Apple M1 Microarchitecture Research by Dougall Johnson

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

UABA (vector, 8B)

Test 1: uops

Code:

  uaba v0.8b, v1.8b, v2.8b
  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)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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722061254825100010001000398313301830373037241532895100010003000303730371110011000010873116112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230612539251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100030003037303711100110000973116112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  uaba v0.8b, v1.8b, v2.8b
  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)0308191e1f3a3f4e51inst 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)9fa0a8a9acc2branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000001294295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071202162329634100001003003830038300383003830038
1020430037224000009992954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000390071012162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071012162229634100001003003830038300383003830038
102043003722400120061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071012162229634100001003003830038300383003830038
102043003722500000975295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000125750071012162229634100001003003830038300383003830038
1020430037225000001100295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071012162329634100001003003830038300383003830038
1020430037225000001027295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071012162229634100001003003830038300383003830038
102043003722500000126295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010001000071012162229634100001003003830038300383003830038
102043003722500000941295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071012162229634100001003003830038300383003830038
1020430037225000001311295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000030071012162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080918191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500009001262954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006404162329630010000103003830038300383003830038
100243003722500000001032954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000090013222954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000011682954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000013082954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006402163229630010000103003830038300383003830038
1002430037225000000011112954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006403162229630010000103003830038300383003830038
1002430037225000000012602954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000011682954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000011792954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000010132954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  uaba v0.8b, v0.8b, v1.8b
  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)030b1e3a3f4e51inst 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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500035929548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225036025029548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500019129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722400036029530251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250008429548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225001262529548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722400039329548251010010010000100100005004277313130018300373003728268328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500014929548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722400010329548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa1cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250014929548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
1002430037225098429548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000102640316332963010000103003830038300383003830038
10024300372250012429548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
1002430037226006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
100243003722406113329548251001010100071010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300853003830038
1002430037225008429548251001010100001010000504277313030018300373003728287328767101602010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372250077429548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
1002430037225008429548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
1002430037225008429548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  uaba v0.8b, v1.8b, v0.8b
  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)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)9fa0a1a7a8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722515061295482510100100100001001000050042773133001830037300372826532874510100202100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10205300372246061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000017101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500726295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030408090b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9aaacc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000000082295482510034121000010111926642773133001830130300372828716287861046020100002030000300373003711100211091010100001000000000006405164529630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000001000006404165529630010000103003830038300383003830038
100243003722400000000072629548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006404165529630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006405164529630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006405165429630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006405165429630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313300183003730037282873287671015920100002030000300373003711100211091010100001000000000006405165429630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006405165529630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006405164529630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000016405165529630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  uaba v0.8b, v8.8b, v9.8b
  movi v1.16b, 0
  uaba v1.8b, v8.8b, v9.8b
  movi v2.16b, 0
  uaba v2.8b, v8.8b, v9.8b
  movi v3.16b, 0
  uaba v3.8b, v8.8b, v9.8b
  movi v4.16b, 0
  uaba v4.8b, v8.8b, v9.8b
  movi v5.16b, 0
  uaba v5.8b, v8.8b, v9.8b
  movi v6.16b, 0
  uaba v6.8b, v8.8b, v9.8b
  movi v7.16b, 0
  uaba v7.8b, v8.8b, v9.8b
  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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042009115001322580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
160204200641510392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
160204200641510392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
1602042006415101672580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
160204200641510602580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
16020420064150010402580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a1e3a3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f6061696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200541513100572580012128000012800006264000011020027200462004632280012208000020240000200462004611160021109101016000010000100498311920221191820043215160000102004720047200472004720047
1600242004615012005125800121280000128000062640000115200272004620046322800122080000202400002004620046111600211091010160000100045100438411720211161720043215160000102004720047201612004720047
16002420046150111440516580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010003100438411120211141220043215160000102004720047200472004720047
160024200461500000452580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010000100448421920211191920043230160000102004720047200472004720047
160024200461503300512580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010000100498411720211182020043215160000102004720047200472004720047
160024200461501000452580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010200100488411820211212120043215160000102004720047200472004720047
1600242004615011005725800121280000128000062640000115200272004620046102280012208000020240000200462005011160021109101016000010000100508411720211181820043215160000102004720047200472004720047
160024200461501100512580012128000012800006264000011520027200462011532280012208000020240000200462004611160021109101016000010000100498411820211181820043215160000102004720047200472004720047
160024200461500000512580012128000012800006264000011520027200462004632280012208000020240000201802004611160021109101016000010000100508412120211212020043215160000102004720047200472004720047
160024200461510100562580012128000012800006264000011520027200462004632280012208000020240000200462005011160021109101016000010000100478411620211171420043215160000102004720047200472004720047

