Apple M1 Microarchitecture Research by Dougall Johnson

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

CMHI (register, 2S)

Test 1: uops

Code:

  cmhi v0.2s, v0.2s, v1.2s
  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)03081e3f4e51inst 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
10042037150020116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150013116872510001000100026468002018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
1004203715008216872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150015916872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160010316872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203716008216872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820852038
10042037150061168725100010001000264680020182037203715723189510001000200020372037111001100012073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmhi v0.2s, v0.2s, v1.2s
  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)030b1e3f4e51inst 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
10204200371500061196872510100100100001001000050028476801200182003720037184223187631010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010003710116111982515100001002003820038200382003820085
102042003715010103196874510100100100121001000052228476800200182003720037184223187451010020010000200200002003720037111020110099100100100001001071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000103196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000371011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715005161196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715004561196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000126402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500044119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100306404162219785010000102003820038200382003820038
10024200371501506119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020085200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmhi v0.2s, v1.2s, v0.2s
  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)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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000003520631196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715036611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100099640217221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715012611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010229640216221978510000102003820038200382003820038
100242003715024611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100015640216211978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010003640216221978510000102003820038200382003820038
100242003715024611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmhi v0.2s, v8.2s, v9.2s
  cmhi v1.2s, v8.2s, v9.2s
  cmhi v2.2s, v8.2s, v9.2s
  cmhi v3.2s, v8.2s, v9.2s
  cmhi v4.2s, v8.2s, v9.2s
  cmhi v5.2s, v8.2s, v9.2s
  cmhi v6.2s, v8.2s, v9.2s
  cmhi v7.2s, v8.2s, v9.2s
  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)03191e3f51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601500382258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010001651103161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100003651101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100009051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100009651101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996802362008000020016000020038200381180201100991001008000010000951101161120035800001002003920039200392003920039
8020420038149104025801001008000010080000500640000120019201022003899733999680100200800002001600002003820038118020110099100100800001000010551101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100009051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000015651101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000351101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100009951101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)5f696d6edispatch 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)9fa8a9accfd2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
800242003815000812580010108000010800006664000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000138502000116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502030116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
8002420038150027392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039