Apple M1 Microarchitecture Research by Dougall Johnson

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

TRN2 (vector, 4S)

Test 1: uops

Code:

  trn2 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
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000673216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371536611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037170611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  trn2 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)03191e3f4e51inst 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
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500216119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372008411102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500072619687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371490276119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500186119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500246119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101162119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100207101161119791100001002003820038200382003820038
10204200371500276119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)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)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500048061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006404162219785010000102003820038200382003820038
1002420037150000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000726196672510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000300061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500045061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500039061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500039061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150009061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000201061196872510010101000010100005028480660200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  trn2 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)0308090b18191e1f3a3f4e51inst 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)9fa1a6a7a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000000611968725101001001000010010000500284768002001820037200371842961874110100200100082002001620037200371110201100991001001000010000000011171801600198010100001002003820038200382003820038
102042003715000000000611968725101001001000010010000500284768002001820037200371842961874110100200100082002001620037200371110201100991001001000010000000011171701600198020100001002003820038200382003820038
10204200371600000021008919687251010010010000100100005002847680020054200372003718429918741101002001000820420016200372003721102011009910010010000100000015011171701600198010100001002003820038200382003820038
102042003715000000000661968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
102042003715000000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371500000090061196872510117100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000156000071011611197910100001002003820038200382003820038
1020420037150100000007261968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
102042003715000000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
102042003715000000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
102042003715000000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000010000073211611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b181e3f4e51inst 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)9fa8acc2cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715600961196872510010101000010100005028476800002001820037200371844431876710010201000020200002003720037111002110910101000010000640002162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476800002001820037200371844431876710010201000020200002003720037111002110910101000010000640002162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476800002001820037200371844431876710010201000020200002003720037111002110910101000010000640002162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476800102001820037200371844431876710010201000020200002003720037111002110910101000010000640002162219785010000102003820038200382003820038
100242003715010061196872510010101000010100005028476800102001820037200371844431876710010201000020200002003720037111002110910101000010000640002162219785010000102003820038200382003820038
1002420037150001561196872510010101000010100005028476800102001820037200371844431876710010201000020200002003720037111002110910101000010000640002162219785010000102003820038200382003820038
1002420037150003361196872510010101000010100005028476800102001820037200371844431876710010201000020200002003720037111002110910101000010000640002162219785010000102003820038200382003820038
1002420037150007561196872510010101001210100005028476800102001820037200371844431876710010201000020200002003720037111002110910101000010000640002162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476800002001820037200371844431876710010201000020200002003720037111002110910101000010000640002482219785010000102003820038200382003820038
1002420037150004861196872510010101000010100005028476800102001820037200371844431876710010201000020200002003720037111002110910101000010000640002162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  trn2 v0.4s, v8.4s, v9.4s
  trn2 v1.4s, v8.4s, v9.4s
  trn2 v2.4s, v8.4s, v9.4s
  trn2 v3.4s, v8.4s, v9.4s
  trn2 v4.4s, v8.4s, v9.4s
  trn2 v5.4s, v8.4s, v9.4s
  trn2 v6.4s, v8.4s, v9.4s
  trn2 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)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)9facc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150244025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102161120035800001002003920039200392003920039
802042003814904025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000151101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500364325801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150023025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150394025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa8a9acc2cfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039187036392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200116112003580000102003920039200392003920039
8002420038150015394480010128000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200116112003580000102003920039200392003920039
800242003815006392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200116112003580000102003920039200392003920039
8002420038175005712580010108000010800005064000002001920038200389996310018800102080000201600002003820038218002110910108000010000050200116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200116112003580000102003920039200392003920039
800242003815006392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200116112003580000102003920039200392003920039