Apple M1 Microarchitecture Research by Dougall Johnson

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

CMLT (zero, 2D)

Test 1: uops

Code:

  cmlt 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)0318191e3f4e51inst 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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371600061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715011261168625100010001000264521020182037203715713189510001000100020372037111001100000373116111786100020382038203820382038
100420371500061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmlt 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)03081e3f4e51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000374111611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000371011611197910100001002003820038200382003820038
10204200371500068919686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500156119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037149006119686251010010010000100100005002847521120018200852008518421318745101002001000020010000200372008521102011009910010010000100304371011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)033f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010200640216221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010300640216221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371505361968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037211002110910101000010103640216221978610000102003820038200382003820038
100242003715061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000165640216221978610000102003820038200382003820038
100242003715061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000219640216221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmlt v0.2d, v8.2d, #0
  cmlt v1.2d, v8.2d, #0
  cmlt v2.2d, v8.2d, #0
  cmlt v3.2d, v8.2d, #0
  cmlt v4.2d, v8.2d, #0
  cmlt v5.2d, v8.2d, #0
  cmlt v6.2d, v8.2d, #0
  cmlt 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)030a1e3f51inst 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)cdcfd6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100212111511816020035800001002003920039200392003920039
80204200981500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100560111511816020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010016111511816020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010026111511816020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010013111511816020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010006111511816020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010020111511816020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010010111511816020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3a3f51inst 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)9fa0a6a7a8a9acc2cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000000000039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000020005020504164320035080000102003920039200392003920039
800242003815000000000039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000000005020502164220035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000015200192003820038999631001880010208000020800002003820038118002110910108000010000101505020502162420035080000102003920039200392003920039
800242003815000000000039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000000005020502164220035080000102003920039200392003920039
8002420038150000000000419258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000020005020502164220035080000102003920039200392003920039
800242003815000000000039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000000005020502164420035080000102003920039200392003920039
800242003815000000000039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000010305020504164220035080000102003920039200392003920039
800242003815000000000039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000000005020504164220035080000102003920039200392003920039
800242003815000000000062258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000000005020502162420035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000015200192003820038999631001880010208000020800002003820038118002110910108000010000480605020502162420035080000102003920039200392003920039