Apple M1 Microarchitecture Research by Dougall Johnson

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

FABS (vector, 4H)

Test 1: uops

Code:

  fabs v0.4h, v0.4h
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715062016862510001000100026452112018203720371571318951000100010002037203711100110001073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  fabs v0.4h, v0.4h
  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)03191e3f4e51inst 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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150006311968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150012611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003714900611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150002511968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150001031968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150027611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010001007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
1002420037150044119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786110000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
10024200371502406119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
10024200371502946119686251001010100001010000502847521120018200372003718443318767100102010180201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
10024200371501026119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402165219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000101006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fabs v0.4h, v8.4h
  fabs v1.4h, v8.4h
  fabs v2.4h, v8.4h
  fabs v3.4h, v8.4h
  fabs v4.4h, v8.4h
  fabs v5.4h, v8.4h
  fabs v6.4h, v8.4h
  fabs v7.4h, v8.4h
  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)030818191e1f3f51inst 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)9fa0a1a6a7a8acc2c5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815000000292580108100800081008002050064013212001902003820038997769989801202008003220080032200382003811802011009910010080000100000000011151181620035800001002003920039200912003920039
802042003815000100292580108100800081008002050064013212001902003820038997769989802242008003220080032200382003821802011009910010080000100000000011151181620035800001002003920039200392003920039
80204200381500000025042580108100800081008011850064013212001902003820038997769989801202008003220080032200382003811802011009910010080000100000000011151341620035800001002008720039200392003920090
802042003815000000292580108100800081008011850064013212001902003820038997769989801202008003220080032200382003811802011009910010080000100000000011151181620035800001002003920039200392003920039
802042003815000000502580108100801081008002050064013212005702003820038997769989801202008003220080032200382003811802011009910010080000100002000011151182920076800001002008820039200392003920039
8020420038150000002925801081008000810080020500640132120057020089200389977129989801202008003220080032200382003821802011009910010080000100020000011151181620035800001002003920039200392003920039
8020420038150000002925801081008000810080020500640132120019020038200389977129989801202008003220080032200382003821802011009910010080000100000100011151182420035800001002003920039200392003920039
802042003815000000292580108100800081008002050064013212005702008720038997769989802262008003220080032200382003811802011009910010080000100000000011151181620035800001002003920039200902003920039
80204200381510000029258010810080008100800205006401321200190200382003899776998980120200800322028003220038201441180201100991001008000010020001253011151183420035800001002003920039200392003920039
802042003815000030292580108100800081008002050064013212001902003820038997769989801202008013620080032200382003821802011009910010080000100000010011151181620035800001002003920039200392003920039

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)6061696d6edispatch 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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001006502000516542003580000102003920039200392003920039
800242003815000392580010108000010800005064000010200192003820109100053100188001020800002080000200382003811800211091010800001000502000416452003580000102003920039200392003920039
80024200381500039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001006502000516552003580000102003920039200392003920039
80024200381500039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001000502000516542003580000102003920039200392003920039
80024200381500060258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001000502000516542003580000102003920039200392003920039
800242003815002139258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001009502000516582003580000102003920039200392003920039
80024200381500039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001006502000516582003580000102003920039200392003920039
8002420038149015392580010108000010800005064000010200192003820038999631001880010208000020800002003820038118002110910108000010005020001016752003580000102003920039200392003920039
800242003815000609258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001000502000516452003580000102003920039200392003920039
800242003815000392580010108000010800005064000010200192003820038999631001880010208000020800002003820038118002110910108000010066502000516552003580000102003920039200392003920039