Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAXP (scalar)

Test 1: uops

Code:

  fmaxp d0, 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452102018203720371571318951000100020002037203711100110003073216331786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100020002037203711100110001073316331786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100020002037203711100110001073316231786100020382038203820382038
1004203716061168625100010001000264521120182037203715713189510001000200020372037111001100001873316331786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100020002037203711100110000673316331786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000200020372037111001100002173316331786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100020002037203711100110001673316331786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100020002037203711100110000073316331786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100020002037203711100110000973216331786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100020002037203711100110000073316331786100020382038203820382038

Test 2: Latency 1->2

Code:

  fmaxp d0, 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)03080918191e3f4e51inst 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
10204200371500000052719686251010010010000100100005002847521120018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521120018200372003718421318745101002001000020020000200372003711102011009910010010000100007101162119791100001002003820038200382003820038
1020420037150001106119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521120065200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500000031319686251010010010000100100005002847521020018200842007018421318745101002001000020220000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10205200371500000019119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000023414619686251010010010000100100005002847521120018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820085200382003820038
1020420037150000006119686251010010010000100100005002847521120018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521120018200372003718421318745101002001000020020000200372003711102011009910010010000100037101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080b18191e1f3a3f4e51inst 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
100242003715000000000168196864510010101000011103045028475210200182022520037184437188021001020101692020000200372003711100211091010100001000000006405167519786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003711100211091010100001000000306406166619786010000102003820038200382003820038
100242003715600000000631196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003711100211091010100001000000006406166719786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475210200182003720037184433187671062120100002020000200372003711100211091010100001000000006406166619786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003711100211091010100001000000006406166619786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003711100211091010100001000000006407167619786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003711100211091010100001000000006406166719786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003711100211091010100001000000006406166619786010000102003820038200382003820038
100242003715000000000428196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003711100211091010100001000000006407167719786010000102003820038200382003820038
100242003715000000360061196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003711100211091010100001000000006405166619786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fmaxp d0, v8.2d
  fmaxp d1, v8.2d
  fmaxp d2, v8.2d
  fmaxp d3, v8.2d
  fmaxp d4, v8.2d
  fmaxp d5, v8.2d
  fmaxp d6, v8.2d
  fmaxp d7, v8.2d
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fa1a8acc5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815036292580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
802042003815527292580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322021600642003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
802042003815021292580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381509292580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b181e1f3f51inst 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)5f60696b6d6edispatch 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)9facbranch mispredict (cb)cfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401500000392580010108000010800005064000070200190200382003899963100188001020800002016000020038200381180021109101080000100050203160332003580000102008820039200392003920039
80024200381550000392580010108000010800005064000070200190200382003899963100188001020800002016000020038200381180021109101080000100050203160332003580000102003920039200392003920039
80024200381500000395080010108000010800005064000060200193200382003899963100188001020800002016000020038200381180021109101080000100050203160222003580000102003920039200392003920039
800242003815000007042580010108000010800005064000031200190200382003899963100188012020800002016000020038200381180021109101080000100050203160322003580000102003920039200392003920039
800242003815000303925800101080000108000050640000402001902003820038100043100188001020800002016019220038200381180021109101080000100050202160232003580000102003920039200392003920039
80024200381500000392580010108000010800005064000040200190200382003899963100188001020800002016000020038200381180021109101080000100050203160322003580000102003920039200392003920039
80024200381500000392580010108000010800005064000051200190200382003899963100188001020800002016000020038200381180021109101080000100050202160332003580000102003920039200392003920039
80024200381500000392580010108000010800005064000040200190200382003899963100188001020800002016000020038200381180021109101080000100050202160332003580000102003920039200392003920039
800242008715000088602580010108000010800005064000040200190200382003899963100188001020800002016000020038200381180021109101080000100050202160322003580000102003920039200392003920039
80024200381500000392580010108000010800005064000040200190200382003899963100188001020800002016000020038200381180021109101080000100050203162332003580000102003920039200392003920039