Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMGE (vector, 8H)

Test 1: uops

Code:

  fcmge v0.8h, v0.8h, v1.8h
  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
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073216111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371596116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572319011000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmge v0.8h, v0.8h, v1.8h
  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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968725101001001000010010000500284768002001820037200371842631874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715012611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002013420038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500821968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371509611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371503611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037202291842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001231000010010000500284768002001820037200371842231874510100200100002002067020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)033f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715010319687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715010319687251001010100001010000502847680200182003720037184443187671001020100002020356200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680200182003720037184443187671001022100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715029319687251001010100001010000502847680200182003720037184443187671001020100002020000200842003711100211091010100001000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fcmge v0.8h, v1.8h, v0.8h
  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)03071e3a3f4e51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500360611968725101001001000010010000500284768012001820037200371842231874510125200100002002000020037200371110201100991001001000010000000071021623197910100001002003820038200382003820038
102042003715001806119687251010010010000100100005002847680020018200372003718422318744101002001000020020000200372003711102011009910010010000100000000710216231979125100001002003820038200382003820038
1020420037150030611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071021722197910100001002003820038200382003820038
10204200371500300611968725101001001000010010000626284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
1020420037150016221031968744101001001000010010000631284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071032422197910100001002008920038200382003820086
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071031622197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
1020420037150030901031968725101001001000010010000626284768012001820037200371842231876210100200101662002000020037200371110201100991001001000010042210271021633197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874410125200100002002000020037200371110201100991001001000010000010071021622197910100001002003820038200382003820038

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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020203382013220037411002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000030600611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000001800611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371590000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000300611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000306402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219853010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fcmge v0.8h, v8.8h, v9.8h
  fcmge v1.8h, v8.8h, v9.8h
  fcmge v2.8h, v8.8h, v9.8h
  fcmge v3.8h, v8.8h, v9.8h
  fcmge v4.8h, v8.8h, v9.8h
  fcmge v5.8h, v8.8h, v9.8h
  fcmge v6.8h, v8.8h, v9.8h
  fcmge v7.8h, v8.8h, v9.8h
  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)03191e3f51inst 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
802042006015102074025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051103162220035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381500184025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000351102162220035800001002003920039200392003920039
802042003815002164025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381500184025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815004444025801001008000010080000500640000020019200382003899733999680225200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381500214025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001001051102162220035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3f51inst 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)9fa1a6a8accficache miss (d3)d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150018392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200191661720035080000102003920039200392003920039
8002420038150012392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050200171661720035080000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020061617620035080000102003920039200392003920039
8002420038150001022580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050200171617620035080000102003920039200392003920039
800242003815001539258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020071617620035080000102003920039200392003920039
800242003815001539258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020061671420035080000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020061617820035080000102003920039200392003920039
800242003815002439258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020081617820035080000102003920039200392003920039
80024200381500310072580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050200171617820035080000102003920039200392003920039
8002420038150002292580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050200716171720035080000102003920039200392003920039