Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMLE (scalar, zero, H)

Test 1: uops

Code:

  fcmle h0, h0, #0
  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)03091e3f4e51inst 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500841686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645210201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500841686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645210201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371600611686251000100010002645210201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645210201820372037157131895100010001000203720371110011000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmle h0, h0, #0
  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)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000000611968625101001001000010010000500284752112001820086200841842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820133
102042003714900000000611968625101001001000010010000500284752112001820037201331842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000000611968625101001001000010010152500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000007261968625101001001000010010000500285004912001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000200071011611197910100001002003820038200382003820038
1020420037150000000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000243071011611197910100001002003820038200382003820038
1020420037150000002100611968625101001001000010010608500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071021611197910100001002003820038200382003820038

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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715001701968625100101010000101000050284752112001820037200371844331876710010201000020101802003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715002121968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010030640216221978610000102003820038200382003820038
100242003715003821968625100101010000101000050284788712001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715001491968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150078019686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000102810640216221978610000102003820038200382003820038
10024200371500711968625100261010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500821968625100101010000101000050284752102001820037200371845931876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201018020100002003720037111002110910101000010001640216221978610000102003820038200382003820038
100242003715001491968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmle h0, h8, #0
  fcmle h1, h8, #0
  fcmle h2, h8, #0
  fcmle h3, h8, #0
  fcmle h4, h8, #0
  fcmle h5, h8, #0
  fcmle h6, h8, #0
  fcmle h7, h8, #0
  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)03091f3f51inst 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)9fa1a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006115000974258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180161020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100120311151180160020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
80204200381500092258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000022251281231120045800001002004920049200502005020049
802042004815000456268011610080016100800285006401961200282004920048997699986801282008003820080038200482004911802011009910010080000100000022251281231120046800001002004920049200502005020050
802042004915000872780116100800161008002850064019612002820049200489976109986801282008003820080038200482004911802011009910010080000100000022251281231120045800001002005020050200502004920049
802042004815000703268011610080016100800285006401961200282004820048997699986801282008003820080038200492004911802011009910010080000100000022251291231120046800001002005020049200492004920050

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e1f3a3f51inst 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)9fa0a6a7a8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150000339258001010800001080000506400000200190200382003899893100118001020800002080000200382003811800211091010800001000000005020116112003580000102003920039200392003920039
8002420038150000062258001010800001080000506400000200190200382003899893100118001020800002080000200382003811800211091010800001000000005020116112003580000102003920039200392003920039
8002420038150000162258001010800001080000506400001200190200382003899893100118001020800002080000200382003811800211091010800001000000305020116612003580000102003920039200392003920039
8002420038150000060258001010800001080000506400000200190200382003899893100118001020800002080000200382003811800211091010800001000000015020116112003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200190200382003899893100118001020800002080000200382003811800211091010800001000000005020116112003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200190200382003899893100118001020800992080099200882003821800211091010800001003104005020116112003580000102003920039200392003920088
8002420038150113288039258001010800001080000506400001200190203442003899893100118001020800002080000200382003811800211091010800001000000005020116112003580000102009920089200392003920039
8002420038150000039258001010800001080000506415361200680200962003899893100118001020800002080000200382003811800211091010800001000010005020116112003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200190200382003899893100118001020800002080000200382003811800211091010800001000000005020116112003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200190200382003899893100118001020800002080000200382003811800211091010800001000000005020116112003580000102003920039200392003920039