Apple M1 Microarchitecture Research by Dougall Johnson

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

SADDW (vector, 2D)

Test 1: uops

Code:

  saddw v0.2d, v0.2d, v1.2s
  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
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073316221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110005073216821787100020382038203820382038
100420371548016872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110001073216221787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110001073216221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037166116872510001000100026618802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  saddw v0.2d, v0.2d, v1.2s
  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)03181e3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000671011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018320037200371842231874510100200100002002000020037200371110201100991001001000010020371011611197910100001002003820038200382003820038
1020420037150008419687441012210010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010001071011611197910100001002003820038200382008620038
1020420037150096119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500063119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000003951968725100101010000101000050284768012001820037201801844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
1002420037150000001206281968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010600006403163319785010000102003820038200382003820038
100242003715000000004201968725100101010000101000050284768002001820037200371844431876710010221000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
10024200371500000000611968725100101010000101030450284768012001820037200371844431876710010201000020200002003720037111002110910101000010001006403163319785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
10024200371500000003523561968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010003019486403163319785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  saddw v0.2d, v1.2d, v0.2s
  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)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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371560000000126196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000471011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e1f3f4e51inst 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)9fa1a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000006403162219785010000102003820038200382003820038
10024200371500003791968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
10024200371500630611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150030611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000006402162219785010000102003820085200382003820038
100242003715000010131968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
10024200371500007291968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
10024200371500007561968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000199006402162219785010000102003820038200382003820038
10024200371500009341968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  saddw v0.2d, v8.2d, v9.2s
  saddw v1.2d, v8.2d, v9.2s
  saddw v2.2d, v8.2d, v9.2s
  saddw v3.2d, v8.2d, v9.2s
  saddw v4.2d, v8.2d, v9.2s
  saddw v5.2d, v8.2d, v9.2s
  saddw v6.2d, v8.2d, v9.2s
  saddw v7.2d, v8.2d, v9.2s
  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)030b1e3f51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042010815003061258010010080000119800005426400002001920088200389973399968010020080000200160000200382003811802011009910010080000100051262161120035800001002003920039200392003920039
802042003815010402580100100800001008000050064000020059200382003899818100218010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
80204200381500040258010010080000100801085006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100351101161120035800001002003920039200392003920039

1000 unrolls and 10 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)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)9fa8c2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715002202580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005020151016642003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000502015616532003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631004580010208000020160000200382003811800211091010800001000502015516352003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000502012316562003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000502015616562003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000502012616652003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000502013316642003580000102003920039200392003920039
80024200381500298258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000502012416552003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000502015616352003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000502012416472003580000102003920039200392003920039