Apple M1 Microarchitecture Research by Dougall Johnson

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

ORR (vector, immediate, 8H)

Test 1: uops

Code:

  orr v0.8h, #1
  movi v0.16b, 1

(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)0309181e3f4e51inst 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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715000342168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500099168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715000187168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203716000505168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715000195168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371600082168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500084168625100010001000264521120182037203715713189510001000100020372037111001100010073116111786100020382038203820382038
100420371500082168625100010001000264521120182037203715713189510001000100020372037111001100010073116111786100020382038203820382038
1004203716000143168625100010001000264521120182037203715713189510001000100020372037111001100060073116111786100020382038203820382038
100420371600061168625100010001000264521120182037203715713189510001000100020372037111001100050073116111820100020382038203820382038

Test 2: Latency 1->1

Code:

  orr v0.8h, #1
  movi v0.16b, 1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e1f3f4e51inst 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)9fa1a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500006119686251010010010000100100005002847521020018200372003718428718741101002001000820010008200372003711102011009910010010000100000611171801600198000100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018200372003718428618741101002001000820010008200372003711102011009910010010000100000011171701600198000100001002003820038200382003820038
1020420037150042006119686251010010010000100100005002847521020018200372003718428618740101002001000820010008200372003711102011009910010010000100000011171701600198000100001002003820038200382003820038
10204200851500006119686251010010010000100100005002847521020018200372003718428618740101002001000820010008200372003711102011009910010010000100000011171701600198000100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018200372003718428618741101002001000820010008200372008611102011009910010010000100000011172222422197870100001002003820038200382003820038
102042003715001621089719686251011410210000100100005002849896020018200372003718409618733101002001000020010000200372003711102011009910010010000100000011172222422197870100001002003820038200382003820038
10204200371500009719686251010010010000100100005002847521020018200372003718409618733101002001000020010000200372003711102011009910010010000100050011172222422197870100001002003820038200382003820038
10204200371500009719686251010010010000100100005172847521020018200372003718428718740101002001000820010008200372003711102011009910010010000100000011171701600198010100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018200372003718428718741101002001000820010008200372003711102011009910010010000100010011171801600198010100001002003820038200382003820038
102042003715001206119686251010010010000100100005002847521020018200372003718428618740101002001000820010008200372003711102011009910010010000100000011171801600198010100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308181e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100150640316331978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010380640316331978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
10024200371500006119686251001010100001010000502847521020018200372003718455318767100102010000201000020037200371110021109101010000100156640316331978610000102003820038200382003820038
1002420037150000103196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
1002420037150002461196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010072640316331978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001009640316331978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  movi v0.16b, 0
  orr v0.8h, #1
  movi v1.16b, 0
  orr v1.8h, #1
  movi v2.16b, 0
  orr v2.8h, #1
  movi v3.16b, 0
  orr v3.8h, #1
  movi v4.16b, 0
  orr v4.8h, #1
  movi v5.16b, 0
  orr v5.8h, #1
  movi v6.16b, 0
  orr v6.8h, #1
  movi v7.16b, 0
  orr v7.8h, #1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)696d6escheduler 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
16020420090151000382580100100800001008000050064000020044200632006332180100200800002008000020063200631116020110099100100160000100061011111611200601600001002006420064200642006420064
160204200631500003825801001008000010080000500640000200442006320063321801002008000020080000200632006311160201100991001001600001000991011111611200601600001002006420064200642006420064
160204200631500150382580100100800001008000050064000020044200632006332180228200800002008000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064
1602042006315000080258010010080000100800005006400002004420063200633218010020080000200800002006320063111602011009910010016000010001171011111611200601600001002006420064200642006420064
160204200631500360382580100100800001008000050064000020044200632006332180100200800002008000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064
16020420063150000382580214100800001008000050064000020044200632006332180100200800002008000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064
16020420063150000382580100100800001008000050064000020044200632006332180100200800002008000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064
16020420063150000382580100100800001008000050064000020044200632006332180100200800002008000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064
16020420063150000382580100100800001008000050064000020044200632006332180100200800002008000020063200631116020110099100100160000100091011111611200601600001002006420064200642006420064
160204200631500210382580100100800001008000050064000020044200632006332180100200800002008000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a0b18191e3a3f51inst 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)9fa0a1a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420068151220007201572580012128000012800006264000011020026200452004532180012208000020800002004520045111600211091010160000100011928100478212724211232420042215160000102004620050200462004620046
1600242004515000000604425800121280000128000062640000115200302004920049321800122080000208000020049200491116002110910101600001000131004811312124422232220046230160000102004620046200462004620046
1600242004515101000018662580012128000012800006264000011520026200452004532180012208000020800002004520045111600211091010160000100412398100468212520211232420132215160000102004620046200502004620046
1600242004515011000017102580012128000012800006264000011520026200452004532180012208000020800002004520045111600211091010160000100000100468212320211222320042215160000102004620046200462004620046
160024200451502200000442580012128000012800006264000011520026200452004532180012208000020800002004520045111600211091010160000100000100488212320211232220042215160000102004620046200502004820046
160024200451501000000502580012128000012800006264000011520026200452004532180012208000020800002004520045111600211091010160000100003100468212220211172520042215160000102004620046200462004620046
160024200451503200000502580012128000012800006264000011520026200452004532180012208000020800002004520045111600211091010160000100020100468212320211232520042215160000102004620046200462004620046
160024200451501200000562580012128000012800006264000011520026200452004532180012208000020800002004520045111600211091010160000100020100488212220211212220042215160000102004620046200462004620046
160024200451500100000502580012128000012800006264000011520026200452004532180012208000020800002004520045111600211091010160000100000100468212320211232320042215160000102004620046200462004620046
160024200451502100000502580012128000012800006264000011520026200452004532180012208000020800002004520045111600211091010160000100000100478212420211232420042215160000102004620046200462004620046

