Apple M1 Microarchitecture Research by Dougall Johnson

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

TBL (single register table, 16B)

Test 1: uops

Code:

  tbl v0.16b, { v0.16b }, v1.16b
  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)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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037160611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371512611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037159611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  tbl v0.16b, { v0.16b }, v1.16b
  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)030b18191e1f3f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000090611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000407101161119791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968725101001001000010010304500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010010007101161119791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000761968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001007101161119791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000107101161119791100001002003820038200382003820038
102042003715000000611966525101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000107101161119791100001002003820038200382003820038
1020420037150000001561968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715010000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080918191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000389506402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680120018200372003718444731876710010201000020200002003720037111002110910101000010000006402162219785010000102003820084200382003820038
10024200371500000008219687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
1002420037150000018886119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000000025119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000026402162219785010000102003820038200382003820229
10024200371500000301046119687251001010100001010000502847680120018200372003718444031882410164201000020200002003720037111002110910101000010201006402162219785010000102003820038200382003820038
10024200371501000006119687251001010100241010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010020006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  tbl v0.16b, { v1.16b }, v0.16b
  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)030918191e1f3f4e51inst 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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000061196872510100100100001001000050028476800200182003720037184296187411010020010008200200162003720037111020110099100100100001000101117170160019802100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184296187411010020010008200200162003720037111020110099100100100001000201117180160019801100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184297187401010020010008200200162003720037111020110099100100100001000091117180160019801100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768002001820037200371842971874110100200100082002001620037200371110201100991001001000010003301117180160019802100001002003820038200382003820038
10204200371500000061196652510100100100001001000050028476800200182003720037184223187611010020010000200200002003720037111020110099100100100001000100007101161119791100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715000000251196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000100007101161119791100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080a0b18191e1f3a3f4e51inst 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)9fa0a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037149000000002661968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010002006441016101219785010000102003820038200382003820038
1002420037150000000002661968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006441016101019785010000102003820038200382003820038
1002420037150000000002661968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006448168819785010000102003820038200382003820038
10024200371500000000026619687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100010064451651019785010000102003820038200382003820038
1002420037150000000002661968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006441016101019785010000102003820038200382003820038
100242003715000000000266196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000644121681019785010000102003820038200382003820038
1002420037150000000002661968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006441016121219785010000102003820038200382003820038
10024200371500000000027311968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006441016101019785010000102003820038200382003820038
1002420037150000000002661968725100101010048101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010001006441216121219785010000102003820038200382003820038
100242003715000000000266196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000644101651019785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  tbl v0.16b, { v8.16b }, v9.16b
  tbl v1.16b, { v8.16b }, v9.16b
  tbl v2.16b, { v8.16b }, v9.16b
  tbl v3.16b, { v8.16b }, v9.16b
  tbl v4.16b, { v8.16b }, v9.16b
  tbl v5.16b, { v8.16b }, v9.16b
  tbl v6.16b, { v8.16b }, v9.16b
  tbl v7.16b, { v8.16b }, v9.16b
  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)9fa0a1a7a8acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000900511021611200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000006025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000513411611200350800001002003920039200392003920039
802042003815000000042025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000006825801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000004025801001278000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000003000511011611200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000004000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090a0b18191e1f3f51inst 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)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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150000000003925800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000000050206165620035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000000050205165520035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000000050206167520035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000000050205167720035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000000050207166520035080000102003920039200392003920039
80024200381501000553528111914180807148055613805815564461202009802039320289100550241009880599208039020161160202922019271800211091010800001022422815251236776520075380000102029220343203442014020347
80024203441520020667955281706137805421280000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000003250727546620155080000102018820089201902003920191
80024201911510101646782648825800101080000108000072640000020019020089200389996031001880108208000020160000200382017811800211091010800001000003050205165720035080000102003920039203392039320442
80024201921610000003016525800101080000108000050640000020058020038200389996031001880010208000020160000200382003811800211091010800001000000050205166520035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000000050206167620035080000102003920039200392003920039