Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMEQ (vector, 8H)

Test 1: uops

Code:

  fcmeq 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)696d6edispatch 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
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037163611687251000100010002646802018203720371572318951000100020002037203711100110000073216231785100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073316331785100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073316331785100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715108611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371515611687251000100010002646802018203720371572318951000100020002037203711100110000373216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmeq 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)030b1e3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003714900292196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000103196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000726196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371501061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150150611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371504290611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371504560611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371504440611967625100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150120611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715090611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150005361968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715090611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000102000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fcmeq 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)0318191e3a3f4e5051inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000006119687025101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000061196872002125101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000906119687025101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011651197910100001002003820038200382003820038
10204200371500047406119687025101001001000010010000500284768002001820037200371842231874410125200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000006119687025101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150001206119687025101001001000010010000500284768002001820037200861842231874410125200100002002000020037200371110201100991001001000010000071411611197910100001002003820038200382003820038
1020420037150001206119687025101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500036606119687025101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021711197910100001002003820038200382003820038
10204200371500012061196870251010010010000100100005002847680020018200372003718422318744101252001000020020000200372003711102011009910010010000100000710116111979125100001002003820038200382003820038
1020420037150001206119687025101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500039611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500001451968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500024611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150003611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000668216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000309611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500015611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010004640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fcmeq v0.8h, v8.8h, v9.8h
  fcmeq v1.8h, v8.8h, v9.8h
  fcmeq v2.8h, v8.8h, v9.8h
  fcmeq v3.8h, v8.8h, v9.8h
  fcmeq v4.8h, v8.8h, v9.8h
  fcmeq v5.8h, v8.8h, v9.8h
  fcmeq v6.8h, v8.8h, v9.8h
  fcmeq 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)03080b18191e1f3f51inst 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)9fa7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000030511021611200350800001002003920039200392003920039
8020420038150000018040258010010080000100800005006400001200192003820038997379996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
80204200381500000210147258010010080000100800005006400001200192003820038997339996801002028000020016000020038200381180201100991001008000010000000511011611200350800001002003920039202282003920039
8020420038150000012040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511022911200350800001002003920039200392003920039
8020420038150000024040258010010080000100800005006400001200192003820038997339996801002008000020016058420038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038150000021040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200882003920039
8020420038150000221040258010010080000100800005006400001201862003820038997339996801002008000020016000020038200381180201100991001008000010000002511011611200350800001002003920039200392003920039
8020420038150000012040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000200511011611200350800001002003920039200392003920039
8020420038150000018040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000047605110116112003517800001002003920039200392003920039
8020420038150000027040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03090a181e1f3f51inst 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)9fa0a1a8accdcfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000011403925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000050200216232003580000102003920039200392003920039
80024200381500001803925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100013050200316342003580000102003920039200392003920039
80024200381500001508125800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000050200316432003580000102003920039200392003920039
80024200381870000070425800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100003050200316232003580000102003920039200392003920039
8002420038150000903925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100030050200227332003580000102003920039200392003920039
80024200381500001203925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000050200316332003580000102003920039200392003920039
80024200381500001503925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000050200316442003580000102003920039200392003920039
80024200381500002103925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100080050200316332003580000102003920039200392003920039
80024200381500001503925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000050200316322003580000102003920039200392003920039
8002420038150000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000050200316342003580000102003920039200392003920039