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, 8B)

Test 1: uops

Code:

  trn2 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)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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100002073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000373116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  trn2 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)03080b191e3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000429611968725101001001000010010000500284768012001820037200371842203187451010020010000212200002003720037111020110099100100100001000037101161119791100001002003820038200382003820038
10204200371501000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119825100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842203187451058920010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000405611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000243611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371490000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b191e3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000309611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000264611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500072611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000417611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000611968725100101010012101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000363611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  trn2 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)03191e1f3f4e51inst 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)9fa6accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500001071968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000017101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715002401231968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500210611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500210611968725101001001000010010000500284768002001820037200371842203187451010020010000200203302008520037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037149000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119847100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

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)9fa0a1a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715515661968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006405166619785310000102003820038200382003820038
100242003715563141968725100101010000101000050284768002001820037200371844431876710010221000020200002003720037111002110910101000010000006407167719785010000102003820038200862003820038
100242003715034691968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006406166619785010000102003820038200382003820038
10024200371500611968725100101010000101015050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006407165719785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006407167719785010000102003820038200382003820038
100242003715004411968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006406167719785010000102003820038200382003820038
10024200371500711968725100101010000101000050284768002001820037200371844431876710010221000020200002003720037111002110910101000010000006407167719785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006405166519785010000102003820038200382003820038
1002420037150222611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006406166619785010000102003820038200382003820038
100242003715021611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006406166619785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  trn2 v0.8b, v8.8b, v9.8b
  trn2 v1.8b, v8.8b, v9.8b
  trn2 v2.8b, v8.8b, v9.8b
  trn2 v3.8b, v8.8b, v9.8b
  trn2 v4.8b, v8.8b, v9.8b
  trn2 v5.8b, v8.8b, v9.8b
  trn2 v6.8b, v8.8b, v9.8b
  trn2 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)030b18191e1f3f51inst 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)9fa0a1a2a6a8a9acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420056150000001102580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511021611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039
8020420038150000001452580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000010000511011611200350800001002003920039200392003920039
802042003815000000822580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000010000511011611200350800001002003920039200392003920039
8020420038154000006662580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03041e3a3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715003024025800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005024161615172003580000102003920039200392003920039
80024200381500024025800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005024171618172003580000102003920039200392003920039
80024200381500024025800101080000108000050640000020019320038200389996310018800102080000201600002003820038118002110910108000010005024161617102003580000102003920039200392003920039
80024200381500024025800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005024171620172003580000102003920039200392003920039
80024200381500024025800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005024151617182003580000102003920039200392003920039
80024200381500024025800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005024151618152003580000102003920039200392003920039
8002420038150028224025800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005024171617162003580000102003920039200392003920039
80024200381500024025800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005024181617172003580000102003920039200392003920039
80024200381500024025800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005024171617172003580000102003920039200392003920039
8002420038150030270525800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005024151616162003580000102003920039200392003920039