Apple M1 Microarchitecture Research by Dougall Johnson

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

SMAXP (vector, 8B)

Test 1: uops

Code:

  smaxp v0.8b, v0.8b, v1.8b
  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)03191e3f4e51inst 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
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715078611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371600611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468020182037203715723189510001000200020372037111001100001873216221787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371600611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  smaxp v0.8b, v0.8b, v1.8b
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200852003820038
102042003715010184196872510100100100001001012654128485660200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200203602003720037111020110099100100100001005071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000371011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)033f4e51inst 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
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
10024200371496119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001010640316331978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
100242003715098319687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640316341978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  smaxp v0.8b, v1.8b, v0.8b
  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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000710317211979125100001002003820038200382003820038
102042003715006119687251012510010000125100006262847680120018200372003718422318744101252001000020020000200372003711102011009910010010000100000071011621197910100001002003820038200382003820038
102042003714906119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011711197910100001002003820038200382003820038
102042003715008419687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071013711197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020054200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150085619687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100200071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071211611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219853010000102003820038200382003820038
1002420037150000000082196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037155000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006405162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000126196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000355196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000306402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402322219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  smaxp v0.8b, v8.8b, v9.8b
  smaxp v1.8b, v8.8b, v9.8b
  smaxp v2.8b, v8.8b, v9.8b
  smaxp v3.8b, v8.8b, v9.8b
  smaxp v4.8b, v8.8b, v9.8b
  smaxp v5.8b, v8.8b, v9.8b
  smaxp v6.8b, v8.8b, v9.8b
  smaxp v7.8b, v8.8b, v9.8b
  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)03080a0b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015000000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511071634200350800001002003920089200392003920039
80204201041500000016200404480100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000010000511031633200350800001002003920039200392003920039
802042003815100000000822580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511041634200350800001002003920039200392003920039
802042003815000000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511041623200350800001002003920039200392003920039
8020420038150000000007052580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511031643200350800001002003920039200392003920039
8020420038150000000006325801001008009512580000500640000120019200382003899821299968010020280000200160188201022003811802011009910010080000100000000000511031622200350800001002003920039200392003920039
8020420038150000001200402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511031644200350800001002003920039200392003920039
802042003815000000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000001511021643200350800001002003920039200392003920039
802042003815000000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000300511041644200350800001002003920039200392003920039
802042003815000000000612580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000040000511041644200350800001002003920039200392003920039

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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200471500039258001010800001080000506400000200192003820088999671001880010208000020160000200382003811800211091010800001005020816862003580000102003920039200392003920039
80024200381550081258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020616772003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001005020616672003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001005020816782003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001005020716992003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001005020816762003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001005020716782003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001005020716882003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001005020716882003580000102003920039200392003920039
800242003815024039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001005020916672003580000102003920039200392003920039