Apple M1 Microarchitecture Research by Dougall Johnson

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

UADDL2 (vector, 8H)

Test 1: uops

Code:

  uaddl2 v0.8h, 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)0308090b18191e1f3a3f4e51inst 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)a0a1a6a7a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500000000611687251000100010002646800201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
100420371500000000611687251000100010002646800201820372037157231895100010002000203720371110011000000010094116111787100020382038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020862038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uaddl2 v0.8h, 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)031e3a3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500082196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000107196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000371011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010026371011611197910100001002003820038200382003820038
102042003715000300196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715001611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000710116111979120100001002003820038200382003820038
102042003715000254196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000208196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000212196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197914100001002003820038200382003820038
102042003715000170196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150001302196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100106402164419787010000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100006402162219787010000102003820038200382003820038
1002420037150088318196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100006402162219849010000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100006402162219787010000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100006402162219787210000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100006402162219787010000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100006402162219787010000102003820038200382003820038
100242003715000191196872510010101000010100006028476801200182003720037184440318767100102010000202000020037200371110021109101010000100006402162219787010000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100006402162219787010000102003820038200382003820038
100242003715000103196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100106402162419787010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uaddl2 v0.8h, 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)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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071001611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100010710116111979124100001002003820038200382003820038
1020420037150002401968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150006119687441010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000779216211989917100001002003820038200382003820038
1020420037150007261968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150001451968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000841968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150002731968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500010311968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)9fa6a8c2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715506119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000102046402162219785110000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500483719687251001010100001010000502847680020018200372003718444318767100122010000202000020037200371110021109101010000100106402162219785010000102003820038200382003820038
1002420037150026319687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150020119687251001010100001010000502847680120018200842008518448318767101622010167202000020037200831110021109101010000100006402163419823010000102003820085200382003820038
100242003715096119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100106402162219785010000102003820038200382003820038
1002420037150012419687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150014519687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100106402162219785010000102003820038200382003820038
1002420037150012419687251001010100001010000502847680020054200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715066119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uaddl2 v0.8h, v8.16b, v9.16b
  uaddl2 v1.8h, v8.16b, v9.16b
  uaddl2 v2.8h, v8.16b, v9.16b
  uaddl2 v3.8h, v8.16b, v9.16b
  uaddl2 v4.8h, v8.16b, v9.16b
  uaddl2 v5.8h, v8.16b, v9.16b
  uaddl2 v6.8h, v8.16b, v9.16b
  uaddl2 v7.8h, 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)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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9fcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099010010080000100511021611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099010010080000100511011611200350800001002003920039200892003920039
8020420038163756125801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099010010080000100511011611200350800001002003920039200392003920039
802042003815006325801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099010010080000100511011611200350800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100990100100800001005110116112003519800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099010010080000100511011611200350800001002003920039200392003920039
8020420038150051525801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099010010080000100511011611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099010010080000100511011611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099010010080000100511011611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099010010080000100511011618200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

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)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)9fa8accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715008125800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502004164220035280000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502004164220035080000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502004164220035080000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502002164220035080000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502005164220035080000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502003166220035080000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502004164220035080000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502002162420035080000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502004162420035080000102003920039200392003920039
8002420038150032425800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502004164320035080000102003920039200392003920039