Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGE (register, 4S)

Test 1: uops

Code:

  cmge v0.4s, v0.4s, v1.4s
  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)031e1f3f4e51inst 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
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037160061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037160061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372075111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmge v0.4s, v0.4s, v1.4s
  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)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
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100097102162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100107102162219791100001002003820038200382003820038
10204200371509611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100107102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037149000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006404162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000010006402162219785010000102003820038200382003820038
1002420037150000000611964125100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000906402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001011100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000001506402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431878810010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmge v0.4s, v1.4s, v0.4s
  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)030818191e1f3a3f4e51inst 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)9fa0a1a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071003162219791100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071002162219791100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200852003718422318745101002001000020020000200372003711102011009910010010000100001071012162219791100001002003820038200382003820038
102042003715000000161196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000006671002162219791100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100001071002162319791100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071002162219791100001002003820038200382003820038
102042003715000000070019687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071002162219791100001002003820038201342003820038
102042003715000000014719687251010010010000100100005002847680020018200372003718422318745101002001000020020000200862008621102011009910010010000100022201573302162219791100001002003820038200382003820038
102042013315000027388053619687251010010010000100100005002847680020054200862008418426718745102562041016720020000200372003711102011009910010010000100001371002162219791100001002003820038200382003820038
10204200371500000006119687431010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071002162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03070a1e3a3f4e51inst 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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150110268196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000102000644111611111978510000102003820038200382003820038
100242003715011026819687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000064411161051978510000102003820038200382003820038
100242003715011026819687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010030064461610101978510000102003820038200382003820038
10024200371501102175196872510010101001210100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000644101610101978510000102003820038202272003820038
1002420037150110258119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000064411161051978510000102003820038200382003820038
100242003715011026819687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000064461610111978510000102003820038200382003820038
100242003715011026819687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000064410168101978510000102003820038200382003820038
1002420037150110268196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000644101610101978510000102003820038200382003820038
1002420037150110268196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000644101611111978510000102003820038200382003820038
1002420037150110225819687251001010100001010000502847680120018020037200371844431876710010201000020200002003720084111002110910101000010000064410165101978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmge v0.4s, v8.4s, v9.4s
  cmge v1.4s, v8.4s, v9.4s
  cmge v2.4s, v8.4s, v9.4s
  cmge v3.4s, v8.4s, v9.4s
  cmge v4.4s, v8.4s, v9.4s
  cmge v5.4s, v8.4s, v9.4s
  cmge v6.4s, v8.4s, v9.4s
  cmge v7.4s, v8.4s, v9.4s
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051104161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100051151101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000138051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500061258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002024720039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03040708090b18191e1f3f51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cfd5d6d9ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000000000021525800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000330600005020231609620035080000102003920039200392003920088
80024200381500000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000000000502091608520035080000102003920039200392003920039
800242003815000000000011025800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000000000502091609620035080000102003920039200392003920039
80024200381500000000009925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000000000502061609620035080000102003920039200392003920039
800242003815000000000018325800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000310150005020716071020035080000102003920039200392003920039
800242003815000000000071825800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000000000502081607720035080000102003920039200392003920039
80024202441500000000903925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000000000502081608820035080000102003920039200392003920039
80024200381500000000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000000000502081609520035080000102003920039200392003920039
800242003815000000000010425800101080000108000050640000120019200382003899969100188001020800002016000020038200381180021109101080000100000000000502051609620035080000102003920039200392003920039
8002420038150000000000161125800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000100000502081605820035080000102003920039200392003920039