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, 16B)

Test 1: uops

Code:

  cmge v0.16b, v0.16b, #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)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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715082168625100010001000264521120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189511521000100020372037111001100000073216221786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000003073216221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000007273216221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100001073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmge v0.16b, v0.16b, #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)030b18191e3f4e51inst 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)9fa8c2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000053619686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000025119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500001626119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100027101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000216119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003714900006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000640516331978610000102003820038200382003820038
1002420037150010611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
10024200841500002511968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmge v0.16b, v8.16b, #0
  cmge v1.16b, v8.16b, #0
  cmge v2.16b, v8.16b, #0
  cmge v3.16b, v8.16b, #0
  cmge v4.16b, v8.16b, #0
  cmge v5.16b, v8.16b, #0
  cmge v6.16b, v8.16b, #0
  cmge v7.16b, v8.16b, #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)0309191e3f51inst 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
8020420048150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181160020035800001002003920039200392003920039
80204200381500021292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150000296380208100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038149000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500033292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3f51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500000000392580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000000050202162220035080000102003920039200392003920039
80024200381550000000392580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000000050202162220035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000000050202162220035080000102003920039200392003920039
800242003815000000003925800881080000108000050640000002001920038200389996031001880010208000020800002003820038118002110910108000010000005150202162220035080000102003920039200392003920039
800242003815000000001592580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000000650202162220035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000000050202162220035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000011200192003820038999603100188001020800002080000200382003811800211091010800001000000050202162220035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000000050202162220035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999603100188001020800002080000200382003811800211091010800001000000050202162220035080000102003920039200392003920039
8002420038150000000010225800101080000108000050640000002001920038200389996031001880010208000020800002003820038118002110910108000010000003050202162220035080000102003920039200392003920039