Apple M1 Microarchitecture Research by Dougall Johnson

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

UZP1 (vector, 8B)

Test 1: uops

Code:

  uzp1 v0.8b, v0.8b, v1.8b
  movi v0.16b, 1
  movi v1.16b, 2

(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)0307181e3f4e51inst 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)a0a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037160069241687681012100010002659630205420372037157231895115210002000203720371110011000000073216221785100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715100611687251000100010002646800201820372085157131895100010002000203720371110011000011073216211785100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715000611687251000100010002646801201820372037157231895100010002000203720371110011000000373216111787100020382038203820382038
1004203716000611687251000100010002646800201820372037157231895100010002000203720371110011000000675116111787100020382038203820382038
1004203715000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715000611687251000100010002646801201820372037157231895100010002000203720371110011000001073116111801100020382038203820382085

Test 2: Latency 1->2

Code:

  uzp1 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): 2.0037

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)5e696d6edispatch 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550000600891968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371550000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010020100071011611197910100001002003820038200382003820038
10204200371550000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715500001500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371550000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715500002400611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010002000071011611197910100001002003820038200382003820038
10204200371610000000611968725101001001000010010000500284896302001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371550000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371550000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715500005700611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000100071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03090b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037155000027006119687251001010100001010000502847680202702036920372184623318875110752211004222197820370203727110021109101010000100002001403007874896420037310000102032420323203712032320323
1002420318157117792752804187196211371008712100841411156712856787202702036420369184663218898110772411096202212220368203228110021109101010000102000021394507746748520037210000102037020321203602036820408
100242037315800435433520537519621157100891510084161106482285537820270203582037018462371888010928211115722223322036720371811002110910101000010020004595547494576319966210000102027520274202752027320275
100242032115710556814400279619643621006112100481410456602852812201982027520276184612618857107772210991202000020037200374110021109101010000100020001000506406483719967210000102027420311202722027320276
1002420272158006540200833196542510010111000012101525028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000306403163319785010000102003820038200382003820038
1002420037155000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006403163319785010000102003820038200382003820038
1002420037156000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006403163319785010000102003820038200382003820038
1002420037155000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000030006403163319785010000102003820038200382003820038
1002420037155000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006403163319785010000102003820038200382003820038
1002420037155000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006403163319785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uzp1 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): 2.0037

retire (01)cycle (02)03081e3f4e51inst 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)9fa8c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715500840196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371550061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371550061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371550061196872510100100100001001000050028476800200182003720037184227187581010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371550061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
102042003715500251196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371550061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
102042003715500103196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371550061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371560061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371550024061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006402164319785010000102003820038200382003820038
1002420037155000061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100006404163419785010000102003820038200382003820038
1002420037155000089196872510010101000010101525028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006404164419785010000102003820038200382003820038
1002420037155000061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100006404164419785010000102003820038200382003820038
10024200371550000162196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100006403162419785010000102003820038200382003820038
1002420037155000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006404164419785010000102003820038200382003820038
10024200371560000149196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006404164419785010000102003820038200382003820038
1002420037161000061196872510010101001210100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006404163419785010000102003820038200382003820038
1002420037155000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100306403164419785010000102003820038200382003820038
1002420037156000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006404162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uzp1 v0.8b, v8.8b, v9.8b
  uzp1 v1.8b, v8.8b, v9.8b
  uzp1 v2.8b, v8.8b, v9.8b
  uzp1 v3.8b, v8.8b, v9.8b
  uzp1 v4.8b, v8.8b, v9.8b
  uzp1 v5.8b, v8.8b, v9.8b
  uzp1 v6.8b, v8.8b, v9.8b
  uzp1 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): 0.2505

retire (01)cycle (02)03080b18191e1f3f51inst 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
802042003815600000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000300511041611200350800001002003920039200392003920039
802042003815500000040258010010080000100800005006400000200192003820038997339996801002008029320016038420038201902180201100991001008000010000020000511011611200350800001002003920039200392003920039
8020420038155000100402580100100800001008000050064232002001920038200389973399968010020080392200160000200382003811802011009910010080000100000340005110116112003516800001002003920039200392003920248
8020420038156000013204025801001008000010080000500640000020019200382003899733999680100200800002001600002003820240118020110099100100800001000000036500511011611200350800001002003920039200392003920039
802042003815500000040258010010080000100800005006400000200192003820038997339996801002028000020016000020038200381180202100991001008000010000010300511011611200350800001002003920039200392003920244
8020420038155000000402580100100800001008000050064000002001920191200389973399968010020080000200160000201942003811802011009910010080000100020100005110116112003510800001002003920039200392003920039
802042003815600000040258010010080000100800005006400000200192003820089997339996801002008000020016000020038201421180201100991001008000010000050000511015311200350800001002009220039200392003920039
802042003815500000264404480100100800001008000050064151202001920038200389984399968010020080000200160000200382003841802011009910010080000100000001200511011611200355800001002006320129200392003920039
8020420038155000002646102580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000540000511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000017700511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)0304090b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2cfd0icache miss (d3)d5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481550000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000005054001816017620035080000102003920039200392003920039
80024200381550000000032425800101080000118000050640000020019200982003899963100188001020800002016000020038200391180021109101080000100001051505020001716017720035080000102003920039200392003920039
80024200381550000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000005020001716017820035080000102003920039200392003920039
800242003815500000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050200017160171720035080000102003920039200392003920039
80024200381550000021003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000000502000816071320035080000102003920039200392003920039
800242003815500000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050200013160171720035080000102003920039200392003920039
800242003815600000000392580010128009510800006064000002001920038200381000531004680010208000020160194200382010311800211091010800001000000605020001716017620035080000102003920039200392003920039
80024200381560000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000005020001716017720035080000102003920039200392003920039
80024200381560000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000005020001716014620035080000102003920039200392003920039
80024200381550000024003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000030502000716081720035080000102003920039200392003920039