Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGE (zero, 2D)

Test 1: uops

Code:

  cmge v0.2d, v0.2d, #0
  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)03191e3f4e51inst 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)a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150061168625100010001000264521201820372037157131895100010001000203720371110011000000073316111786100020382038203820382038
10042037150061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037150061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111852100020382038203820382038
10042037150061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037150061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371500177168625100010001000264521201820372037157131895100010001000203720371110011000005073116111786100020382038203820382038
10042037150061168625100010001000264521201820372037157131895100010001000203720371110011000000373116111786100020382038203820382038
10042037150061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037150082168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371500775168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmge v0.2d, v0.2d, #0
  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
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100207101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100207101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100067101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000277101161119791100001002003820038200382003820038
102042003714906119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100137101161119791100001002003820038200382003820038

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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100213640516221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715006119686103100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010040640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010010640216221978610000102003820038200382003820038
1002420037150013071968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715002511968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500711968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001001615640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010003640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmge v0.2d, v8.2d, #0
  cmge v1.2d, v8.2d, #0
  cmge v2.2d, v8.2d, #0
  cmge v3.2d, v8.2d, #0
  cmge v4.2d, v8.2d, #0
  cmge v5.2d, v8.2d, #0
  cmge v6.2d, v8.2d, #0
  cmge v7.2d, v8.2d, #0
  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)03091e3f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049150202925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151440160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181160020035800001002003920039200392003920039
8020420038150002925801081008000810080122500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000711151180160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
80204200381500052025801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010040011151180160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010013011151180160020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150000000622580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050204165320035080000102003920039200392003920039
80024200381500000001232580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050205165520035080000102003920039200392003920039
8002420038150000000602580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000150203163520035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020087200381180021109101080000100000000050203163520035080000102003920039200392003920039
80024200381500000001022580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100001000050205165320035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050203165520035080000102003920039200392003920086
80024200381500000001922580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050205164520035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050203163520035080000102003920039200392003920039
80024200381500000001022580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050205165320035080000102003920039200392003920039
80024200381500000002482580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050205165320035080000102003920039200392003920039