Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAXP (vector, 4S)

Test 1: uops

Code:

  fmaxp v0.4s, v0.4s, v1.4s
  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)031e3a3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150061168725100010001152264680120182037203715723189510001000200020372037111001100000073216111787100020382038203820382038
10042037160061168725100010001000264680120182037203715723189510001000200020372037111001100000373116121787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150082168725100010001000264680120182037203715723189510001000200020372037111001100040373116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100010073116111787100020382038203820382038
10042037160061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000015673116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmaxp v0.4s, v0.4s, v1.4s
  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)0308181e3f4e51inst 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)9fa6a7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000103196872510100100100001001000050028476801200182003720037184221518745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000072619687251010010010000100100005002847680020018200372003718422818745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000032119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820086
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000710116111979129100001002003820038200382003820038
10204200371500007919687251010010010000100100005002847680120018200372003718422818745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500001911968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000122371011611197910100001002003820038200382003820038
10204200371501008219687251010010010000100100005002847680120018201332008418422318745101002001000020020000200372003711102011009910010010000100000371011611197910100001002003820038200382003820038
102042003715000017219687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000019319687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382008520038

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)6061696d6edispatch 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)9fa0a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371490536196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100000064034164419785010000102003820038200382003820038
1002420037150082196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100000064003164419785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100000064004163419785010000102003820038200382003820038
10024200371500516196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100000064004164319785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100000064004164319785010000102003820038200382003820038
10024200371500367196872510010101000010100005028476800320018200372003718444318767100102010000202000020037200371110021109101010000100000064003164319785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476801320018200372003718444318767100102010000202000020037200371110021109101010000100000064034164319785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100000064004164419785010000102003820038200382003820038
10024200371500441196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100000064004164419785010000102003820038200382003820038
10024200371500415196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100000064004164419785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmaxp v0.4s, v1.4s, v0.4s
  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)9facc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150054619687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150032519687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150044119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150012419687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500103196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640416221978510000102003820038200382003820038
10024200371500103196672510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500193196872510010101000010100005028476802001820037200371844431876710010201016820200002008420037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmaxp v0.4s, v8.4s, v9.4s
  fmaxp v1.4s, v8.4s, v9.4s
  fmaxp v2.4s, v8.4s, v9.4s
  fmaxp v3.4s, v8.4s, v9.4s
  fmaxp v4.4s, v8.4s, v9.4s
  fmaxp v5.4s, v8.4s, v9.4s
  fmaxp v6.4s, v8.4s, v9.4s
  fmaxp v7.4s, v8.4s, v9.4s
  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)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)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)9faccfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000511021611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000511011611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000511011611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000511011611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000511011611200350800001002003920039200392003920039
802042003815008225801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000511011611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000511011611200350800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010005110116112003514800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000511011611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304070a0b18191e1f3a3f51inst 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)9fa0a1a8a9acc2cfd5d6d9ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150000000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000502017160171720035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000012001920038200389996310018800122080000201600002003820038118002110910108000010000000502014160171420035080000102003920039200392003920039
80024200381501000000003955258001010800001080000506400001200192003820038999631001880012208000020160000200382003811800211091010800001000000050209160161420035080000102003920039200392003920039
800242003815000000000039258001010800001080000506400000200192003820038999631001880012208000020160000200382003811800211091010800001000000050208160171420035080000102003920039200392003920039
80024200381500000000001652580010108000010800006064075612001920038200389996310018800122080000201600002003820038118002110910108000010000000502017160161720035080000102003920039200392003920039
8002420038150000000000395080010108000010800005064000012001920038200389996310018800122080000201600002003820038118002110910108000010000000502017160171720035080000102003920039200392003920039
80024200381500000000003925800101080000108000050640000020019200382003810010310018800122080000201600002003820038118002110910108000010000000502014160171020035080000102003920039200392003920039
8002420038150000000000812580010108000010800005064000012001920038200389996310018800122080000201600002003820038118002110910108000010000000502017160181720035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000012001920038200389996310018800122080000201600002003820038118002110910108000010000000502016160171720035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000012001920038200389996310018800122080000201600002003820038118002110910108000010000000502017160171420035080000102003920039200392003920039