Apple M1 Microarchitecture Research by Dougall Johnson

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

CMHS (register, 4S)

Test 1: uops

Code:

  cmhs 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)0309181e3f4e51inst 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
10042037150006116872510001000100026468012018203720371572318951000100020002037203711100110000073116121787100020382038203820382038
10042037150006116872510001000100026468012018203720371572318951000100020002037203711100110000073116131787100020382038203820382038
10042037150006116872510001000100026468012018203720371572318951000100020002037203711100110000073116131787100020382038203820382038
10042037150006116872510001000100026468012018203720371572318951000100020002037203711100110004073116141787100020382038203820382038
10042037150006116872510001000100026468012018203720371572318951000100020002037203711100110000073116141787100020382038203820382038
10042037150006116872510001000100026468012018203720371572318951000100020002037203711100110000073116131787100020382038203820382038
10042037150006116872510001000100026468012018203720371572318951000100020002037203711100110000073116131787100020382038203820382038
10042037160006116872510001000100026468012018203720371572318951000100020002037203711100110000073116131787100020382038203820382038
100420371500666116872510001000100026468012018203720371572318951000100020002037203711100110000073116131787100020382038203820382038
100420371500023216872510001000100026468012018203720371572318951000100020002037203711100110000073116131787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmhs 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)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)6061696b6d6edispatch 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)9fa8acc2cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968725101001001000010010000500284768011020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071010102162219791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028528120020018020037200371842231874510100200100002002000020037200371110201100991001001000010050870710002162219791100001002003820038200382003820038
10204200371500611968725101141001000010010000500284768000200180200372003718422318745101002001000020020000200372003711102011009910010010000100000710002162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768000200180200372003718422318745101002001000020020000200372003711102011009910010010000100000710002162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680002001802003720037184223187451010020010000200200002003720037111020110099100100100001003390710002162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680010200180200372003718422318745101002001000020020000200372008511102011009910010010000100000710002162219791100001002003820038200382003820038
102042003715006119687251010010010000100103045002847680002001802003720037184223187451010020010000200200002003720037111020110099100100100001004400710002162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680002001832003720037184223187451010020010000200200002003720037111020110099100100100001005130710002162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768000200180200372003718422318745101002001000020020000200372003711102011009910010010000100000710002162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768000200180200372003718422318745101002001000020020000200372003711102011009910010010000100000710002162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308091e3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150000103196762510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371501001138196874210010101000010101525028489630200182003720037184443187671001020100002020000200372003711100211091010100001000002076640216221982310000102003820086200382003820180
1002420083150110611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000024640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510037101004810100006028476801200182003720037184443187671001020100002020000200372003711100211091010100001000105990640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000003640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmhs 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)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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371501501031968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020084200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119855100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150001871968725101001001000010010000500284768002001820037200371842231874510100200101672042000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150005221968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820085200382008520038
102042003715000611968725101001001000010010000500284768002006520037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

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)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
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000006311968780100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmhs v0.4s, v8.4s, v9.4s
  cmhs v1.4s, v8.4s, v9.4s
  cmhs v2.4s, v8.4s, v9.4s
  cmhs v3.4s, v8.4s, v9.4s
  cmhs v4.4s, v8.4s, v9.4s
  cmhs v5.4s, v8.4s, v9.4s
  cmhs v6.4s, v8.4s, v9.4s
  cmhs 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)03080b18191e1f3f51inst 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
802042006015000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511021611200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
8020420038150000030040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
8020420038149000018040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
802042003815000006040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
80204200381500000102040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200471500400392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050207164220035080000102003920039200392003920039
8002420038150001500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050204164720035080000102003920039200392003920039
80024200381500000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050205262420035080000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050204482420035080000102003920039200392003920039
80024200381500000392580010108000010800006664000012001920038200389996310018800102080000201600002003820038118002110910108000010000050204164220035080000102003920039200392003920039
80024200381500000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010004050202164320035080000102003920039200392003920089
8002420038150001920392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050202164220035080000102003920039200392003920039
8002420038150001590392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050204162420035080000102003920039200392003920039
800242003815000001672580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050204162420035080000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050204164220035080000102003920039200392003920039