Apple M1 Microarchitecture Research by Dougall Johnson

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

CMEQ (zero, 2S)

Test 1: uops

Code:

  cmeq v0.2s, v0.2s, #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)0308090b18191e1f3a3f4e51inst 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)a0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715000000006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203715000003006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203715000000006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203715000003006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203716000000006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203715000000006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203716000000006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382086
1004203715000000006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203715000000006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203715000000006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmeq v0.2s, v0.2s, #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)030b1e1f3a3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200542003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184243187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037149000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000371011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037149000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010002640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150012221968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010060640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100120640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820179200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010030640216231978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmeq v0.2s, v8.2s, #0
  cmeq v1.2s, v8.2s, #0
  cmeq v2.2s, v8.2s, #0
  cmeq v3.2s, v8.2s, #0
  cmeq v4.2s, v8.2s, #0
  cmeq v5.2s, v8.2s, #0
  cmeq v6.2s, v8.2s, #0
  cmeq v7.2s, v8.2s, #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)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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006715002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511821622200350800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010013111511811612200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997761002480120200800322008003220038200381180201100991001008000010000111511821622200350800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010020111511821621200350800001002003920039200392003920039
80204200381500292580108100800081028002050064013202001920038200389977119989801202008003220080032200382003811802011009910010080000100460111511821621200350800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511821622200350800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010020111511811621200350800001002003920039200392003920039
802042008815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010020111511811612200350800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511821621200350800001002003920039200392003920039
8020420038150029828010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100383111511821621200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500021125800101080000108000050640000002001920038200389996031001880010208000020800002003820038118002110910108000010000005037031633200350080000102003920039200392003920039
8002420038150003925800101080000108000050640000012001920038200389996031001880010208000020800002003820038118002110910108000010000005020031632200350080000102003920039200392003920039
80024200381500014425800101080000108000050640000012001920038200389996031001880010208000020800002003820038118002110910108000010000005037031633200350080000102003920039200392003920039
80024200381500016925800101080000108000050640000012001920038200389996731001880010208000020800002003820038118002110910108000010000005020021623200350080000102003920039200392003920039
80024200381501809825800101080000108000050640000002001920038200389996031001880010208000020800002003820038118002110910108000010000005020031633200350080000102003920039200392003920039
8002420038150006025800101080000108000050640000012001920038200389996031001880010208000020800002003820038118002110910108000010000005020031632200350080000102003920039200392003920039
8002420038150003925800101080000108000050640000002001920038200389996031001880010208000020800002003820038118002110910108000010000005020031672200350080000102003920039200392003920039
80024200381500053825800101080000108000050640000012001920038200389996031001880010208000020800002003820038118002110910108000010000005020031643200350080000102003920039200392003920039
8002420038150003925800101080000108000050640000012001920038200389996031001880010208000020800002003820038118002110910108000010000005020021633200350080000102003920039200392003920039
8002420038150003925800101080000108000050640000002001920038200389996031001880010208000020800002003820038118002110910108000010000005020021643200350080000102003920039200392003920039