Apple M1 Microarchitecture Research by Dougall Johnson

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

REV64 (vector, 4H)

Test 1: uops

Code:

  rev64 v0.4h, v0.4h
  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
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000673116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
100420371508216862510001000100026452102018203720371571318951000100010002037203711100110000673116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100003673116111786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100001873116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  rev64 v0.4h, v0.4h
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715001031968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715002121968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715002511968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100137101161119791100001002003820038200382003820038
102042003715005021968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100137101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03093f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150010319686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162319786010000102003820038200382003820038
1002420037150073819686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
1002420037149012419686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162319786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715008219686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100106402162319786010000102003820038200382003820038
100242003715008219686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715008219686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162319786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162319786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100106402162319786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  rev64 v0.4h, v8.4h
  rev64 v1.4h, v8.4h
  rev64 v2.4h, v8.4h
  rev64 v3.4h, v8.4h
  rev64 v4.4h, v8.4h
  rev64 v5.4h, v8.4h
  rev64 v6.4h, v8.4h
  rev64 v7.4h, v8.4h
  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)03070a18193f51inst 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
802042006715011001972580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161220035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161220035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013202001920038200389986699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161220035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161220035800001002003920039201032003920039
80204200381501100292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181181120035800001002003920039200392003920039
802042003815011001192580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)9fa0a8accfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000146258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000050201216814142003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000050201616612152003580000102003920039200392003920039
800242003815000127528001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000050201716612122003580000102003920039200392003920086
800242003815000392580010108000010800005064000002001902003820038999631001880010208000020800002003820038118002110910108000010252650201116614142003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000050201616611142003580000102003920039200392003920039
800242003815000197258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000050201316612122003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000050201616614142008580000102003920039200392003920039
80024200381500083258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000050201416615122003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000050201116612122003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000050201516816142003580000102003920039200392003920039