Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAXNMV (8H)

Test 1: uops

Code:

  fmaxnmv h0, v0.8h
  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)696d6edispatch 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
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110006073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372301052547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723486125472510001000100039816030183037303724143289510001000100030373037111001100014073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fmaxnmv h0, 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): 3.0037

retire (01)cycle (02)0307191e3a3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000014929547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
102043003722500026129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018300373003728264328760101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
102043003722500008429547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100073411611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
1020430037225000021029547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
1020430037225000019129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e3f4e51inst 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)696b6d6edispatch 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500002332954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010002155716404164529629010000103003830038300383003830038
10024300372240120822954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000006406166629629010000103003830038300383003830038
100243003722500001072954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000006406166529629010000103003830038300383003830038
100243003722500001702954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000006406166529629010000103003830038300383003830038
100243003722500001472954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000006405166629629010000103003830038300383003830038
100243003722500001892954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000006406166629629110000103003830038300383003830038
100243003722500001492954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000006405165629629010000103003830038300383003830038
100243003722500001702954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000006406166529629010000103003830038300383003830038
100243003722510002122954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000006406166629629010000103003830038300383003830038
100243003722500009892954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000006405165629629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fmaxnmv h0, v8.8h
  fmaxnmv h1, v8.8h
  fmaxnmv h2, v8.8h
  fmaxnmv h3, v8.8h
  fmaxnmv h4, v8.8h
  fmaxnmv h5, v8.8h
  fmaxnmv h6, v8.8h
  fmaxnmv h7, v8.8h
  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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915048202580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039150932580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039150302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391501142580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391506952580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
802042003915074258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100053711151181161120036800001002004020040200402004020040
8020420039150302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039150302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039150302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039150302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308181e1f3a3f51inst 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150009008425801071080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001001005020111611132003680000102004020040200402004020040
80024200391500000034625800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020121611132003680000102004020040200402004020040
80024200391500000026325800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020121611132003680000102004020040200402004020040
8002420039150000008225800101080000108000050640000020020200392003999963100198001020800002280000200392003911800211091010800001000005020121612122003680000102004020040200402004020040
80024200391500000010325800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001001005020131611132003680000102004020040200402004020040
80024200391500000012425800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001001005020141614142003680000102004020040200402004020040
80024200391500100040258001010800001080000506400001200202003920039100053100198001020800002080000200392003911800211091010800001001005038141611132003680000102004020040200402004020040
80024200391500000012625800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001021005020121611112003680000102004020040200402004020040
8002420039150000006125800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020131615152003680000102004020040200402004020040
800242003915000120036725800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020111613112003680000102004020040200402004020040