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, 8H)

Test 1: uops

Code:

  cmge v0.8h, v0.8h, #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)033f4e51inst 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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371582168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371561168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371584168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371661168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371561168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371561168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371661168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371661168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371561168625100010001000264521120182037203715713189510001000100020372037111001100020073116111786100020382038203820382038
100420371561168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmge v0.8h, v0.8h, #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)03181e1f3f4e51inst 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
1020420037150000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500004141968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100167101161119791100001002003820038200382003820038
10204200371500008419686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001002707101161119791100001002003820038200382003820038
1020420037150000841968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500001301968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000108611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080a0b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000000001031968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000000821968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037311002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000000001241968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000000821968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371490000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmge v0.8h, v8.8h, #0
  cmge v1.8h, v8.8h, #0
  cmge v2.8h, v8.8h, #0
  cmge v3.8h, v8.8h, #0
  cmge v4.8h, v8.8h, #0
  cmge v5.8h, v8.8h, #0
  cmge v6.8h, v8.8h, #0
  cmge v7.8h, v8.8h, #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)031e3f51inst 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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150071258010810080008100800205006401320200192003820038997706998980120200800322008003220038202401180201100991001008000010000111511841600200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511801600200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511801600200350800001002003920039200392003920039
8020420038150071258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511801600200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997776998980120200800322008003220038200381180201100991001008000010000111511811600200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511801600200350800001002003920039200392003920039
80204200381500284258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511801600200350800001002003920039200392003920039
80204200381500155258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511801600200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511801600200350800001002003920039200392003920039
8020420038150071258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511801600200350800001002003920039200392003920039

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)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)9fcfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001050201161120035080000102003920039200392003920039
800242003815000126325800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001050201161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001050201161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001050201161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001050201161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001050201161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020803862080000200382003811800211091010800001050201161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001050201161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001050201161120035080000102003920039200392003920039
80024200381500013425800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001050201161120035080000102003920039200392003920039