Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGT (register, 16B)

Test 1: uops

Code:

  cmgt v0.16b, v0.16b, v1.16b
  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)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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371596116872510001000100026468002018203720371572318951000100020002037203711100110004273116111787100020382038203820382038
10042037160611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371515611687251000100010002646800201820372037157231895100010002000203720371110011000973116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371690611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmgt v0.16b, v0.16b, v1.16b
  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)030b191e1f3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150101748861196872510100100100001001000066728476801200182008720037184223187451010020010000200200002003720037111020110099100100100001000020071021622197910100001002003820038200382003820132
1020420037150001288589196872510100100100001001015259728476801200182003720037184223187451025520010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
10204202271500012061196872510100100100001001000050028476801200182003720037184223187451025920010000200200002003720037111020110099100100100001000000371021622197910100001002003820038200382003820038
102042003715000195061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000010071021622197910100001002003820038200382003820038
10204200371500018061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
10204200371500012061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021634197910100001002003820038200382003820038
10204200371500018061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
10204200371500015061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
10204200371500021061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
10204200371500021061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0309191e3f4e51inst 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)9fa7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150001561196872510010101000010100005028476801200182003720037184443187671001022100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000011100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150002761196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150009943196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150001561196872510010101000010100005028476801200182003720037184483187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150001861196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmgt v0.16b, v1.16b, v0.16b
  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)60696b6d6edispatch 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371503661196872510100100100001001000050028476800200180200862008418422318745101002001000020020000200372003711102011009910010010000100600071032422198610100001002003820038200382003820038
1020420037150961196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371501261196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371500726196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028489630200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371502461196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038

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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000147001071968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500000900611968725100101210000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715000003600611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500000900611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150000021009121968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmgt v0.16b, v8.16b, v9.16b
  cmgt v1.16b, v8.16b, v9.16b
  cmgt v2.16b, v8.16b, v9.16b
  cmgt v3.16b, v8.16b, v9.16b
  cmgt v4.16b, v8.16b, v9.16b
  cmgt v5.16b, v8.16b, v9.16b
  cmgt v6.16b, v8.16b, v9.16b
  cmgt v7.16b, v8.16b, v9.16b
  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)03083f51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010010051103162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100360951102162220035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100340351102162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100280051102162220035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010050051102162220035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010027046851102162220035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000011751102162220035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000013551102162220035800001002003920039200392003920039
80204200381500515258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039

1000 unrolls and 10 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)5f60696d6edispatch 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100005020216112003580000102003920039200392003920039
80024200381500392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001004335020116112003580000102003920039200392003920039
8002420038150054258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100095020116112003580000102003920039200392003920039
800242003815003622580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001002035020116112003580000102003920039200392003920039
80024200381500392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001003735020116112003580000102003920039200392003920039
80024200381500392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001003835020116112003580000102003920039200392003920039
8002420038150039258001010800001080000506400001120019200382003899963100188001020800002016000020038200381180021109101080000100121655020116122003580000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100005020216112003580000102003920039200392003920039
800242003815003925800101080000108000050640000012001920038200879996310018800102080000201600002003820038118002110910108000010035905020116112003580000102003920039200392003920039
800242003815003925800101080000108000050640000112001920038200389996310018800102080000201600002003820038118002110910108000010050995020116112003580000102003920039200392003920039