Apple M1 Microarchitecture Research by Dougall Johnson

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

TRN1 (vector, 4S)

Test 1: uops

Code:

  trn1 v0.4s, v0.4s, v1.4s
  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)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
10042037163611687251000100010002646802018203720371572318951000100020002037203711100110000073216111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037153611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371515611687251000100010002646802018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100004273116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  trn1 v0.4s, v0.4s, v1.4s
  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)030b3f4e51inst 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100004807101161019791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001027101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000010006403162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000536196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000010006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000020606402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003714900000001036196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000306402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000010006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  trn1 v0.4s, v1.4s, v0.4s
  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)03080b1e3f4e51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820086200382003820038
1020420037150000536196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308091e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000406402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150001261196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715010061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150000147196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150000103196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000136402162219785010000102003820038200382003820038
100242003715000989196872510010101000010100005028476801200182003720037184443187671016020100002020000200832003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000306402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  trn1 v0.4s, v8.4s, v9.4s
  trn1 v1.4s, v8.4s, v9.4s
  trn1 v2.4s, v8.4s, v9.4s
  trn1 v3.4s, v8.4s, v9.4s
  trn1 v4.4s, v8.4s, v9.4s
  trn1 v5.4s, v8.4s, v9.4s
  trn1 v6.4s, v8.4s, v9.4s
  trn1 v7.4s, v8.4s, v9.4s
  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)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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150724025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100051104164420035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100051105166520035800001002003920039200392003920039
8020420038149604025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100051104165420035800001002003920039200392003920039
8020420038150244025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100051105165420035800001002003920039200392003920039
80204200381501024025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100051105165420035800001002003920039200392003920039
8020420038150394025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100051103164520035800001002003920039200392003920039
8020420038150664025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100051105163520035800001002003920039200392003920039
8020420038150694025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100051104164420035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100051104164420035800001002003920039200392003920039
8020420038150454025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100051105165520035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304090b18191e3f51inst 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)9fa8accfitlb miss (d4)d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000000123925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050200916171420035080000102003920039200392003920039
800242003815000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001046502001716161720035080000102003920039200392003920039
800242003815000000213925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050200171691720035080000102003920039200392003920039
800242003815000000939258001010800001080000506400000200192003820038999631001880010208000020160000200382008911800211091010800001000502001716171420035080000102003920039200392003920039
8002420038150001000392580010108000010800005064000002001920038200381001031001880010208000020160000200382003811800211091010800001000502001716171720085080000102003920039200392003920039
800242003815000000039258001010800001080000506400000200192003820087999631001880010208000020160000200382003811800211091010800001000502001016171420035080000102003920039200392003920039
80024200381500000015039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000502001416171620035080000102003920039200392003920039
800242003815000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000502001716171720035080000102003920039200392003920039
8002420038150000000704258001010800001080000506400000200192003820038999631007280108208000020160000200382003811800211091010800001006502001716171720035080000102003920039200392003920039
800242003815000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000502001716171720035080000102003920039200392003920039