Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGT (zero, 2S)

Test 1: uops

Code:

  cmgt v0.2s, v0.2s, #0
  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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150155168625100010001000264521020182037203715713189510001000100020372037111001100000073316331786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073316331786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073216331786100020382038203820382038
1004203715082168625100010001000264521020182037203715713189510001000100020372037111001100000095316331786100020382038203820382038
10042037150156168625100010001000264521020182037203715713189510001000100020372037111001100000073316331786100020382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100000373316221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073316331786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372085111001100000073216331786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073316331786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100000073316331786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmgt v0.2s, v0.2s, #0
  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)0318191e1f3f4e51inst 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)9fa0a7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000030071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000006071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000100071011611197910100001002003820038200382003820038

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)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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500103196862510010101000010100005028475210200182003720037184430318767100102010000201000020037200371110021109101010000100000640216221985410000102003820038200382003820038
10024200371500126196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420085150061196862510010101000010100005028475210200182003720037184430318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500166196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500145196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037149082196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500103196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500258196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100030640216221978610000102003820038200382003820038
1002420037150084196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmgt v0.2s, v8.2s, #0
  cmgt v1.2s, v8.2s, #0
  cmgt v2.2s, v8.2s, #0
  cmgt v3.2s, v8.2s, #0
  cmgt v4.2s, v8.2s, #0
  cmgt v5.2s, v8.2s, #0
  cmgt v6.2s, v8.2s, #0
  cmgt v7.2s, v8.2s, #0
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)033f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151182162320035800001002003920039200392003920039
80204200381503032580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001002011151183162220035800001002003920039200392003920039
8020420038150922580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151184162320035800001002003920039200392003920039
8020420038150292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151184165220035800001002003920039200392003920039
8020420038150292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151183162220035800001002003920039200392003920039
8020420038150292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151183164320035800001002003920039200392003920039
80204200381505992580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151183163320035800001002003920039200392003920039
8020420038150292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151182162320035800001002003920039200392003920039
8020420038150292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151184163320035800001002003920039200392003920039
8020420038150292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151184162220035800001002003920039200392003920039

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150393925800101080000108000050640000120019020038200389996310018800102080000208000020038200381180021109101080000100050201116692003580000102003920039200392003920039
800242003815005142580010108000010800005064000012001902003820038999631001880010208000020800002003820038118002110910108000010005020716692003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000502011161092003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000502010165112003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100050201016952009780000102003920039200392003920039
80024200381500392580010108000010800005064000002001902003820038999631001880010208000020800002003820038118002110910108000010005020816752003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100050209166112003580000102003920039200392003920039
800242003815054392580010108000010800005064000002001902003820038999631001880010208000020800002003820038118002110910108000010005020716472003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001902003820038999631001880010208000020800002003820038118002110910108000010005020816952003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001902003820038999631001880010208000020800002003820038118002110910108000010005020616772003580000102003920039200392003920039