[llvm] r177105 - ARM cost model: Increase cost of some vector selects we do terrible on
Arnold Schwaighofer
aschwaighofer at apple.com
Thu Mar 14 12:17:02 PDT 2013
Author: arnolds
Date: Thu Mar 14 14:17:02 2013
New Revision: 177105
URL: http://llvm.org/viewvc/llvm-project?rev=177105&view=rev
Log:
ARM cost model: Increase cost of some vector selects we do terrible on
By terrible I mean we store/load from the stack.
This matters on PAQp8 in _Z5trainPsS_ii (which is inlined into Mixer::update)
where we decide to vectorize a loop with a VF of 8 resulting in a 25%
degradation on a cortex-a8.
LV: Found an estimated cost of 2 for VF 8 For instruction: icmp slt i32
LV: Found an estimated cost of 2 for VF 8 For instruction: select i1, i32, i32
The bug that tracks the CodeGen part is PR14868.
radar://13403975
Modified:
llvm/trunk/lib/Target/ARM/ARMTargetTransformInfo.cpp
llvm/trunk/test/Analysis/CostModel/ARM/select.ll
llvm/trunk/test/CodeGen/ARM/vselect_imax.ll
Modified: llvm/trunk/lib/Target/ARM/ARMTargetTransformInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM/ARMTargetTransformInfo.cpp?rev=177105&r1=177104&r2=177105&view=diff
==============================================================================
--- llvm/trunk/lib/Target/ARM/ARMTargetTransformInfo.cpp (original)
+++ llvm/trunk/lib/Target/ARM/ARMTargetTransformInfo.cpp Thu Mar 14 14:17:02 2013
@@ -334,6 +334,30 @@ unsigned ARMTTI::getCmpSelInstrCost(unsi
int ISD = TLI->InstructionOpcodeToISD(Opcode);
// On NEON a a vector select gets lowered to vbsl.
if (ST->hasNEON() && ValTy->isVectorTy() && ISD == ISD::SELECT) {
+ // Lowering of some vector selects is currently far from perfect.
+ static const TypeConversionCostTblEntry<MVT> NEONVectorSelectTbl[] = {
+ { ISD::SELECT, MVT::v4i1, MVT::v4i8, 2*4 + 2*1 },
+ { ISD::SELECT, MVT::v8i1, MVT::v8i8, 2*8 + 1 },
+ { ISD::SELECT, MVT::v16i1, MVT::v16i8, 2*16 + 1 },
+ { ISD::SELECT, MVT::v4i1, MVT::v4i16, 2*4 + 1 },
+ { ISD::SELECT, MVT::v8i1, MVT::v8i16, 2*8 + 1 },
+ { ISD::SELECT, MVT::v16i1, MVT::v16i16, 2*16 + 1 + 3*1 + 4*1 },
+ { ISD::SELECT, MVT::v8i1, MVT::v8i32, 4*8 + 1*3 + 1*4 + 1*2 },
+ { ISD::SELECT, MVT::v16i1, MVT::v16i32, 4*16 + 1*6 + 1*8 + 1*4 },
+ { ISD::SELECT, MVT::v4i1, MVT::v4i64, 4*4 + 1*2 + 1 },
+ { ISD::SELECT, MVT::v8i1, MVT::v8i64, 50 },
+ { ISD::SELECT, MVT::v16i1, MVT::v16i64, 100 }
+ };
+
+ EVT SelCondTy = TLI->getValueType(CondTy);
+ EVT SelValTy = TLI->getValueType(ValTy);
+ int Idx = ConvertCostTableLookup<MVT>(NEONVectorSelectTbl,
+ array_lengthof(NEONVectorSelectTbl),
+ ISD, SelCondTy.getSimpleVT(),
+ SelValTy.getSimpleVT());
+ if (Idx != -1)
+ return NEONVectorSelectTbl[Idx].Cost;
+
std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(ValTy);
return LT.first;
}
