Apple M1 Microarchitecture Research by Dougall Johnson

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

SSHL (vector, 2D)

Test 1: uops

Code:

  sshl v0.2d, v0.2d, v1.2d
  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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371548611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371566611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371518611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037156611687251000100010002646800201820372037157231895100010002000203720371110011000273116111787100020382038203820382038
10042037159611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  sshl v0.2d, v0.2d, v1.2d
  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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000008219687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002061000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037151000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680120126200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037150000009006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
10204200371500000021006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
102042003715000000435006119687251010010010000100100005002847680120018200372003718422318745101002001017220020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b191e1f3f4e51inst 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000024061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100010006402162219785010000102003820038200382003820038
100242003715000000726196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500006061196872510010101000010100005028476800200180200372003718444318767101642010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
100242003715000000147196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000006402162219851010000102003820038200382003820038
1002420037150000210061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  sshl v0.2d, v1.2d, v0.2d
  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)9fa0a8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715002961968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715036611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715018841968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161120034100001002003820038200382003820038
102042003715007261968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100050007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150228611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100030007101161119791100001002003820038200382003820038
10204200371500821968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242008415113010319687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010010640216221978510000102003820038200382003820038
100242003715001210319687251001010100001110000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010010640216221978510000102003820038200382003820038
10024200371500786119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010003640216221978510000102003820038200382003820038
10024200371500366119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010003640216221978510000102003820038200382003820038
10024200371500156119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010220640216221978510000102003820038200382008620038
1002420037150036119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150096119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500156119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500696119687251001010100001010000552847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  sshl v0.2d, v8.2d, v9.2d
  sshl v1.2d, v8.2d, v9.2d
  sshl v2.2d, v8.2d, v9.2d
  sshl v3.2d, v8.2d, v9.2d
  sshl v4.2d, v8.2d, v9.2d
  sshl v5.2d, v8.2d, v9.2d
  sshl v6.2d, v8.2d, v9.2d
  sshl v7.2d, v8.2d, v9.2d
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)030818191e1f3a3f51inst 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)9fa0a1a8a9acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591500038402452580100100800001008000050064000002006920038200389973399968010020080000200160000200382003811802011009910010080000100000000051148169920035800001002003920039200392003920039
8020420038150000002452580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051149169920035800001002003920039200392003920039
80204200381490001202452580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051149169920035800001002003920039200392003920039
8020420038150000002452580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000030051147167720035800001002003920039200392003920039
80204200381500009024525801001008000010080000500640000120019200382003899733100238010020080000200160000200922003811802011009910010080000100005000051149167720035800001002003920039200982009020039
80204200381501036024525801001008000010080000500640000020019201932019499731210153807142008058420216116620192203497180201100991001008000010020122823005220161029920035800001002003920039200392003920039
80204200381500004502452580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051149169920035800001002003920039200392003920039
8020420038150000300287258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010004000005114416101020085800001002003920039200392003920039
802042003815000030024525801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511495291120035800001002003920039200392003920039
80204200861610100024525801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511416169920035800001002003920039200392003920039

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)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)9fa0a8accfd0d5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150231392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000502007167520035080000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502005167520035080000102003920039200392003920039
800242003815066392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010009502007167520035080000102003920039200392003920039
8002420038150967042580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502007167520035080000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502007167520035080000102003920039200392003920039
800242003815024392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502005167720035880000102003920039200392003920039
80024200381500392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000502007168520035080000102003920039200392003920039
800242003815015392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502005167520035080000102003920039200392003920039
8002420038150275142580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000502005167520035080000102003920039200392003920039
80024200381500392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000502007165720035080000102003920039200392003920039