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, 2S)

Test 1: uops

Code:

  ushr v0.2s, v0.2s, #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)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
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100014073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110001373116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716121041686251000100010002645212018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
100420371601031686251000100010002645212018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
10042037160821686251000100010002645212018203720371571819141000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  ushr v0.2s, v0.2s, #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)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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715512611968625101001001000010010000500284752112001820037200371842131876610100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371560611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371550611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371560611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371550611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371550611967525101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715505361968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010017101161119791100001002003820038200382003820038
10204200371550611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371550611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715506119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100467101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000064021622197860010000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001020064021622197860010000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000064021622197860010000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000064021622197860010000102003820038200382003820038
1002420037150004081968444100231210000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010012064022422197860010000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010443064021622197860010000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001013064021622197860010000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010206064021622197860010000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001016064021622197860010000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000064022422197860010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  ushr v0.2s, v8.2s, #3
  ushr v1.2s, v8.2s, #3
  ushr v2.2s, v8.2s, #3
  ushr v3.2s, v8.2s, #3
  ushr v4.2s, v8.2s, #3
  ushr v5.2s, v8.2s, #3
  ushr v6.2s, v8.2s, #3
  ushr v7.2s, v8.2s, #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)03080f18191e1f3a3f51inst 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)9fa0a1a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015500000002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000000011151180160020035800001002003920039200392003920039
802042003815500000002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000000011151180160020035800001002003920039200392003920039
802042003815600000002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000003011151180160020035800001002003920039200392003920039
802042003815500000002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000000011151180160020035800001002003920039200392003920039
802042003815500000002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000000011151180160020035800001002003920039200392003920039
802042003815500000002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000000011151180160020035800001002003920039200392003920039
8020420038155050000029258010810080008100800205006401320200190200872003899771499898051220080032200800322003820038118020110099100100800001000000011151180160020035800001002003920039200392003920039
802042003815500000002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000000011151180290020035800001002003920039200392003920039
80204200381551000264880299280204102801041008022250064172002008102010020102999512100138022620080135200801352010320092318020110099100100800001004000104011151360160020333800001002015220145201362010220102
8020420092156102213211215672580108100800081008021550064013202001902003820038997711100158022420080137200801352009020038118020110099100100800001000000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03041e3f51inst 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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051155103672580010108000010800005064000000200192003820038999673100188001020800002080000200382003811800211091010800001000050202816282620035080000102003920039200392003920039
800242003815500392580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000050202616292720035080000102003920039200392003920039
800242003815500392580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001010050202616272720035080000102003920039200392003920039
800242003815500392580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000050202916283120035080000102003920039200392003920039
800242003815500492580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000050202916152720035080000102003920039200392003920039
8002420038156012392580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000050201916262020035080000102003920039200392003920039
8002420038156006592580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000050201316262020035080000102003920039200392003920039
800242003815500392580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000050202816202720035080000102003920039200392003920039
800242003815500392580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000050202716152820035080000102003920039200392003920039
800242003815500392580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000050201316281420035080000102003920039200392003920039