Modified: llvm/trunk/test/Analysis/CostModel/ARM/select.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Analysis/CostModel/ARM/select.ll?rev=177105&r1=177104&r2=177105&view=diff
==============================================================================
--- llvm/trunk/test/Analysis/CostModel/ARM/select.ll (original)
+++ llvm/trunk/test/Analysis/CostModel/ARM/select.ll Thu Mar 14 14:17:02 2013
@@ -21,26 +21,39 @@ define void @casts() {
; Vector values
; CHECK: cost of 1 {{.*}} select
%v7 = select <2 x i1> undef, <2 x i8> undef, <2 x i8> undef
- ; CHECK: cost of 1 {{.*}} select
+ ; CHECK: cost of 10 {{.*}} select
%v8 = select <4 x i1> undef, <4 x i8> undef, <4 x i8> undef
- ; CHECK: cost of 1 {{.*}} select
+ ; CHECK: cost of 17 {{.*}} select
%v9 = select <8 x i1> undef, <8 x i8> undef, <8 x i8> undef
- ; CHECK: cost of 1 {{.*}} select
+ ; CHECK: cost of 33 {{.*}} select
%v10 = select <16 x i1> undef, <16 x i8> undef, <16 x i8> undef
; CHECK: cost of 1 {{.*}} select
%v11 = select <2 x i1> undef, <2 x i16> undef, <2 x i16> undef
- ; CHECK: cost of 1 {{.*}} select
+ ; CHECK: cost of 9 {{.*}} select
%v12 = select <4 x i1> undef, <4 x i16> undef, <4 x i16> undef
- ; CHECK: cost of 1 {{.*}} select
+ ; CHECK: cost of 17 {{.*}} select
%v13 = select <8 x i1> undef, <8 x i16> undef, <8 x i16> undef
+ ; CHECK: cost of 40 {{.*}} select
+ %v13b = select <16 x i1> undef, <16 x i16> undef, <16 x i16> undef
; CHECK: cost of 1 {{.*}} select
%v14 = select <2 x i1> undef, <2 x i32> undef, <2 x i32> undef
; CHECK: cost of 1 {{.*}} select
%v15 = select <4 x i1> undef, <4 x i32> undef, <4 x i32> undef
+ ; CHECK: cost of 41 {{.*}} select
+ %v15b = select <8 x i1> undef, <8 x i32> undef, <8 x i32> undef
+ ; CHECK: cost of 82 {{.*}} select
+ %v15c = select <16 x i1> undef, <16 x i32> undef, <16 x i32> undef
+
; CHECK: cost of 1 {{.*}} select
%v16 = select <2 x i1> undef, <2 x i64> undef, <2 x i64> undef
+ ; CHECK: cost of 19 {{.*}} select
+ %v16a = select <4 x i1> undef, <4 x i64> undef, <4 x i64> undef
+ ; CHECK: cost of 50 {{.*}} select
+ %v16b = select <8 x i1> undef, <8 x i64> undef, <8 x i64> undef
+ ; CHECK: cost of 100 {{.*}} select
+ %v16c = select <16 x i1> undef, <16 x i64> undef, <16 x i64> undef
; CHECK: cost of 1 {{.*}} select
%v17 = select <2 x i1> undef, <2 x float> undef, <2 x float> undef
Modified: llvm/trunk/test/CodeGen/ARM/vselect_imax.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/ARM/vselect_imax.ll?rev=177105&r1=177104&r2=177105&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/ARM/vselect_imax.ll (original)
+++ llvm/trunk/test/CodeGen/ARM/vselect_imax.ll Thu Mar 14 14:17:02 2013
@@ -10,3 +10,210 @@ define void @vmax_v4i32(<4 x i32>* %m, <
ret void
}
+; We adjusted the cost model of the following selects. When we improve code
+; lowering we also need to adjust the cost.
