Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMGE (scalar, S)

Test 1: uops

Code:

  fcmge s0, s0, s1
  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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037151931687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037161741687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715821687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmge s0, s0, s1
  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)03090b18191e3a3f4e51inst 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
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500000210061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500000249061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001015261228476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500000198061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500000189061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038

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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010002600640216221978510000102003820038200382003820038
10024200371500000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000000821968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010005090640216221978510000102003820038200382003820038
10024200371500000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010004803640216221978510000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100010126640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fcmge s0, s1, s0
  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)0309181e3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000201007101161119791100001002003820086200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000002007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000001007101161119791100001002003820038200382003820038
1020420037150000611966525101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002008620038200382003820086
1020420037150000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000001007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000001007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842273187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000013310000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000001007101161119791100001002003820038200382003820038

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)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
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010137360640216221978510000102003820038200382003820038
10024200371509611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000103000640216221978510000102003820038200382003820038
100242003715001661968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010030640216221978510000102003820038200382003820083
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010100640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fcmge s0, s8, s9
  fcmge s1, s8, s9
  fcmge s2, s8, s9
  fcmge s3, s8, s9
  fcmge s4, s8, s9
  fcmge s5, s8, s9
  fcmge s6, s8, s9
  fcmge s7, s8, s9
  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)03081e3f51inst 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
802042006015001540258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511041611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010003511011611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002028009620016000020038200381180201100991001008000010010511011611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
80204200381500040258010010080000100800965126400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
80204200381500068258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039

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)5f60696d6edispatch 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)9fa0a8accfd2d5d6dbddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815003925800101080000108000050640000012001920038200389996031001880010208000020160000200382003811800211091010800001000050200316033200352780000102003920039200392003920039
8002420038150060258001010800001080000506400000020019200382003899960310018800102080000201600002003820038118002110910108000010003050200216033200352080000102003920039200392003920039
8002420038150015025800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001002050200316032200352080000102003920044200392003920039
8002420038150039258001010800001080000506400000120019200382003899960310018800102080000201600002003820038118002110910108000010005150200316032200352080000102003920039200392003920039
800242003815003925800101080000108000050640000012001920038200389996031001880010208000020160000200382003811800211091010800001020050200216032200352080000102003920039200392003920039
800242003815003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001000050200316023200352080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899960310018800102080000201600002003820038118002110910108000010007850200316033200352080000102003920039200392003920039
800242003815003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001000050200316033200352080000102003920039200392003920039
800242003815003925800101080000108000050640000012001920038200389996031001880010208000020160000200382003811800211091010800001000050200216023200352880000102003920039200392003920039
8002420038150022925800101080000108000050640000012001920038200389996031001880010208000020160000200382003811800211091010800001000050200216023200352080000102003920039200392003920039