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, 4S)

Test 1: uops

Code:

  fabs v0.4s, v0.4s
  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)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
1004203715126116862510001000100026452112018203720371571318951000100010002037203711100110000073316111786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100008173116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000673116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000673116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018208420371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fabs v0.4s, 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150246119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150156119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715036119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150338219686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150156119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371502744119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371503606119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9fa0a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000450611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010001006403162219786210000102003820038200382003820038
1002420037150001080611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
100242003715000900611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
100242003715000690611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
100242003715000570611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820180200382003820038
100242003715000510611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000606402162219786010000102003820038200382003820038
100242003715000120611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
100242003715000780611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820181
1002420037150001506119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100015106402162219786010000102003820038200382003820038
100242003715000660611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)0318191e1f3f51inst 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)9fa0a1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200481500012059925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
802042003815000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
80204200381500092642925801081008010810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181501120035800001002003920039200392003920039
802042003815000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
802042003815000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
802042003815000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
802042003815000602925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100020011151181161120035800001002003920039200392003920039
8020420038150201202925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
8020420038150000069425801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
802042003815000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308181e3f51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150003392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201816171720035080000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201716171720035080000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201316171420035080000102003920039200392003920039
8002420038150009392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001012050201316171420035080000102003920039200392003920039
80024200381500002292580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000350201416171420035080000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201416171420035080000102003920039200392003920039
800242003815000039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100005020171691620035080000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201716131720035080000102003920039200392003920039
800242003815000010225800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000502091617920035080000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201616171720035080000102003920039200392003920039