Apple M1 Microarchitecture Research by Dougall Johnson

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

UMAXP (vector, 8B)

Test 1: uops

Code:

  umaxp 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)033f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037166116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000673216221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371561168725100010001000264680020182037203715723189510001000200020372037111001100002473216221787100020382038203820382038
100420371661168725100010001000264680020182037203715723189510001000200020372037111001100001573216221787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110001373216221787100020382038203820382038
10042037166116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  umaxp 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)03090b18191e1f3f4e51inst 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000145196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071002161119791100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
1020420037150000000726196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
102042003715000000082196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
1020420037150000000751196872510100100100001001000050028476801200182003720037184223187451010020010000200203322013320037111020110099100100100001000071001161119791100001002003820038200382008620038
102042003715000009061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030818191e3f4e51inst 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)9fa8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037166000017219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000108219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150000126119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200862003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100030640216221978510000102003820038201802007420038
1002420037150000095219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100060640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020085200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150000063419687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  umaxp 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)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)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)9facc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150145196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150201196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003714961196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150135196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003714961196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150693196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002008420037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037151000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371510000006651968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000005681968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  umaxp v0.8b, v8.8b, v9.8b
  umaxp v1.8b, v8.8b, v9.8b
  umaxp v2.8b, v8.8b, v9.8b
  umaxp v3.8b, v8.8b, v9.8b
  umaxp v4.8b, v8.8b, v9.8b
  umaxp v5.8b, v8.8b, v9.8b
  umaxp v6.8b, v8.8b, v9.8b
  umaxp 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)0308091e1f3f51inst 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)9fa7a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102161120035800001002003920039200392003920039
802042003815000001722580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815000001052580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101163120035800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815000001932580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03091e3f51inst 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)9faccfd5d6d9dbddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481650039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005033416014420035080000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005038416004320035080000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005033416003520035080000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005033216005420035080000102003920039200392003920039
800242003815000704258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005033316004320035080000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005032416203320035080000102003920039200392003920039
80024200381490039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005036316005320035080000102003920039200392003920039
800242003815000145258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001065031316003520035080000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005030416003320035080000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005031316003520035080000102003920039200392003920039