Test 4: throughput

Count: 16

Code:

  orr v0.8h, #1
  orr v1.8h, #1
  orr v2.8h, #1
  orr v3.8h, #1
  orr v4.8h, #1
  orr v5.8h, #1
  orr v6.8h, #1
  orr v7.8h, #1
  orr v8.8h, #1
  orr v9.8h, #1
  orr v10.8h, #1
  orr v11.8h, #1
  orr v12.8h, #1
  orr v13.8h, #1
  orr v14.8h, #1
  orr v15.8h, #1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

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)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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020440057300040251601001001600001001600005001120016140019400384003819973319996160100200160000200160000400384008711160201100991001001600001000001011011611400351600001004003940039400394003940039
16020440038301040441602191001600001001600005001120016040019400384003819973319996160100200160000200160000400384003811160201100991001001600001000001011011611400351600001004003940039400394003940039
16020440038299040251601001001600001001600005001120016040019400384003819973319996160100200160000200160000400384003811160201100991001001600001000001011011611400351600001004003940039400394003940039
16020440038300040251601001001600001001600005001120016040019400384003819973319996160100200160000200160000400384003811160201100991001001600001000001011011611400351600001004003940039400394003940039
16020440038299040251601001001600001001600005001120016140019400384003819973319996160100200160000200160000400384003811160201100991001001600001000001011011611400351600001004003940039400394003940039
16020440038300040511601001001600001001600005001120016140019400384003819973319996160100200160000200160000400384003811160201100991001001600001000001011011611400351600001004003940039400394003940039
16020440038300040251601001001600001001600005001120016040019400384003819973319996160100200160000200160000400384003811160201100991001001600001000001011011611400351600001004003940039400394003940039
1602044003830041440251601001001600001001600005001120016140019400384003819973319996160100200160000200160000400384003811160201100991001001600001000001011011611400351600001004003940039400394003940039
16020440038300040251601001001600001001600005001120016140019400384003819973319996160100200160000200160000400384003811160201100991001001600001000001011011611400351600001004003940039400394003940039
160204400383000705251601001001600001001600005001120016040019400384003819973319996160100200160000200160000400384003811160201100991001001600001000001011011611400351600001004003940039400394003940039

1000 unrolls and 10 iterations

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

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)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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244004830004525160010101600001016000050112001601040019400384003819996320018160010201600002016000040038400381116002110910101600001006100243113916211141640035208160000104003940039400394003940039
1600244003830005125160010101600001016000050112001610040019400384003819996320018160010201600002016000040038400381116002110910101600001000100228411916211131140035208160000104003940039400394003940039
1600244003830004525160010101600001016000050112001610540019400384003819996320018160010201600002016000040038400381116002110910101600001009100223111316211131740035208160000104003940039400394003940039
1600244003830004525160010101600001016000050112001611040019400384003819996320018160010201600002016000040038400381116002110910101600001000100228111316211181440035208160000104003940039400394003940039
1600244003830007825160010101600001016000050112001610540019400384003819996320018160010201600002016000040038400381116002110910101600001000100228411316211141240035208160000104003940039400394003940039
1600244003830005525160010101600001016000050112001611040019400384003819996320018160010201600002016000040038400381116002110910101600001000100223511316211131140035208160000104003940039400394003940039
1600244003830004525160010101600001016000050112001610540019400384003819996320018160010201600002016000040038400381116002110910101600001000100228411316211201540035208160000104003940039400394003940039
1600244003830004525160010101600001016000050112001611540019400384003819996320018160010201600002016000040038400381116002110910101600001000100228411116211131240035208160000104003940039400394003940039
1600244003830004525160010101600001016000050112001611540019400384008819996320018160010201600002016000040038400381116002110910101600001000100223411316211111340035208160000104003940039400394003940039
1600244003830004525160010101600001016000050112001611540019400384003819996320018160010201600002016000040038400381116002110910101600001000100228411616211112040035208160000104003940039400394003940039