Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAXNMP (vector, 4H)

Test 1: uops

Code:

  fmaxnmp v0.4h, v0.4h, v1.4h
  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)03080b18191e1f3a3f4e51inst 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)a0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500000006116872510001000100026468002018203720371572318951000100020002037203711100110000000000073116111801100020382038203820382038
100420371500000006116872510001000100026468002018203720371572318951000100020002037203711100110000000000073116111787100020382038203820382038
100420371500009008216872510001000100026468002018203720371572318951000100020002037203711100110000000000073116111787100020382038203820382038
100420371500000006116872510001000100026468002018203720371572318951000100020002037203711100110000000000073116111787100020382038203820382038
100420371500003006116872510001000100026468012018203720371572318951000100020002037203711100110000000000073116111787100020382038203820382038
100420371500000006116872510001000100026468002018203720371572318951000100020002037203711100110000000000073116111787100020382038203820382038
100420371600000006116872510001000100026468002018203720371572318951000100020002037203711100110000000100073116111787100020382038203820382038
100420371500000006116872510001000100026468002018203720371572318951000100020002037203711100110000000000073116111787100020382038203820382038
100420371600000006116872510001000100026468002018203720371572318951000100020002037203711100110000000000073116111787100020382038203820382038
1004203715000000010716872510001000100026468002018203720371572318951000100020002037203711100110000000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmaxnmp v0.4h, v0.4h, v1.4h
  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)03070818191e1f3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000371011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010001971011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10205200371490000001561968725101251001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071411611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010004413871011711197910100001002003820038200382003820038
1020420037150100000611968725101001001000012510000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001371451711197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000626284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000371411611197910100001002003820038200382003820038
1020420037150000000611968725101001001000012510000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000006119687251012510010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100006710117111979125100001002003820038200382003820038

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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037149126119687251001010100001010000502847680020018020037202271844431876710010201000020200002003720037111002110910101000010100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101001210100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000101120640216221982310000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720131111002110910101000010000640216221978510000102003820038200382003820038
1002420037150072619687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221982410000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000661216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmaxnmp v0.4h, v1.4h, 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)03181e3a3f4e51inst 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)9fa0a1a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037155072061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715003061196874310100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150033061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715600061196872510100100100001001000050028476800200183200372003718422318745101002001000020020000200372008511102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007102161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b1e3f4e51inst 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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000061196762510025101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402172219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100221091010100001000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000661196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150003361196672510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
10024200371500021726196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmaxnmp v0.4h, v8.4h, v9.4h
  fmaxnmp v1.4h, v8.4h, v9.4h
  fmaxnmp v2.4h, v8.4h, v9.4h
  fmaxnmp v3.4h, v8.4h, v9.4h
  fmaxnmp v4.4h, v8.4h, v9.4h
  fmaxnmp v5.4h, v8.4h, v9.4h
  fmaxnmp v6.4h, v8.4h, v9.4h
  fmaxnmp v7.4h, v8.4h, v9.4h
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)0307080b18191e3f51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601500000027135258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102161120035800001002003920039200392003920039
8020420038150000009640258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102161120035800001002003920039200392003920039
802042003815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150000000515258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000000940258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)033f51inst 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)9fa0a6a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000012305020416242003580000102003920039200392003920039
80024200381503925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100007505020416422003580000102003920039200392003920039
8002420038150392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000305020216442003580000102003920039200392003920039
8002420038150602580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010001005020416442003580000102003920039200392003920039
8002420038150392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000005020216242003580000102003920039200392003920039
8002420038150392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000005020316422003580000102003920039200392003920039
80024200381503925800101080000108000050640000120079200902009899961510018800102080000201600002003820038118002110910108000010000305020216442003580000102003920039200392003920039
8002420038150392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010220005020216242003580000102003920039200392003920039
8002420038150392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000005020416242003580000102003920039200392003920039
80024200381506025800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100007205020416442003580000102003920039200392003920039