Apple M1 Microarchitecture Research by Dougall Johnson

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

SMIN (vector, 4H)

Test 1: uops

Code:

  smin v0.4h, v0.4h, v1.4h
  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)033f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037158416872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371512416872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  smin v0.4h, v0.4h, v1.4h
  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)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)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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000084119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000097919687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010090007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018020037200371842231874510100202100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000097819687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000033019687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371490006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000053619687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018020037200371842231874510100204100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000104219687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010030007101161119791100001002003820038200382003820038

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)696b6d6edispatch 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)9fa6a8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968725100101010000101000050284768020018020037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382008520038
1002420037150014271968725100101010000101000050284768020018020037200371844831876710010201000020200002013120037111002110910101000010500006403163319785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018020037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102022720038200382003820038
10024200371500611968725100101010000101000050284768020018020037200371844431876710010201016320200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018020037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
10024200371490611968725100101010000101000050284768020018020037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680200180200372003718444318767100102010000202000020037200371110021109101010000100210006403163319785010000102003820038200382003820038
100242003715008751968725100101010000101000050284768020018020037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018020037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018020037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  smin v0.4h, v1.4h, v0.4h
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510100103100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001001071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001001071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000710116111979114100001002003820038200382003820038
102042003715001044196874310100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500145196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500149196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001001371011611197910100001002003820038200382003820038
10204200371500149196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000001681968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000001261968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000002531968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000001261968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844471876710164201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000005111968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  smin v0.4h, v8.4h, v9.4h
  smin v1.4h, v8.4h, v9.4h
  smin v2.4h, v8.4h, v9.4h
  smin v3.4h, v8.4h, v9.4h
  smin v4.4h, v8.4h, v9.4h
  smin v5.4h, v8.4h, v9.4h
  smin v6.4h, v8.4h, v9.4h
  smin v7.4h, v8.4h, v9.4h
  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)03091e1f3a3f51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000004025801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000511021611200350800001002003920039200392003920039
8020420038150000016625801001008000010080000500640000020019200382003899810399968010020080000200160000200382003811802011009910010080000100103511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150000051525801001008000010080000500640000120019200382003899737399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000005110116112003517800001002003920039200392003920039
8020420038150000014725801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100103511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150000012425801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100003511011611200350800001002003920039200392003920039
8020420038150000010525801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)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)9fcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000462258001010800001080000506400002001920038200389996031001880010208000020160000200382003811800211091010800001050207163520035080000102003920088200392003920039
800242003815000457258001010800001080000506400002001920038200389996031001880034208000020160000200382003811800211091010800001050205165520035080000102003920039200392003920039
800242003815000812580010108000010800005064000020019200382003810005031001880010208000020160000200382003811800211091010800001050205167520035080000102003920039200392003920039
80024200381500060258001010800001080000506400002001920038200389996031001880010208000020160000200382003811800211091010800001050205163520035080000102003920039200392003920039
800242003815000144258001010800001080000506400002001920038200389996031001880010208000020160000200382003811800211091010800001050203163520035080000102003920039200392003920039
80024200381500039258001010800001080000506400002001920038200389996731001880010208000020160000200382003811800211091010800001050205165320035080000102003920039200392003920039
80024200381500039258001010800001080000506400002001920038200389996031001880010208000020160000200382003811800211091010800001050205165320035080000102003920039200392003920039
80024200381500039258001010800001080000506400002001920038200389996031001880010208000020160000200382003811800211091010800001050203165520035080000102003920039200392003920039
80024200381500039258001010800001080000506400002001920038200389996031001880010208000020160000200872003811800211091010800001050205163520035080000102003920039200392003920039
80024200381509039258001010800001080000506400002001920038200389996031001880010208000020160000200382003811800211091010800001050205165420035080000102003920039200392003920039