Apple M1 Microarchitecture Research by Dougall Johnson

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

FACGE (scalar, D)

Test 1: uops

Code:

  facge d0, d0, d1
  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
10042037158416872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371515616872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371534516872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110001389116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110003073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110009073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  facge d0, d0, d1
  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)03193f4e51inst 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)9fa8c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150038219687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715008419687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150067519687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042008515006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119855100001002003820038200382003820038
1020420037150021619687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150125119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150094319687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150091319687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119855100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002008620038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e3f4e51inst 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
1002420037150000105196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150000172196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001060640216221978510000102003820038200382003820038
1002420037150000231196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150000187196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001030640216221978510000102003820038200382003820038
1002420037150000210196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  facge d0, d1, d0
  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)03080918191e1f3a3f4e51inst 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)9fa0a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000008219687251010010010000100100005002847680020018200372003718429061874110100200100082002001620037200371110201100991001001000010000000011171701600198010100001002003820038200382003820038
1020420037150000000014519687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
102042003714900000006119687251010010010000100100005002847680120018200372003718422031874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
1020420037150000000012419687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
102042003715000000008219687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
1020420037150000000021019687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000210006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820079200382003820038
10024200371500000061196872510010101000010100005028476800200542003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003721100211091010100001000010006402162219785010000102003820038200382003820038
100242003715000012061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371490000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476800200182003720037184483187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000061196872510010111000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000010006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476800200182003720037184443187671047120100002020000200372003711100211091010100001000000006402163319785010000102003820038200382003820038
100242003715010000726196872510010101000010100005028476800200182003720037184443187671062220100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  facge d0, d8, d9
  facge d1, d8, d9
  facge d2, d8, d9
  facge d3, d8, d9
  facge d4, d8, d9
  facge d5, d8, d9
  facge d6, d8, d9
  facge d7, d8, d9
  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)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
8020420058150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010060511051644200350800001002003920039200392003920039
80204200381500339258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511041654200350800001002003920039200392003920039
8020420038150040458020510080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511051654200350800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511051655200350800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511051655200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000108511061655200350800001002003920039200392003920039
8020420097150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511051654200350800001002003920039200392003920039
80204200381500705258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511041655200350800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511041645200350800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511041654200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b181e3f51inst 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)9fa6a8accfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150009127258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050200316232003580000102003920039200392003920039
8002420038150000104258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050200316332003580000102003920039200392003920039
8002420038150000102258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050200350232003580000102003920039200392003920039
800242003815010039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050200316322003580000102003920039200392003920039
8002420038150000622580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502013316232003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050205216232003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050205216322003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200192003820088999631001880010208000020160000200382003811800211091010800001000050205316332003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050205316332003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050200216332003580000102003920039200392003920039