Apple M1 Microarchitecture Research by Dougall Johnson

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

NEG (vector, 4H)

Test 1: uops

Code:

  neg v0.4h, v0.4h
  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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203716061168625100010001000264521120182037203715713189510001000100020372037111001100073216221786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100073216221786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100073216221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100073216221786100020382038203820382038
1004203715661168625100010001000264521020182037203715713189510001000100020372037111001100073216221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100073216221786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100073216221786100020382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100073216221786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100073216221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  neg v0.4h, v0.4h
  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)0309191e3f4e51inst 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)9fa0a8c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500097261968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715500273611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200841510042611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020085200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500012611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150009611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110202100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150006611968645101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010003071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006403163319786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006403163419786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000007053163319786010000102003820038200382003820038
1002420037149000000611968625100121010000101000050284878512001820037200371844331876710010201000020100002003720037111002110910101000010000000006403163319786010000102003820038200382003820038
1002420037150000000611968625100101210000101000060284752112001820037200371844331876710012201000020100002003720037111002110910101000010000000006403163319786010000102003820038200382008520038
10024200371500001800611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006403163319786010000102003820038200382003820038
10024200371500001200611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006403164319786010000102003820038200382003820038
100242003715000019800611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006403163319786010000102003820038200382003820038
1002420037150000000611968625100101010012101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006423163319786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006404163319786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  neg v0.4h, v8.4h
  neg v1.4h, v8.4h
  neg v2.4h, v8.4h
  neg v3.4h, v8.4h
  neg v4.4h, v8.4h
  neg v5.4h, v8.4h
  neg v6.4h, v8.4h
  neg v7.4h, v8.4h
  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)03181e3f51inst 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)9fa0a1a6acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200491500602925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511821633200350800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511831633200350800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511831633200350800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511831634200350800001002003920039200392003920039
80204200381500692925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511841643200350800001002003920039200392003920039
80204200381500069425801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511841634200350800001002003920039200392003920039
80204200381490182925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511831643200350800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511831633200350800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511841634200350800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511841643200350800001002003920039200392003920039

1000 unrolls and 10 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005315003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020516662003580000102003920039200392003920039
8002420038150639258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100785020516662003580000102003920039200392003920039
800242005015007425800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020616762003580000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020716562003580000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020616652003580000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208013220800002003820038118002110910108000010005020816652003580000102003920039200392003920039
800242004815003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020816772003580000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020616642003580000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020616772003580000102003920039200392003920039
8002420038150058725800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020516772003580000102003920039200392003920039