[PATCH] D75016: [X86][TwoAddressInstructionPass] Teach tryInstructionCommute to continue checking for commutable FMA operands in more cases.
Chris Elrod via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Sun Feb 21 23:16:52 PST 2021
chriselrod added a comment.
Herald added a subscriber: pengfei.
I'm still seeing this for a complex dot product on LLVM 11.0.1. Godbolt example <https://godbolt.org/z/z53fzP>
llvm
L61: ; preds = %L61, %L30.preheader
%value_phi20178 = phi <8 x double> [ %res.i118, %L61 ], [ zeroinitializer, %L30.preheader ]
%value_phi19177 = phi <8 x double> [ %res.i119, %L61 ], [ zeroinitializer, %L30.preheader ]
%value_phi16176 = phi <8 x double> [ %res.i124, %L61 ], [ zeroinitializer, %L30.preheader ]
%value_phi15175 = phi <8 x double> [ %res.i125, %L61 ], [ zeroinitializer, %L30.preheader ]
%value_phi9174 = phi i64 [ %ptr.2.i114, %L61 ], [ %11, %L30.preheader ]
%value_phi173 = phi i64 [ %ptr.2.i117, %L61 ], [ %10, %L30.preheader ]
%ptr.1.i148 = inttoptr i64 %value_phi173 to <16 x double>*
%res.i149 = load <16 x double>, <16 x double>* %ptr.1.i148, align 8
%res.i147 = shufflevector <16 x double> %res.i149, <16 x double> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
%res.i146 = shufflevector <16 x double> %res.i149, <16 x double> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
%ptr.0.i143 = inttoptr i64 %value_phi173 to double*
%ptr.1.i144 = getelementptr inbounds double, double* %ptr.0.i143, i64 16
%ptr.1.i141 = bitcast double* %ptr.1.i144 to <16 x double>*
%res.i142 = load <16 x double>, <16 x double>* %ptr.1.i141, align 8
%res.i140 = shufflevector <16 x double> %res.i142, <16 x double> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
%res.i139 = shufflevector <16 x double> %res.i142, <16 x double> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
%ptr.1.i137 = inttoptr i64 %value_phi9174 to <16 x double>*
%res.i138 = load <16 x double>, <16 x double>* %ptr.1.i137, align 8
%res.i136 = shufflevector <16 x double> %res.i138, <16 x double> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
%res.i135 = shufflevector <16 x double> %res.i138, <16 x double> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
%ptr.0.i132 = inttoptr i64 %value_phi9174 to double*
%ptr.1.i133 = getelementptr inbounds double, double* %ptr.0.i132, i64 16
%ptr.1.i130 = bitcast double* %ptr.1.i133 to <16 x double>*
%res.i131 = load <16 x double>, <16 x double>* %ptr.1.i130, align 8
%res.i129 = shufflevector <16 x double> %res.i131, <16 x double> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
%res.i128 = shufflevector <16 x double> %res.i131, <16 x double> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
%res.i127 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i146, <8 x double> %res.i135, <8 x double> %value_phi15175)
%res.i126 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i139, <8 x double> %res.i128, <8 x double> %value_phi16176)
%res.i125 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i147, <8 x double> %res.i136, <8 x double> %res.i127)
%res.i124 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i140, <8 x double> %res.i129, <8 x double> %res.i126)
%res.i123 = fneg nsz contract <8 x double> %res.i146
%res.i122 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i123, <8 x double> %res.i136, <8 x double> %value_phi19177)
%res.i121 = fneg nsz contract <8 x double> %res.i139
%res.i120 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i121, <8 x double> %res.i129, <8 x double> %value_phi20178)
%res.i119 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i147, <8 x double> %res.i135, <8 x double> %res.i122)
%res.i118 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i140, <8 x double> %res.i128, <8 x double> %res.i120)
%ptr.1.i116 = getelementptr inbounds double, double* %ptr.0.i143, i64 32
%ptr.2.i117 = ptrtoint double* %ptr.1.i116 to i64
%ptr.1.i113 = getelementptr inbounds double, double* %ptr.0.i132, i64 32
%ptr.2.i114 = ptrtoint double* %ptr.1.i113 to i64
%.not = icmp ugt double* %ptr.1.i116, %ptr.1.i157
br i1 %.not, label %L88, label %L61
asm
.LBB0_5: # %L61
vmovupd zmm8, zmmword ptr [rsi]
vmovupd zmm6, zmmword ptr [rsi + 64]
vmovupd zmm9, zmmword ptr [rsi + 128]
vmovupd zmm7, zmmword ptr [rsi + 192]
vmovapd zmm10, zmm8
vpermt2pd zmm10, zmm2, zmm6
vpermt2pd zmm8, zmm3, zmm6
vmovapd zmm11, zmm9
vpermt2pd zmm11, zmm2, zmm7
vmovupd zmm12, zmmword ptr [rdx]
vmovupd zmm13, zmmword ptr [rdx + 64]
vmovupd zmm14, zmmword ptr [rdx + 128]
vpermt2pd zmm9, zmm3, zmm7
vmovupd zmm15, zmmword ptr [rdx + 192]
vmovapd zmm6, zmm12
vpermt2pd zmm6, zmm2, zmm13
vpermt2pd zmm12, zmm3, zmm13
vmovapd zmm7, zmm14
vpermt2pd zmm7, zmm2, zmm15
vpermt2pd zmm14, zmm3, zmm15
vfmadd231pd zmm0, zmm8, zmm12 # zmm0 = (zmm8 * zmm12) + zmm0
vfmadd231pd zmm1, zmm9, zmm14 # zmm1 = (zmm9 * zmm14) + zmm1
vfmadd231pd zmm0, zmm10, zmm6 # zmm0 = (zmm10 * zmm6) + zmm0
vfmadd231pd zmm1, zmm11, zmm7 # zmm1 = (zmm11 * zmm7) + zmm1
vfmsub213pd zmm6, zmm8, zmm5 # zmm6 = (zmm8 * zmm6) - zmm5
vfmsub213pd zmm7, zmm9, zmm4 # zmm7 = (zmm9 * zmm7) - zmm4
vfmsub231pd zmm6, zmm10, zmm12 # zmm6 = (zmm10 * zmm12) - zmm6
vfmsub231pd zmm7, zmm11, zmm14 # zmm7 = (zmm11 * zmm14) - zmm7
add rsi, 256
add rdx, 256
vmovapd zmm4, zmm7
vmovapd zmm5, zmm6
cmp rsi, r11
jbe .LBB0_5
Note the
asm
vfmsub213pd zmm6, zmm8, zmm5 # zmm6 = (zmm8 * zmm6) - zmm5
vfmsub213pd zmm7, zmm9, zmm4 # zmm7 = (zmm9 * zmm7) - zmm4
vfmsub231pd zmm6, zmm10, zmm12 # zmm6 = (zmm10 * zmm12) - zmm6
vfmsub231pd zmm7, zmm11, zmm14 # zmm7 = (zmm11 * zmm14) - zmm7
# ...
vmovapd zmm4, zmm7
vmovapd zmm5, zmm6
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D75016/new/
https://reviews.llvm.org/D75016
More information about the llvm-commits
mailing list