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, 2D)

Test 1: uops

Code:

  saddl v0.2d, v0.2s, 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
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037166116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  saddl v0.2d, v0.2s, 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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101160119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150961196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150661196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101401119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001001470640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100810640216221978510000102003820038200382003820038
100242003715000106119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500001514719687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010060640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100930646216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  saddl v0.2d, v1.2s, 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010001657101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000847101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e3f4e51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150008791968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006403162219785210000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100029006402162219785010000102003820038200382003820038
10024200371500010519687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100029006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
1002420037150001241968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010021006402162219785010000102003820038200382003820038
1002420037150003421968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
1002420037150002101968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
1002420037150001261968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
1002420037150101051968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  saddl v0.2d, v8.2s, v9.2s
  saddl v1.2d, v8.2s, v9.2s
  saddl v2.2d, v8.2s, v9.2s
  saddl v3.2d, v8.2s, v9.2s
  saddl v4.2d, v8.2s, v9.2s
  saddl v5.2d, v8.2s, v9.2s
  saddl v6.2d, v8.2s, v9.2s
  saddl v7.2d, v8.2s, 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)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)9fa7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420047150018725801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051103162120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500123825801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815064025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381504814525801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010002051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161220035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392008820039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a0b3f51inst 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)9fa8c5branch mispredict (cb)cfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000104258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050204164432003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050205163442003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050204163442003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050203164442003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050204163342003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050205163432003580000102003920039200392003920039
80024200381500060258001010800001080000506400000200192003820038999431001880010208000020160000200382003811800211091010800001000050204163452003580000102003920039200392003920039
80024200381560039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050204163442003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050204163442003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050204163442003580000102003920039200392003920039