Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAXNM (vector, 4H)

Test 1: uops

Code:

  fmaxnm v0.4h, v0.4h, v1.4h
  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
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100001873116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100003073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100003073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100001573116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318991000100020002037203711100110004373116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmaxnm v0.4h, v0.4h, v1.4h
  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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037155084196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500216196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500124196872510100100100001001000050028476800200182003720037184223187451010020010000200203302003720037111020110099100100100001000000007100161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b1e3f4e51inst 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)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)9fa0a1a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000012691968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000006405163319785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
100242003715900010681968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000606403163319785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
1002420037150000821968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
100242003715000026619687251001010100001010000502847680200182003720037184440131876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768020018200372003718444031876710160201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmaxnm v0.4h, v1.4h, v0.4h
  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)03181e1f3f4e51inst 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)9fa0a1a6a8acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000103196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000020071001162119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071001161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071001161119791100001002003820038200382003820038
1020420037150000550196872510100100100001001000050028476802005420037200371842231874510100200100002002000020037200371110201100991001001000010000000074001161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071001161119791100001002003820038200382003820038
102042003714900061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071001161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071001161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071001161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028502462001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071001161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071001161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e3a3f4e51inst 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)9fa0cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000017219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216231978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000101640216321978510000102003820038200382003820038
1002420037150000041619687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216231978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216321978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216321978510000102003820038200382003820038
1002420037150000043519687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216321978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216321978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmaxnm v0.4h, v8.4h, v9.4h
  fmaxnm v1.4h, v8.4h, v9.4h
  fmaxnm v2.4h, v8.4h, v9.4h
  fmaxnm v3.4h, v8.4h, v9.4h
  fmaxnm v4.4h, v8.4h, v9.4h
  fmaxnm v5.4h, v8.4h, v9.4h
  fmaxnm v6.4h, v8.4h, v9.4h
  fmaxnm v7.4h, v8.4h, v9.4h
  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)03181e1f3f51inst 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)9fa8c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102161120035800001002003920039200392003920039
80204200381500270402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150160402580100100800001008000050064000020019200382019599733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000251101161120035800001002003920039200392003920039
8020420038150000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101162120035800001002003920039200392003920039
8020420038150000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161220035800001002003920039200392003920039
80204200381500300402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3f51inst 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)9fa0a6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000453925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000050207166520035080000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000050206166520035080000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000050205167720035080000102003920039200392003920039
800242003815000039258001010800001080000506400000200192003820038100043100188001020800002016000020038200381180021109101080000100000050207167820035080000102003920039200392003920039
800242003815000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502061678200351680000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000050205165520035080000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000050206166620035080000102003920039200392003920039
800242003815000183925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000050206166720035080000102003920039200392003920039
800242003815000123925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000050207165620035080000102003920039200392003920039
800242003815000245425800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000050205165620035080000102003920039200392003920039