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, 2S)

Test 1: uops

Code:

  fcmeq v0.2s, 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)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
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110003073116111787100020382038203820382038
100420371512611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
10042037150821687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382086203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmeq v0.2s, 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)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
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000967101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372008418422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715007261968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100397101161119791100001002003820038200382003820038
10204200371510611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100307101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100507101161119791100001002003820038200382003820038
102042003715005361968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100207101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100107101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080a0b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024201321510100000006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000010606406166619785010000102003820038200382003820038
10024200371500000000006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000020006404165519785010000102003820038200382003820038
100242003715000000000010319687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000021006405165619785010000102003820038200382003820038
100242003715000000000061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000120306405165519785010000102007420085200382003820038
100242003715000000012006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000060006406166519785010000102003820038200382003820038
10024200371500000000006119687251001010100001010000502847680020018200372003718448031876710010201000020200002003720037111002110910101000010000000006405165519785010000102003820038200382003820038
10024200371500000000006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006406166519785010000102003820038200382003820038
10024200371500000000006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006406165619785010000102003820038200382003820038
10024200371500000000006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000010006405166619785010000102003820038200382003820038
10024200371500000000006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000000006404165619785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fcmeq v0.2s, 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001207101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001001007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001001007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001001007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001001007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200203282008520086211020110099100100100001006206007101161119791100001002003820038200382003820084

1000 unrolls and 10 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500012619687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000101600640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010064640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221979710000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715010611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037155003581968725100101010000121000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fcmeq v0.2s, v8.2s, v9.2s
  fcmeq v1.2s, v8.2s, v9.2s
  fcmeq v2.2s, v8.2s, v9.2s
  fcmeq v3.2s, v8.2s, v9.2s
  fcmeq v4.2s, v8.2s, v9.2s
  fcmeq v5.2s, v8.2s, v9.2s
  fcmeq v6.2s, v8.2s, v9.2s
  fcmeq v7.2s, 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)030b18191e1f3a3f51inst 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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150000000402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000003511031611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000002001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038149000000255258010010080189100800005006400001200642014620142997303100218010020080000200160000200382003811802011009910010080000100024032805229199112031723800001002044920394203962039720343
802042040415306693652811207163807761248065312280684609644562020225202862029710019027101288051120080481204160978202892034561802011009910010080000100020223355193185112023518800001002024720293203372029320296
8020420286152156672440095714280595121800001188048562164384212030320402203931003802010178807072008000020016000020038201362180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038150000000822580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010001003511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392024420039
8020420038150000000868480100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000006511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)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)9fa0a1a8accficache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100006502001216000121220035680080000102003920039200392003920039
80024200381500039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000502001616000151520035490080000102003920039200392003920039
80024200381500039258009210800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000502001616000161420035490080000102003920039200392003920039
80024200381500039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000502001816000171420035490080000102003920039200392003920039
80024200381500039258001010800921280000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000502001616000171320035490080000102003920039200392003920039
80024200381500039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100006502001616000171320035490080000102003920039200392003920039
80024200381500060258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000102200502001616000161320035490080000102003920039200392003920039
800242003815016235239258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000502001316000131320035490080000102003920039200392003920039
800242003815000392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000035020091600091520035490080000102003920039200392003920039
80024200381500039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000502001616000161220035490080000102003920039200392003920039