+; RUN: opt < %s -cost-model -analyze -mtriple=thumbv7-apple-ios6.0.0 -march=arm -mcpu=cortex-a8 | FileCheck %s --check-prefix=COST
+%T0_3 = type <4 x i8>
+%T1_3 = type <4 x i1>
+; CHECK: func_blend3:
+define void @func_blend3(%T0_3* %loadaddr, %T0_3* %loadaddr2,
+ %T1_3* %blend, %T0_3* %storeaddr) {
+; CHECK: strh
+; CHECK: strh
+; CHECK: strh
+; CHECK: strh
+; CHECK: vldr
+ %v0 = load %T0_3* %loadaddr
+ %v1 = load %T0_3* %loadaddr2
+ %c = load %T1_3* %blend
+; COST: func_blend3
+; COST: cost of 10 {{.*}} select
+ %r = select %T1_3 %c, %T0_3 %v0, %T0_3 %v1
+ store %T0_3 %r, %T0_3* %storeaddr
+ ret void
+}
+%T0_4 = type <8 x i8>
+%T1_4 = type <8 x i1>
+; CHECK: func_blend4:
+define void @func_blend4(%T0_4* %loadaddr, %T0_4* %loadaddr2,
+ %T1_4* %blend, %T0_4* %storeaddr) {
+ %v0 = load %T0_4* %loadaddr
+ %v1 = load %T0_4* %loadaddr2
+ %c = load %T1_4* %blend
+; check: strb
+; check: strb
+; check: strb
+; check: strb
+; check: vldr
+; COST: func_blend4
+; COST: cost of 17 {{.*}} select
+ %r = select %T1_4 %c, %T0_4 %v0, %T0_4 %v1
+ store %T0_4 %r, %T0_4* %storeaddr
+ ret void
+}
+%T0_5 = type <16 x i8>
+%T1_5 = type <16 x i1>
+; CHECK: func_blend5:
+define void @func_blend5(%T0_5* %loadaddr, %T0_5* %loadaddr2,
+ %T1_5* %blend, %T0_5* %storeaddr) {
+ %v0 = load %T0_5* %loadaddr
+ %v1 = load %T0_5* %loadaddr2
+ %c = load %T1_5* %blend
+; CHECK: strb
+; CHECK: strb
+; CHECK: strb
+; CHECK: strb
+; CHECK: vld
+; COST: func_blend5
+; COST: cost of 33 {{.*}} select
+ %r = select %T1_5 %c, %T0_5 %v0, %T0_5 %v1
+ store %T0_5 %r, %T0_5* %storeaddr
+ ret void
+}
+%T0_8 = type <4 x i16>
+%T1_8 = type <4 x i1>
+; CHECK: func_blend8:
+define void @func_blend8(%T0_8* %loadaddr, %T0_8* %loadaddr2,
+ %T1_8* %blend, %T0_8* %storeaddr) {
+ %v0 = load %T0_8* %loadaddr
+ %v1 = load %T0_8* %loadaddr2
+ %c = load %T1_8* %blend
+; CHECK: strh
+; CHECK: strh
+; CHECK: strh
+; CHECK: strh
+; CHECK: vld
+; COST: func_blend8
+; COST: cost of 9 {{.*}} select
+ %r = select %T1_8 %c, %T0_8 %v0, %T0_8 %v1
+ store %T0_8 %r, %T0_8* %storeaddr
+ ret void
+}
+%T0_9 = type <8 x i16>
+%T1_9 = type <8 x i1>
+; CHECK: func_blend9:
+define void @func_blend9(%T0_9* %loadaddr, %T0_9* %loadaddr2,
+ %T1_9* %blend, %T0_9* %storeaddr) {
+ %v0 = load %T0_9* %loadaddr
+ %v1 = load %T0_9* %loadaddr2
+ %c = load %T1_9* %blend
+; CHECK: strh
+; CHECK: strh
+; CHECK: strh
+; CHECK: strh
+; CHECK: vld
+; COST: func_blend9
+; COST: cost of 17 {{.*}} select
+ %r = select %T1_9 %c, %T0_9 %v0, %T0_9 %v1
+ store %T0_9 %r, %T0_9* %storeaddr
+ ret void
+}
+%T0_10 = type <16 x i16>
