Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMEQ (scalar, zero, H)

Test 1: uops

Code:

  fcmeq h0, h0, #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)03081e3f4e51inst 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
10042037160061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715016261168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371509361168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100002073116111786100020382038203820382038
10042037150361168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmeq h0, h0, #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)696b6d6edispatch 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715008419686251010010010000100100005002847643200180200372003718421318745101002001000020010000200372003711102011009910010010000100000710216111979100100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521200180200372003718421318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037150084196862510100100100001001000050028475212001802003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791270100001002003820038200382003820038
1020420037150023319686251010010010000100100005002847521200180200372003718421318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521200180200372003718421318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
102042003715008419686251010010010000100100005002847521200180200372003718421318745101002001000020010000200372003711102011009910010010000100000710116111979101100001002003820038200382003820038
1020420037150010519686251010010010000100100005002847521200180200372003718421318745101002001000020010000200372003711102011009910010010000100023710116111979100100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521200180200372003718421318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
102042003715008419686251010010010000100100005002847521200180200372003718421318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521200180200372003718421318745101002001000020010000200372003711102011009910010010000100010710116111979100100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000726196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000010006402162219786010000102003820038200382003820038
1002420037150000000061196752510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102008420038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmeq h0, h8, #0
  fcmeq h1, h8, #0
  fcmeq h2, h8, #0
  fcmeq h3, h8, #0
  fcmeq h4, h8, #0
  fcmeq h5, h8, #0
  fcmeq h6, h8, #0
  fcmeq h7, h8, #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)03080b18191e1f3f51inst 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)9fa0a1a6a7a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000003060292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000003900292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000750292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000780292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000003120292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200902003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000002880292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
8020420038150000034202192580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b181e1f3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242010115200135039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039
800242003815000366039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039
80024200381500015039258001010800001080108506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039
80024200381500030039258001010800001080000506400000200192003820038999631001880010208000020800002003820086118002110910108000010105020116112003580000102003920039200392003920039
8002420038150003039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039
8002420038150009060258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039
8002420038150000039140804771080559108058250644590020299203912038510057281020380692208068520807792033420392818002110910108000010032755020116112003580000102003920039200392003920141
8002420038150000069258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039