Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAX (vector, 8H)

Test 1: uops

Code:

  fmax 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)033f4e51inst 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
1004203715611687251000100010002646802018203720371572318951000100020002037203711100110000073316111787100020382038203820382038
1004203715611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037151241687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203716611687251000100010002646802018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
1004203715611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203716611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmax 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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071031622197910100001002003820038200382003820038
1020420037150082196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010030071021622197910100001002003820038200382003820038
10204200371500768196872510100100100001001000051728487312005420037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
1020420037149061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010012671021622197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197918100001002003820038200382003820038
10204200371560124196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03071e3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500047319687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100036402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162419785210000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500010319687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006632162219785010000102003820038200382003820038
1002420037150008219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000101020266402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010608502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500486119687251001010100001010000502847680020126200372003718444318767100102010000202000020037200371110021109101010000104036402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010671202000020037200371110021109101010000100406402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmax 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)03081e3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500126119687251010010010000100100005002847680200182003720037184223187451010020010492200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715001506119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101331119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500156119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000307101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200902003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500126119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200862008620038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

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)9fa8cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000961196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443188231001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
10024200371500016861196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
1002420037150000536196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
10024200371500028261196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010101505028476801200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmax v0.8h, v8.8h, v9.8h
  fmax v1.8h, v8.8h, v9.8h
  fmax v2.8h, v8.8h, v9.8h
  fmax v3.8h, v8.8h, v9.8h
  fmax v4.8h, v8.8h, v9.8h
  fmax v5.8h, v8.8h, v9.8h
  fmax v6.8h, v8.8h, v9.8h
  fmax 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)0318191e1f3f51inst 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150006004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511061611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400000200192003820038997331002280100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
8020420038150003604025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815000604025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
8020420038150001204025801001008000010080000500640000020019200382003899733999680100200800002001600002003820091218020110099100100800001000100511011612200354800001002003920039200392003920039
802042003815001240040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000005110117112007325800001002003920039200392003920091
8020420038150101471048225801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000100511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000030511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)60696b6d6edispatch 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150003925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010000050201161120035080000102003920039200392003920039
80024200381500123925800101080093108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010000050201161120035080000102003920039200392003920039
80024200381500039258001010800001080000506400000200190200382003899963100188001020800002016000020038200381180021109101080000100039050201161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010000050201161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010023050201161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010000050201161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010000050201161120035080000102003920039200392003920039
80024200381500039258001010800001080000506400000200190200872003899963100188001020800002016000020038200381180021109101080000100263050201161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010009050201161120035080000102003920039200392003920039
8002420038150103925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010000050201161120035080000102003920039200392003920039