Apple M1 Microarchitecture Research by Dougall Johnson

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

FNEG (vector, 2D)

Test 1: uops

Code:

  fneg v0.2d, v0.2d
  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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037160611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371512611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371512611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037160611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371569611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fneg v0.2d, v0.2d
  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)9fa8c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150014519686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372008411102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150072619686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100107102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371505708219686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038

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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000120103196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000000316196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000006061196862510010101000010100005028475211200182003720037184543187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000000445196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000024061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fneg v0.2d, v8.2d
  fneg v1.2d, v8.2d
  fneg v2.2d, v8.2d
  fneg v3.2d, v8.2d
  fneg v4.2d, v8.2d
  fneg v5.2d, v8.2d
  fneg v6.2d, v8.2d
  fneg v7.2d, v8.2d
  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)030b1e3a3f51inst 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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006815002102925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815006602925801081008000810080020500640132020019200382003899776998980120200800322008013320038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815003064125801081008000810080020500640920020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150041102925801081008000810080020500640964020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815001202925802061008000810080020500640132020065200382003899776998980226200800322008023120091200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815011202925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000022251291231120046800001002005020049200492004920049
80204200481500006427801161008001610080028500640196120028200492004999769998680128200800382008003820048200481180201100991001008000010000022251281231120045800001002005020050200502004920050
80204200491500306427801161008001610080028500640196020028200482004999769998680128200800382008003820048200481180201100991001008000010000022251281231120045800001002005020050200492004920049
802042004915000064268011610080016100800285006401960200282004820049997610998680128200800382008003820048200481180201100991001008000010000022251281231120045800001002004920049200502005020050
802042004915101206426801161008001610080028500640196020028200482004899769998680128200800382008003820048200491180201100991001008000010001622251291232120046800001002004920049200502010920049

1000 unrolls and 10 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)5f6061696d6edispatch 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)9fa1a8cfd0d2d5d6d9dadbddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391509903925800101080000108000050640000110200192003820038999631001880010208000020800002003820038118002110910108000010005020008160005320035080000102003920039200392003920039
8002420038150003925800101080000108000050640000010200192003820038999631001880010208000020800002003820038118002110910108000010005020005160003520035080000102003920039200392003920039
8002420038150003925800101080000108000050640000110200192003820038999631001880010208000020800002003820038118002110910108000010005020003160003520035080000102003920039200392003920039
800242003815033082325800101080000108000050640000010200192003820038999631001880010208000020800002003820038118002110910108000010005020005160005320035080000102003920039200392003920039
8002420038150003925800101080000108000050640000000200192003820038999631001880010208000020800002003820038118002110910108000010005020003160005520035080000102003920039200392003920039
8002420038150003925800101080000108000050640000000200192003820038999631001880010208000020800002003820038118002110910108000010005020003160003520035080000102003920039200392003920039
8002420038150003925800101080000108000050640000010200192003820038999631001880010208000020800002003820038118002110910108000010005020005160005520035080000102003920039200392003920039
8002420038150003925800101080000108000050640000010200192003820038999631001880010208000020800002003820038118002110910108000010005020003160003520035080000102003920039200392003920039
8002420038150003925800101080000108000050640000010200192003820038999631001880010208000020800002003820038118002110910108000010005020005160005320035080000102003920039200392003920039
8002420038150003925800101080000108000050640000010200192003820038999631001880010208000020800002003820038118002110910108000010005020003160005320035080000102003920039200392003920039