Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMLE (vector, zero, 2D)

Test 1: uops

Code:

  fcmle v0.2d, v0.2d, #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)03081e3f4e51inst 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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000273116111786100020382038203820382038
100420371600841686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371600611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371600611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371600611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmle v0.2d, v0.2d, #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)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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150072619686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000381271011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010002371011611197910100001002003820038200382003820038
1020420037149061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000371011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150061196752510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010002071011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010003371011611197910100001002003820038200382003820038
10204200371500103196862510100100100001001000050028475212001820037200371842131874510100200100002001000020084200371110201100991001001000010003071011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010002371011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000371011611197910100001002003820038200382003820038
10204200371500892196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030f1e3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715020611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003714900611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150007091968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715000661968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmle v0.2d, v8.2d, #0
  fcmle v1.2d, v8.2d, #0
  fcmle v2.2d, v8.2d, #0
  fcmle v3.2d, v8.2d, #0
  fcmle v4.2d, v8.2d, #0
  fcmle v5.2d, v8.2d, #0
  fcmle v6.2d, v8.2d, #0
  fcmle v7.2d, v8.2d, #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)03081e3f51inst 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)9fa0a7a8acc5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
80204200381500329258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001011151181620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100200011151181620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
80204200381490029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000502071696200357380000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100000502091679200357380000102003920039200392003920039
800242003815000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000305020101696200357380000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100000502071699200358880000102003920039200392003920039
80024200381500000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000502071679200357380000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100100502010161111200357380000102003920039200392003920039
800242003815000003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020111699200358980000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100000502091696200358880000102003920039200392003920039
80024200381500000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000502091669200358880000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000050201116117200357380000102003920039200392003920039