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, 4H)

Test 1: uops

Code:

  cmge v0.4h, v0.4h, #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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371519861168625100010001000264521120182037203715713189510001000100020372037111001100001073116111786100020382038203820382038
1004203715084168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715082168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmge v0.4h, v0.4h, #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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100010071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000009371011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000001271011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001004048071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030818191e3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000001871968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010300640516551978610000102003820038200382003820038
10024200371500110611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640516551978610000102003820038200382003820038
1002420037150000097819686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000102360640516551978610000102003820038200382003820038
100242003715000008419686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000104400640416551978610000102003820085200382003820038
1002420037150000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001043840640516551978610000102003820038200382003820038
10024200371500000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640516551978610000102003820038200382003820086
1002420037150000095919686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000104400640516551978610000102003820038200382003820038
100242003715000001241968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640516551978610000102003820038200382003820038
10024200371500000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640516551978610000102003820038200382003820038
10024200371500000109419686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000104100640416541978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmge v0.4h, v8.4h, #0
  cmge v1.4h, v8.4h, #0
  cmge v2.4h, v8.4h, #0
  cmge v3.4h, v8.4h, #0
  cmge v4.4h, v8.4h, #0
  cmge v5.4h, v8.4h, #0
  cmge v6.4h, v8.4h, #0
  cmge v7.4h, v8.4h, #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)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)9fa8acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500093825801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511811620035800001002003920039200392003920039
80204200381500065258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100320111511801620035800001002003920039200392003920039
80204200381500081125801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815000115258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100290111511801620035800001002003920039200392003920039
8020420038150002925801081008000810080104500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
80204200381500092258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100380111511801620035800001002003920039200392003920039
8020420038149002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100310111511801620035800001002003920039200392003920039
80204200381500629258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100420111511801620035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030e191e3a3f51inst 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)9fa0a1a8accficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150200075125800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000050200416242003580000102003920039200392003920039
800242003815000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000050200216242003580000102003920039200392003920039
800242003815000008325800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010001050200416422003580000102003920039200392003920039
800242003815000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000050200416242003580000102003920039200392003920039
800242003815000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000050200216442003580000102003920039200392003920039
8002420038150000034325800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000050200216242003580000102003920039200392003920039
800242003815000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000050200416422003580000102003920039200392003920039
8002420038150000039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100033650200216422003580000102003920039200392003920039
800242003815000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000050200416422003580000102003920039200392003920039
800242003815000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000350200216242003580000102003920039200392003920039