Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAXNM (vector, 8H)

Test 1: uops

Code:

  fmaxnm v0.8h, v0.8h, v1.8h
  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
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073216111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371536116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmaxnm v0.8h, v0.8h, v1.8h
  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)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)9fa0a6a7a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000018061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000307102162219791100001002003820038200382003820038
102042003715000000084196872510100100100001001000050028476801200182003720037184363187451010020010000200200002003720037111020110099100100100001000000007102163219791100001002003820038200382003820038
1020420037150000021061196872510100100100001001000050028476801200182003720037184228187451010020010000200200002003720037111020110099100100100001000000007102162219791100001002003820038200382003820038
1020420037150000027061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007102162219791100001002003820038200382003820038
102042003715000001517682196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007102162219791100001002003820038200382003820038
10204200371500100240536196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000002007102162219791100001002003820038200382003820038
1020420037150000021061196872510100100100001001000050028476800200182003720037184223187451010020010000202200002003720037111020110099100100100001000000007102162219791100001002003820038200382003820038
102042003715000000061196872510100100100001191060850028476801200182003720037184223187451010020010000200200002003720084511020110099100100100001000000007102162219791100001002003820038200382003820038
1020420037150000024061196872510100100100001001000050028476800200182003720037184293187451010020010000200200002003720037111020110099100100100001000322007102162219791100001002003820038200382003820038
10204200371500002144061196872510100100100001001000050028476800200182003720037184223187451010020410000200200002003720037111020110099100100100001000000007102162219791100001002003820038200382003820038

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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150009082196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150003061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000168061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000324061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150009061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000192061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmaxnm v0.8h, v1.8h, v0.8h
  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)030b181e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000156196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500015061196872510100100100001001000050028476800200182003720037184223187451010020410000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000225061196872510100100100001001000050028476800200182003720037184223187451010020010000204200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420083150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000917661196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001002071011611197910100001002003820038200382003820038
102042003715000327061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000234061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308191e3f4e51inst 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)72scheduler 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
10024200371500006119687251001010100001010000502847680020018020037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382008520038
10024200371500006119687251001010100001010000502847680120018020037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018020037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500036119687251001010100001010000502847680020018020037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018020037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000396119687251001010100001010000502847680020018020037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018020037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020054020037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000276119687251001010100001010000502847680120018020037200371844473187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018320037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmaxnm v0.8h, v8.8h, v9.8h
  fmaxnm v1.8h, v8.8h, v9.8h
  fmaxnm v2.8h, v8.8h, v9.8h
  fmaxnm v3.8h, v8.8h, v9.8h
  fmaxnm v4.8h, v8.8h, v9.8h
  fmaxnm v5.8h, v8.8h, v9.8h
  fmaxnm v6.8h, v8.8h, v9.8h
  fmaxnm v7.8h, v8.8h, v9.8h
  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)03081e1f3f51inst 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)9fa8acbranch mispredict (cb)cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000040258010010080000100800005006400000520019200382003899733999680100200800002001600002003820038118020110099100100800001000015110005162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000520019200382003899733999680100200800002001600002003820038118020110099100100800001000005110002162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000520019200382003899733999680100200800002001600002003820038118020110099100100800001000005110012162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000520019200382003899733999680100200800002001600002003820038118020110099100100800001000005110012162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000020019200382003899733999680100200800002001600002003820038118020110099100100800001000005110002162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001520019200382003899733999680100200800002001600002003820038118020110099100100800001000005110002162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001020019200382003899733999680100200800002001600002003820038118020110099100100800001000005110012162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000020019200382003899733999680100200800002001600002003820038118020110099100100800001000605110002162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000520071200382003899733999680100200800002001600002003820038118020110099100100800001000005110012162220035800001002003920039200392003920039
8020420038150015040258010010080000100800005006400000020019200382003899733999680100200800002001600002003820038118020110099100100800001000005110002162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304081e3f51inst 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)9fa8accfitlb miss (d4)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715010081258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001006050211161617102003580000102003920039200392003920039
80024200381511003925800101080000128000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100350211171617172003580000102003920039200392003920039
80025200381501003925800101080000128000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050211171617172003580000102003920039200392003920039
8002420038150100394980010108000012800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005021114161792003580000102003920039200392003920039
80024200381501003925800101080000128000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050211171617172003580000102003920039200392003920039
80024200381501003925800101080000128000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050211141617142003580000102003920039200392003920039
80024200381501003925800101080000128000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050211171618172003580000102003920039200392003920039
8002420038150101839258001010800001280000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000502119161792003580000102003920039200392003920039
80024200381501003925800101080000128000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050211141617132003580000102003920039200392003920039
80024200381501012200125800101080000128000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050211171616172003580000102003920039200392003920039