Apple M1 Microarchitecture Research by Dougall Johnson

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

REV32 (vector, 4H)

Test 1: uops

Code:

  rev32 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)0318191e3f4e51inst 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
10042037160006116862510001000100026452102018203720371571318951000100010002037203711100110000073216111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500010316862510001000100026452102018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
100420371500396116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  rev32 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)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
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100137101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100367101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686461010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001002507101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001005037101161119791100001002003820038200382003820038
1020420037150063119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100237101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100107101161119791100001002003820038200382003820038

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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001004296403162219786010000102003820038200382003820038
10024200371500611968625100231010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100366402162219786010000102003820038200382003820038
10024200371500821968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100396402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752120018200372003718443318767100102010000201016920037200371110021109101010000104006402162219786010000102003820038200382003820038
1002420037150061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010051936402162219786010000102003820038200382003820038
1002420037150044119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001002940236402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100106402162219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001002136402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  rev32 v0.4h, v8.4h
  rev32 v1.4h, v8.4h
  rev32 v2.4h, v8.4h
  rev32 v3.4h, v8.4h
  rev32 v4.4h, v8.4h
  rev32 v5.4h, v8.4h
  rev32 v6.4h, v8.4h
  rev32 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)030a1e3f51inst 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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920120200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200891180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010001011151180160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100030611151180160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000001005020516632003580000102003920039200392003920039
80024200381500098425800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000209435020516532003580000102003920039200392003920039
80024200381500039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000001035020516452003580000102003920039200392003920039
8002420038159016239258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000002005020516552003580000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000004005020516532003580000102003920039200392003920039
80024200881500039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000001005020516532003580000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000201035020516352003580000102003920039200392003920039
800242003815000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010200000125020316352003580000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000000005020316352003580000102003920039200392003920039
8002420038150042939258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000001005020516352003580000102003920039200392003920039