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, 4H)

Test 1: uops

Code:

  cmhi v0.4h, v0.4h, v1.4h
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmhi v0.4h, v0.4h, v1.4h
  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)03181e3f4e51inst 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)9fa8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500156119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500025119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018320037200371842231874510100200100002002000020037200371110201100991001001000010010007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382008520038
1020420037150006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150096119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000307101161119791100001002003820038200382003820038
10204200371500216119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715502511968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012005420037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500821968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820085
10024200371550611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500821968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmhi v0.4h, v1.4h, v0.4h
  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)0308090b18191e1f3f4e51inst 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
10204200371500000000726196872510100100100001001000050028476800200182003720037184223187451010020010000200213342003720037111020110099100100100001000000100071011611197910100001002003820038200382003820038
102042003715000000004041196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000003071011621198270100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002007120038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3a3f4e51inst 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)9fa6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150007221968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
1002420037150002511968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500010961968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
1002420037150001031968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431878510010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
1002420037150005341968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
1002420037150004251968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
1002420037150003721968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000036402162219785010000102003820038200382003820038
100242003715000841968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmhi v0.4h, v8.4h, v9.4h
  cmhi v1.4h, v8.4h, v9.4h
  cmhi v2.4h, v8.4h, v9.4h
  cmhi v3.4h, v8.4h, v9.4h
  cmhi v4.4h, v8.4h, v9.4h
  cmhi v5.4h, v8.4h, v9.4h
  cmhi v6.4h, v8.4h, v9.4h
  cmhi v7.4h, v8.4h, v9.4h
  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)0318191e3f51inst 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)9fa8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500002925801081008000810080020500640132120019200382003899770699898012020080032200160064200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
80204200381500002925801081008000810080020500640132120019200382003899770699898012020080039200160078200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
80204200381500004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381500008225801001008000010080000626640000020019200382003899737399968010020080000200160000200382003811802011009910010080000100000000511011711200350800001002003920039200392003920039
8020420038150000105325801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381500004025801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381500004025801251008000012580000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
802042003815000010525801001258000010080000626640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000012000511011611200350800001002003920039200392003920039
802042003815000010525801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070b1e3f51inst 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 ld/st (80)~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)9fa8branch mispredict (cb)cfd5d6d9daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150000392580010108000010800005064000012001920038200389996310018800102080000200160000200382003811800211091010800001000502010160011102003580000102003920039200392003920039
800242003815000039258001010800001080000506400001200192003820038999631001880010208000020016000020038200381180021109101080000100050201016001072003580000102003920039200392003920039
800242003815000047625800101080000108000050640000020019200382003899963100188001020800002001600002003820038118002110910108000010005020616007102003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200192003820038999631001880010208000020016000020038200381180021109101080000100050201016006102003580000102003920039200392003920039
80024200381500001022580010108000010800005064000002001920038200389996310018800102080000200160000200382003811800211091010800001000502010160010102003580000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002001600002003820038118002110910108000010005020616006102003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200192003820038999631001880010208000020016000020038200381180021109101080000101050201016006102003580000102003920039200392003920039
8002420038150000102258001010800001080000506400001200192003820038999631001880010208000020016000020038200381180021109101080000100050201016006102003580000102003920039200392003920039
80024200381500008325800101080000108000050640000020019200382003899963100188001020800002001600002003820038118002110910108000010005020616006102003580000102003920039200392003920039
8002420038150000148258001010800001080000506400001200192003820038999631001880010208000020016000020038200381180021109101080000100050201016006102003580000102003920039200392003920039