Apple M1 Microarchitecture Research by Dougall Johnson

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

SSHR (vector, 2D)

Test 1: uops

Code:

  sshr v0.2d, v0.2d, #3
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110003073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110001073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110002073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
10042037150126116862510001000100026452112018203720371571318951000100010002037208511100110000073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  sshr v0.2d, v0.2d, #3
  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)03080918191e1f3a3f4e51inst 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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000120061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000300071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010001100071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000103071011611197910100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000054071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000003071011611197910100001002003820038200382003820038
102042003715000000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000038072071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000403071011611197910100001002003820038200382003820038
1020420037150000000082196862510100100100001001000050028475212001820037200371844031874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000120061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst 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)72scheduler 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
1002420037150006119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010000640216321978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150006619686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371501206119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010003640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000103803640316221985010000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000104609640216221978610000102003820038200382003820082
1002420037150008919686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010103640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010106640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sshr v0.2d, v8.2d, #3
  sshr v1.2d, v8.2d, #3
  sshr v2.2d, v8.2d, #3
  sshr v3.2d, v8.2d, #3
  sshr v4.2d, v8.2d, #3
  sshr v5.2d, v8.2d, #3
  sshr v6.2d, v8.2d, #3
  sshr v7.2d, v8.2d, #3
  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)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)9fa0a8a9acc5branch mispredict (cb)cdcfd6dde0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006115005025801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100014001115118160200350800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010001001115118160200350800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000001115118160200350800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010001001115118160200350800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000001115118160200350800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010001001115118160200350800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010001001115118160200350800001002003920039200392003920039
802042003815002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100033001115118160200350800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000001115118160200350800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000231115118160200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03090b18191e1f3f51inst 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)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000001005020316112003580000102003920039200392003920039
8002420038150000081039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000001035020116112003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000001065020116222003580000102003920039200392003920039
8002420038150000000704258001010800001080000506400000200190200382003899963100188010820800002080000200382003811800211091010800001000001018635020216222003580000102003920039200392003920039
800242003815010000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000001035020158112003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000001035020116112003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000002035020116112003580000102003920039200392003920039
800242023915000000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000001035020116222003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000001035020116112003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000002035020216112003580000102003920039200392003920039