Apple M1 Microarchitecture Research by Dougall Johnson

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

CMTST (register, 4S)

Test 1: uops

Code:

  cmtst 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)03071e3f4e51inst 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
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221785100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116121787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000075116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
1004203716006116872510001000100026468012018203720371571318951000100020002037203711100110000073116111787100020382038203820382038
1004203715096116872510001000100026468012018203720371572318951000100020002037203711100110000075116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmtst 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)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)9fa0a1a7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000007261968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000333071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000215071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000204071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030809181e1f3f4e51inst 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
10024200371500000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000124196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000002302196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000606402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000001217196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000010006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmtst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150018919687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150010519687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371501986119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100307101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150025119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3a3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150002190196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000064412161291978510000102003820038200382003820038
100242003715012108262196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000064412161251978510000102003820038200382003820038
100242003715000262196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000064451612111978510000102003820038200382003820038
10024200371500021271968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000644101610111978510000102003820038200382003820038
10024200371500021461968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010010644516581978510000102003820038200382003820038
100242003715000262196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000064481610111978510000102003820038200382003820038
10024200371500021921968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000644101610111978510000102003820038200382003820038
100242003715000262196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000064412165101978510000102003820038200382003820038
100242003715000262196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000064410161281978510000102003820038200382003820038
10024200371500026219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006445161251978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmtst v0.4s, v8.4s, v9.4s
  cmtst v1.4s, v8.4s, v9.4s
  cmtst v2.4s, v8.4s, v9.4s
  cmtst v3.4s, v8.4s, v9.4s
  cmtst v4.4s, v8.4s, v9.4s
  cmtst v5.4s, v8.4s, v9.4s
  cmtst v6.4s, v8.4s, v9.4s
  cmtst 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)030708191e1f3f51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150000008225801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000024000051102161120035800001002003920039200392003920039
80204200381500000042025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000202000051101161120035800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000051101161120035800001002003920039200392003920039
80204200381500002404025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000051101161120035800001002003920039200392003920039
802042003815000000287425801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000051102161120035800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000051101161120035800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000051101161120073800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000051101161120035800001002003920039200392003920039
80204200381500000014525801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000051101161120035800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b1e3f51inst 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)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)9fa7a8a9cficache miss (d3)d5d6d9daddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000753925800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000050200516003520035080000102003920039200392003920039
8002420038150005523925800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000050200316003520035080000102008820039200392003920039
800242003815000372373225800101080000118000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000050200516005320035080000102003920039200392003920039
80024200381500003925800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000050200516003520035080000102003920039200392003920039
80024200381500003925800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000050200516005320035080000102003920039200392003920039
800242003815000027125800101080000108000050640000020019020087200389996031001880010208000020160000200382039411800211091010800001010250200516003520035080000102003920039200392003920039
80024200381500103925800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000050200327005320035080000102003920089201102003920039
80024200381500003925800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000050200516005320035080000102003920039200392003920039
80024200381500003925800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000050200516005420035080000102003920039200392003920039
800242003815000070425800101080000108000050640000020019020038200389996031001880010208000020160000200382003811800211091010800001000050200316006420035080000102003920039200392003920039