Apple M1 Microarchitecture Research by Dougall Johnson

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

SADDL (vector, 4S)

Test 1: uops

Code:

  saddl v0.4s, 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)031e3f4e51inst 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
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371636116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  saddl v0.4s, 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)03080b18191e1f3f4e51inst 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)9fa0a1a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000001260611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000120611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000270611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000270611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000030611968725101001091000010010152500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611198550100001002003820038200382003820038
102042003715000002730611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000300611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3a3f4e51inst 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
10024200371501200611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150000611968725100101210012101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820083
10024200371501200611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371491800611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371502700611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150000611968725100101010000121000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371501500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10025200371502700611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  saddl v0.4s, 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)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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100010071011611197910100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500048365196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000070196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000018071011611197910100001002003820038200382003820038
1020420037150003061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000073311611198230100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500015166196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500022261196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

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)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
1002420037150061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150061196872510022101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371502461196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037156061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371502461196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371502161196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  saddl v0.4s, v8.4h, v9.4h
  saddl v1.4s, v8.4h, v9.4h
  saddl v2.4s, v8.4h, v9.4h
  saddl v3.4s, v8.4h, v9.4h
  saddl v4.4s, v8.4h, v9.4h
  saddl v5.4s, v8.4h, v9.4h
  saddl v6.4s, v8.4h, v9.4h
  saddl v7.4s, 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)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)696b6d6edispatch 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)9fa8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200381501223025801001008000010080000500640000200190200382003899730399968010020080000200160000200382003811802011009910010080000100000051102161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200190200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200190200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200190200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200190200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200190200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200190200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200190200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150304025801001008000010080000500640000200190200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200190200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200471500051039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020216322003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020316232003580000102003920039200392003920039
80024200381500027039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020316242003580000102003920039200392003920039
8002420038157000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020216322003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020216232003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020316322003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020316342003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020316332003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020216332003580000102003920039200392003920039
80024200381500000704258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020316232003580000102003920039200392003920039