362580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
160204200641500152102580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001004901011111611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010045001011111611200611600001002006520065200652006520065
1602042006415000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001001001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030407090a0b191e1f3a3f51inst 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)5f6061696d6e74scheduler 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)9fa8acc2cfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200771500000000011102780012128000012800006264000011520034200532005303228001220800002024000020053200531116002110910101600001000010040811142271111736200502211160000102005420054200542005420054
160024200531501011000011062780012128000012800006264000010520034200532005303228001220800002024000020053200531116002110910101600001000010040841118271112832200502211160000102005420054200542005420054
160024200531501010000001362780012128000012800006264000011520034200532005303228001220800002024000020053200531116002110910101600001000010045841117271112834200502211160000102005420054200542005420054
160024200531501111000011062780012128000012800006264000011520034200532005303228001220801242024000020053200531116002110910101600001000010053841129271112438200502211160000102005420054200542005420054
160024200531501010000001062780012128000012800006264000011520034200532005303228001220800002024000020053200531116002110910101600001000010038841125271112625200502211160000102005420054200542005420054
160024200531510101000011062780012128000012800006264000011520034200532005303228001220800002024000020053200531116002110910101600001000010050841126271111732200502211160000102005420054200542005420054
160024200531501111000011152780012128000012800006264000011520034200532005303228001220800002024000020053200531116002110910101600001000010051841125271111834200502211160000102005420054200542005420054
160024200531501110000001062780012128000012800006264000010520034200532005303228001220800002024000020053200531116002110910101600001000010050811126271112039200502211160000102005420054200542005420054
16002420053150111100000942780012128000012800006264000011520034200532005303228001220800002024000020053200531116002110910101600001000010050341126271111532200502211160000102005420054200542005420054
160024200531501111009017592780012128000012800006264000011520034200532005303228001220800002024000020053200531116002110910101600001000010040811121271112633200502211160000102005420054200542005420054

Test 6: throughput

Count: 16

Code:

  mla v0.4s, v16.4s, v17.4s
  mla v1.4s, v16.4s, v17.4s
  mla v2.4s, v16.4s, v17.4s
  mla v3.4s, v16.4s, v17.4s
  mla v4.4s, v16.4s, v17.4s
  mla v5.4s, v16.4s, v17.4s
  mla v6.4s, v16.4s, v17.4s
  mla v7.4s, v16.4s, v17.4s
  mla v8.4s, v16.4s, v17.4s
  mla v9.4s, v16.4s, v17.4s
  mla v10.4s, v16.4s, v17.4s
  mla v11.4s, v16.4s, v17.4s
  mla v12.4s, v16.4s, v17.4s
  mla v13.4s, v16.4s, v17.4s
  mla v14.4s, v16.4s, v17.4s
  mla v15.4s, v16.4s, v17.4s
  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)030a1e373f51inst 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)5f60696d6edispatch 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)9fa8accfd0d2icache miss (d3)d5d6d9dbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044004830000062251601171001600001001600005001280000004002040048400391997303199971601002001600002004800004004840039111602011009910010016000010000101100001160012400360001600001004004940049400404004040040
1602044003930000041251601001001600001001600005002398999004002940039400391997303200061601002001600002004800004003940048111602011009910010016000010000101100001160012400360001600001004004040040400404004040040
1602044003930000041251601001001600171001600005001280000004002040039400391997303200061601002001600002004800004003940039111602011009910010016000010000101100001160011400360001600001004004940040400404004940087
1602044004830000050251601001001600001001600005001280000004002940049400401997303199971601002001600002004800004004840039111602011009910010016000010000101100001160012400360001600001004004040049400494004040040
1602044003930000071251601001001600001001600005001280000004002040039400481997303199971601002001600002004800004004040039111602011009910010016000010000101100001160013400360001600001004004040040400404004040040
1602044003930000050251601001001600001001600005001280000004002940048400481997303199971601002001600002004800004003940039111602011009910010016000010000101100001160013400450001600001004004040040400404004040040
16020440039300001741251601001001600001001600005001280000004002040039400481997303199971601002001600002004800004003940039111602011009910010016000010000101100001160011400450001600001004004040040400404004940040
1602044003930000050251601171001600001001600005002398999004002040039400391997303199971601002001600002004800004003940039111602011009910010016000010000101100001160012400360001600001004004040040400404004940040
16020440039300001750251601171001600001001600005001280000004002040048400401997303199971601002001600002004800004003940039111602011009910010016000010000101100001160011400450001600001004004040040400404004040040
16020440039300000146251601001001600001001600005001280000004002040039400391997303199971601002001600002004800004003940039211602011009910010016000010000101100001160012400370001600001004004040040400404004040040

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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024400792990548825160028101600001016000050128000011540020040039400391999632001916001020160000204800004003940039111600211091010160000100391002284151623215340046206160000104004040040400404004040040
16002440039300004625160010101600001016000050128000011540020040049400391999632001916001020160000204800004004940049111600211091010160000100010022114231622713440036206160000104004140040400404004040040
16002440039300017462516001010160018101600005012800001154002004004940049199963200191600102016000020480000400394003911160021109101016000010001002284141623114340046207160000104005040050400504004040040
1600244003930000462516001010160018101600005024388651154002034003940039199963200191600102016000020480000400494004911160021109101016000010001002284131623013540046207160000104004040040400404004040050
1600244003930000462516002710160017101600005012800001154002004003940039199963200191600102016000020480000400394003911160021109101016000010001002284131622814440036206160000104005040050400414004040040
16002440039301008372516001010160000101600005012800001154003004003940039199963200291600102016000020480000400494003911160021109101016000010001002284151622715540036206160000104004040040400404004140040
16002440039300017462516002710160000101600005012800001154002004003940039199963200191600102016000020480000400394003911160021109101016000010101002284131622814440036206160000104004040040400404004040041
1600244003930000462516001010160000101600005012800001154002004003940039199963200201600102016000020480000400394003911160021109101016000010001002284151622714340036206160000104005040050400504004040040
160024400393000184625160010101600001016000050128000011540020040039400391999632001916001020160000204800004003940039111600211091010160000100010022114131623114540036207160000104004940049400404004040040
1600244003930000462516001010160000101600005012800001154002004004940049199963200191600102016000020480000400404004911160021109101016000010001002284131622416440036206160000104004040040400404004040040