Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMULH (by element, 4S)

Test 1: uops

Code:

  sqdmulh v0.4s, v0.4s, v1.s[1]
  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)03181e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a0cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220061254825100010001000398313301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037230061254825100010001000398313301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037230061254825100010001000398313301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037230061254825100010001000398313301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037230061254825100010001000398313301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037230061254825100010001000398313301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037220061254825100010001000398313301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037230061254825100010001000398313301830373037241532895100010002000303730371110011000073216222702100030383038303830383038
100430372301861254825100010001000398313301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
100430372201261254825100010001000398313301830373037241532895100010002000303730371110011000073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqdmulh v0.4s, v0.4s, v1.s[1]
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010002107101161129634100001003003830038300383003830038
102043003722500000103295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372240000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830228
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000204200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500012061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000107101161129634100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010004307101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010001207101321129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295482510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100001506402162229668010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037211002110910101000010000306402162229630010000103003830038302273003830038
100243003722506129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000006402162229630210000103003830038300383003830038
1002430037225126129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372251261295482510010101000010100005042773131300180301783017828297112878710462221000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000554277313130018030037300372828732876710010201000020200003003730037111002110910101000010000006402412229630010000103003830038300383003830038
1002430037225396129548251001010100001010000504277313130018030037300372828732876710010221000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037226012429548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037211002110910101000010000006402162229630010000103003830227300383003830038
1002430037225023129548251001010100001010000504277313130018030037300372828732876710010201066420200003003730037111002110910101000010000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqdmulh v0.4s, v1.4s, v0.s[1]
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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)696b6d6edispatch 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)9fa0a8branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225061295482510100100100001001000050042773133001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773133001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773133001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773133001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225084295482510100100100001001000050042773133001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003023330038300383003830038
1020430037224061295482510110100100001001000050042810023001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129702100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773133001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773133001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372243061295482510100100100001001000054742773133001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773133001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830087300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030a181e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000631295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295392510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216642963010000103008530225301793013230085
100243003722506061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828726287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500084295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001020640216222963010000103003830038300383003830038
100243003722400061295482510010101000010100005042773130300183003730085282873287671001020100002020000300373003711100211091010100001003640216222963010000103003830038300383003830038
100243003722500084295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqdmulh v0.4s, v8.4s, v9.s[1]
  sqdmulh v1.4s, v8.4s, v9.s[1]
  sqdmulh v2.4s, v8.4s, v9.s[1]
  sqdmulh v3.4s, v8.4s, v9.s[1]
  sqdmulh v4.4s, v8.4s, v9.s[1]
  sqdmulh v5.4s, v8.4s, v9.s[1]
  sqdmulh v6.4s, v8.4s, v9.s[1]
  sqdmulh v7.4s, v8.4s, v9.s[1]
  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)03181e1f3f51inst 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)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
8020420060150000374258010010080000100800005006400002002020039200399973039997801002008000020016000020039200391180201100991001008000010000051107164420036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973039997801002008000020016000020039200391180201100991001008000010000051103165420036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020113200399982039997801002008000020016000020039200391180201100991001008000010000651105165520036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973039997801002008000020016000020039200391180201100991001008000010000051105164520036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973039997801002008000020016000020039200391180201100991001008000010000051105165420036800001002004020040200402004020040
802042003915000062258010010080000100800005006400002002020039200399973039997801002008000020016000020039200391180201100991001008000010000051105166520036800001002004020040200402004020040
802042003915000041258010010080000100800005006407882002020039200399973039997801002008000020016000020039200391180201100991001008000010000051104165420036800001002004020040200402004020040
8020420039150000421258010010080000100800005006400002002020039200399973039997801002008000020016000020039200391180201100991001008000010000051104165420036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973039997801002008000020016000020039200391180201100991001008000010000651104165620036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973039997801002008000020016000020039200391180201100991001008000010000051105163520036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03091e3f51inst 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)5f60696b6d6edispatch 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)9fa8accficache miss (d3)d5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500040258001010800001080000506400000120020020039200399996310019800102080000201600002003920039118002110910108000010005020017161717200360080000102024320040200402004020040
80024200391500070525800101080000108000050640000112002002003920039999631001980010208000020160000200392003921800211091010800001000502001716177200360080000102004020040200402004020040
800242003915000402580010108000010800005064000001200200200392003999963100198001020800002016000020039200391180021109101080000100050200716147200360080000102004020040200402004020040
800242003915000402580010108000010800005064000001200200200392003999963100198001020800002016000020039200391180021109101080000100050200716177200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000012002002003920039999631001980010208000020160000200392003911800211091010800001019350200716717200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000012002002003920039999631001980010208000020160000200392003911800211091010800001003502001716717200360080000102004020040200402004020040
800242003915000402580010108000010800005064000000200200200392003999963100198001020800002016000020039200391180021109101080000100050201171617172003615580000102004020040200402004020040
8002420039150004025800101080000108000050640000002002002003920039999631001980010208000020160000200392003911800211091010800001000502007161717200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000012002002003920039999631001980010208000020160000200392003911800211091010800001000502001716717200360080000102004020040200402004020040
800242003915000462580010108000010800005064000001200200200392003999963100198001020800002016000020039200391180021109101080000100050200716714200360080000102004020040200402004020040