Apple M1 Microarchitecture Research by Dougall Johnson

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

USHR (vector, 8B)

Test 1: uops

Code:

  ushr v0.8b, v0.8b, #3
  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
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716010316862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371608216862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037161210416862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  ushr v0.8b, v0.8b, #3
  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)030a0b181e3f4e51inst 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
1020420037156000961196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001002207102162219791100001002003820038200382003820038
1020420037155000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
10204200371550009361196862510100100100001001000050028475210200182008420085184213187451010020010000200100002003720037211020110099100100100001000007102162219791100001002003820038200382003820038
1020420037155210089196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000037102162219791100001002003820038200382003820038
1020420037155200061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
10204200371552001282196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007102162219857100001002003820038200382003820038
102042003715620015103196862510146100100001151030450028475210200182003720037184247187451043120010000200100002003720037111020110099100100100001000107102162219791100001002003820038200382003820038
1020420037155200061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000037102162219791100001002003820038200382003820038
10204200371562002161196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037155000082196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000107102162219791100001002003820038200382003820038

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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715008219686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715096119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000103640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201016920084200371110021109101010000100640216221978610000102003820038200382003820038
100242003714908219686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120054200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  ushr v0.8b, v8.8b, #3
  ushr v1.8b, v8.8b, #3
  ushr v2.8b, v8.8b, #3
  ushr v3.8b, v8.8b, #3
  ushr v4.8b, v8.8b, #3
  ushr v5.8b, v8.8b, #3
  ushr v6.8b, v8.8b, #3
  ushr v7.8b, v8.8b, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)030b1e3f51inst 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
8020420061155024292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038156007762580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815500292580108100801041008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000311151180160020035800001002003920039200392003920039
8020420038155012292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815600292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038155006942580108100800081008002050064013202001920049200489976999868012820080038200800382004820048118020110099100100800001000022251281231120046800001002005020050200492004920050
8020420049155006426801161008001610080028500640196020028200482004899761099868012820080038200800382004820049118020110099100100800001000022251291231120045800001002004920050200502005020049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304080b18191e3f5051inst 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)9fa0a8a9acbranch mispredict (cb)cecfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024205101621119830939045802921080281108000050640000002025320241203381003830101838059320805832080780203362039061800211091010800001021232780050555104542038380000102044720489205002039520441
8002420443156000000200025800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000005020785242019180000102003920039200392003920039
8002420141163010003390258001010800001080000506400000120019200382003899963100458001020800002080000200382003811800211091010800001000001195020316232003580000102003920039200392003920039
8002420038161000000243025800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100003005020616232003580000102003920039200392003920039
800242003815500000039025800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000005020516322003580000102003920039200392003920039
800242003815500000039025800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100003005020316362003580000102003920039200392003920039
8002420038155000001539025800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000005020516322003580000102003920039200392003920039
800242003815500000039025800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000005020316652003580000102003920039200392003920039
800242003815500000039025800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000005020216632003580000102003920039200392003920039
8002420038155000000609025800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000005020316532003580000102003920039200392003920039