Test 6: throughput

Count: 16

Code:

  uaba v0.8b, v16.8b, v17.8b
  uaba v1.8b, v16.8b, v17.8b
  uaba v2.8b, v16.8b, v17.8b
  uaba v3.8b, v16.8b, v17.8b
  uaba v4.8b, v16.8b, v17.8b
  uaba v5.8b, v16.8b, v17.8b
  uaba v6.8b, v16.8b, v17.8b
  uaba v7.8b, v16.8b, v17.8b
  uaba v8.8b, v16.8b, v17.8b
  uaba v9.8b, v16.8b, v17.8b
  uaba v10.8b, v16.8b, v17.8b
  uaba v11.8b, v16.8b, v17.8b
  uaba v12.8b, v16.8b, v17.8b
  uaba v13.8b, v16.8b, v17.8b
  uaba v14.8b, v16.8b, v17.8b
  uaba v15.8b, v16.8b, v17.8b
  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)030b18191e1f373f4e51inst 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)9fa8a9acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044007230000000092025160100100160000100160000500239899940020400494004819973320007160100200160000200480000400394003911160201100991001001600001000000010110116224003601600001004004940040400504004940050
16020440071300000000412525160100100160001100160000500239902740030400484003919973320006160100200160000200480000400394004911160201100991001001600001000000010110116114003601600001004004040072400404007240072
1602044004830000000141025160161100160000100160000500239902740052400394003919973319998160100200160000200480000400394004911160201100991001001600001000000010110116114004501600001004004040040400404004940040
16020440039300000001741025160117100160000100160000500239899940020400494004819973319997160100200160000200480000400394003911160201100991001001600001000000010110116104003601600001004004040040400504004040050
1602044004830000000041025160100100160000100160000500128000040021400394003919973319997160100200160000200480000400394003911160201100991001001600001000000010110116114003601600001004004040050400494004040040
16020440039300000001741025160100100160001100160000500128000040029400394004019973319997160100200160000200480000400394003911160201100991001001600001000000010110116114003601600001004005040040400404005040040
1602044004930000000051025160100100160000100160000500128000040020400394003919973319997160100200160000200480000400394003911160201100991001001600001000000010110116114003601600001004004940040400504004940040
16020440048300000000738025160100100160000100160000500239899940030400394004919973319997160100200160000200480000400484007111160201100991001001600001000000010110116114003601600001004004040122400404004040040
1602044007130000002081751025160274120160135113160169500128000040131400394004919973320006160100200160000200480000400394003911160201100991001001600001000047000101101161140045171600001004004940040400504004940040
1602044004930000000041025160100100160000100160000500538718840029400494004819973319997160100200160000200480000400494003911160201100991001001600001000000010110116114003601600001004004040050400494004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03041e373f51inst 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)9fa8accdcfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024400403000017100251600271016000010160000502398999115400204003940039199963200281600102016000020480000400404003911160021109101016000010000100261162128163223321400454118160000104004940049400404004940040
16002440039300100462516001010160000101600005012800001154002940039400401999632002916001020160000204800004003940048111600211091010160000100001002383203416211353640045209160000104004940040400404004940049
16002440039300000682516001110160000101600005023990821154002140040400391999632001916001020160000204800004004040039111600211091010160000100001002284102716211332140036206160000104005040049400404004140040
16002440039300000552516002710160000101600005012800001154002940048400391999632002816001020160000204800004004940049111600211091010160000100001002384103116211362040045209160000104005040041400404004140041
160024400403000017562516001010160000101600005013199981154002140049400481999632002016001020160000204800004004940040111600211091010160000100001002284103516211363640046209160000104004940040400494004040049
16002440048299000762516001110160001101600005012800001154003040039400401999632001916001020160000204800004004840039111600211091010160000100001002285103516211283440046207160000104004140040400414004040041
1600244004030000172452516001010160000101600005023990551154003040048400481999632001916001020160000204800004004040039111600211091010160000100001002385103316211363540045209160000104004940040400494004940049
160024400483000017462516001110160001101600005012800001154002140040400391999632001916001020160000204800004004840048111600211091010160000100001002285105316211353240045207160000104005040049400494004940049
160024400483000017472516002710160017101600005023990551154002040048400481999632001916001020160000204800004003940039111600211091010160000100001002285103316211372140045206160000104004140040400414004040041
160024400403000017462516002710160017101600005023990551154002140039400491999632001916001020160000204800004003940048111600211091010160000100001002285103516211353540036209160000104004940050400494004940040