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, 16B)

Test 1: uops

Code:

  ushr v0.16b, v0.16b, #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)03181e3a3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
1004203716000611686251000100010002645212018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
10042037160390611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716030611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160451611686251000100010002645212018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
1004203715090611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715000611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160360611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716000611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150150611686251000100010002645212018203720371571318951000100010002037203711100110001073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  ushr v0.16b, v0.16b, #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)030818191e3f4e51inst 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
10204200371550000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000037101161119791100001002003820038200382003820038
102042003715500096119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000907101161119791100001002003820038200382003820038
10204200371560000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000097101161119791100001002003820038200382003820038
102042003715500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000907101161119791100001002003820038200382003820038
102042003715500006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000907101161119791100001002003820038200382003820038
102042003715510006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000967101161119791100001002003820038200382003820038
102042003715500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000907101161119791100001002003820038200382003820038
102042003715500006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000727101161119791100001002003820038200382003820038
102042003715500006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000847101161119791100001002003820038200382003820038
10204200371550000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e1f3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715500076196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715600061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715606061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037155000943196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001010640216221978610000102003820038200382003820038
100242003715600061196862510012101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  ushr v0.16b, v8.16b, #3
  ushr v1.16b, v8.16b, #3
  ushr v2.16b, v8.16b, #3
  ushr v3.16b, v8.16b, #3
  ushr v4.16b, v8.16b, #3
  ushr v5.16b, v8.16b, #3
  ushr v6.16b, v8.16b, #3
  ushr v7.16b, v8.16b, #3
  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)030b181e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591550002925801081008000810080020500640132120019020038200389977699898012020080032200800322003820038118020110099100100800001000011151183160020035800001002003920039200392003920039
80204200381550002925801081008000810080020500640132120019020038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815500029258010810080008100800205006401321200190200382003899776998980120200800322008003220038200381180201100991001008000010034011151180160020035800001002003920039200392003920039
80204200381561032925801081008000810080020500640132120019020038200389977699898012020080032200800322003820038118020110099100100800001006011151180160020035800001002003920039200392003920039
80204200381550002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381550002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815500071258010810080008100800205006401321200190200382003899771199898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381550002925801081008000810080020500640132120019020038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381550002925801081008000810080020500640132120019020038200389977699898012020080032200800322003820038118020110099100100800001001011151180160020035800001002003920039200392003920039
802042003815600059925801081008000810080020500640132120019020038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b191e3f51inst 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)6066696d6edispatch 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015500039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001002005020616532003580000102003920039200392003920039
800242008815700039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001001005020516352003580000102003920039200392003920039
800242003815600039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005005020516542003580000102003920039200392003920039
8002420038155000277258001010800001080000506400000020019200382003899963104138001020800002080000200382003811800211091010800001001005020316632003580000102003920039200392003920039
8002420038155000144258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001001035020516632003580000102003920039200392003920039
800242003815500039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000035020316662003580000102003920039200392003920039
8002420038156001839258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001002065020616352003580000102003920039200392003920039
800242003815500039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001001035020316532003580000102003920039200392003920039
800242003815500039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001001035020516352003580000102003920039200392003920039
800242003815500039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001003005020316552003580000102003920039200392003920039