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, 4H)

Test 1: uops

Code:

  ushr v0.4h, v0.4h, #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
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000373216111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100012773116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606116862510001000100026452120182037203715713189510001000100020372037111001100001573116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  ushr v0.4h, v0.4h, #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)03181e1f3f4e51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715500022519686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101162119791100001002003820038200382003820038
102042003715500010319686251010010010000100100005002847521120018200372003718421318745101002041000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715500010319686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550008219686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371551006119686251010010010000100100005002847521120018200372003718421318745101002001000020010167200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715500014719686251010010010000100100005002847521120018200372008418421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa8acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003716100127196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371560061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371550061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371560061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786110000102003820038200382003820038
10024200371550061196754510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715600251196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001010006402162219786010000102003820038200382003820038
100242003715600105196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371550061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371550061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219928010000102003820038200382003820038
100242003715500103196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  ushr v0.4h, v8.4h, #3
  ushr v1.4h, v8.4h, #3
  ushr v2.4h, v8.4h, #3
  ushr v3.4h, v8.4h, #3
  ushr v4.4h, v8.4h, #3
  ushr v5.4h, v8.4h, #3
  ushr v6.4h, v8.4h, #3
  ushr v7.4h, v8.4h, #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)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)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
802042003815518292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181160020035800001002003920039200392003920039
8020420038155297292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038155300292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381550292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815533292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038156150292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038155294292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815512292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381550292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815503422580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3f51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050205164220035080000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050913164220035080000102003920039200392003920039
8002420090150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050203162420035080000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050204162420035080000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050204162420035080000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050204164220035080000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050204162420035080000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899968100188001020800002080132200482003811800211091010800001000050204164220035080000102003920039200392003920039
80024200381500153925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050202164220035080000102003920039200392003920039
8002420038149003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050204162420035080000102003920039200392003920039