+%T1_10 = type <16 x i1>
+; CHECK: func_blend10:
+define void @func_blend10(%T0_10* %loadaddr, %T0_10* %loadaddr2,
+ %T1_10* %blend, %T0_10* %storeaddr) {
+ %v0 = load %T0_10* %loadaddr
+ %v1 = load %T0_10* %loadaddr2
+ %c = load %T1_10* %blend
+; CHECK: strb
+; CHECK: strb
+; CHECK: strb
+; CHECK: strb
+; CHECK: vld
+; COST: func_blend10
+; COST: cost of 40 {{.*}} select
+ %r = select %T1_10 %c, %T0_10 %v0, %T0_10 %v1
+ store %T0_10 %r, %T0_10* %storeaddr
+ ret void
+}
+%T0_14 = type <8 x i32>
+%T1_14 = type <8 x i1>
+; CHECK: func_blend14:
+define void @func_blend14(%T0_14* %loadaddr, %T0_14* %loadaddr2,
+ %T1_14* %blend, %T0_14* %storeaddr) {
+ %v0 = load %T0_14* %loadaddr
+ %v1 = load %T0_14* %loadaddr2
+ %c = load %T1_14* %blend
+; CHECK: strb
+; CHECK: strb
+; CHECK: strb
+; CHECK: strb
+; COST: func_blend14
+; COST: cost of 41 {{.*}} select
+ %r = select %T1_14 %c, %T0_14 %v0, %T0_14 %v1
+ store %T0_14 %r, %T0_14* %storeaddr
+ ret void
+}
+%T0_15 = type <16 x i32>
+%T1_15 = type <16 x i1>
+; CHECK: func_blend15:
+define void @func_blend15(%T0_15* %loadaddr, %T0_15* %loadaddr2,
+ %T1_15* %blend, %T0_15* %storeaddr) {
+ %v0 = load %T0_15* %loadaddr
+ %v1 = load %T0_15* %loadaddr2
+ %c = load %T1_15* %blend
+; CHECK: strb
+; CHECK: strb
+; CHECK: strb
+; CHECK: strb
+; COST: func_blend15
+; COST: cost of 82 {{.*}} select
+ %r = select %T1_15 %c, %T0_15 %v0, %T0_15 %v1
+ store %T0_15 %r, %T0_15* %storeaddr
+ ret void
+}
+%T0_18 = type <4 x i64>
+%T1_18 = type <4 x i1>
+; CHECK: func_blend18:
+define void @func_blend18(%T0_18* %loadaddr, %T0_18* %loadaddr2,
+ %T1_18* %blend, %T0_18* %storeaddr) {
+ %v0 = load %T0_18* %loadaddr
+ %v1 = load %T0_18* %loadaddr2
+ %c = load %T1_18* %blend
+; CHECK: strh
+; CHECK: strh
+; CHECK: strh
+; CHECK: strh
+; COST: func_blend18
+; COST: cost of 19 {{.*}} select
+ %r = select %T1_18 %c, %T0_18 %v0, %T0_18 %v1
+ store %T0_18 %r, %T0_18* %storeaddr
+ ret void
+}
+%T0_19 = type <8 x i64>
+%T1_19 = type <8 x i1>
+; CHECK: func_blend19:
+define void @func_blend19(%T0_19* %loadaddr, %T0_19* %loadaddr2,
+ %T1_19* %blend, %T0_19* %storeaddr) {
+ %v0 = load %T0_19* %loadaddr
+ %v1 = load %T0_19* %loadaddr2
+ %c = load %T1_19* %blend
+; CHECK: strb
+; CHECK: strb
+; CHECK: strb
+; CHECK: strb
+; COST: func_blend19
+; COST: cost of 50 {{.*}} select
+ %r = select %T1_19 %c, %T0_19 %v0, %T0_19 %v1
+ store %T0_19 %r, %T0_19* %storeaddr
+ ret void
+}
+%T0_20 = type <16 x i64>
+%T1_20 = type <16 x i1>
+; CHECK: func_blend20:
+define void @func_blend20(%T0_20* %loadaddr, %T0_20* %loadaddr2,
+ %T1_20* %blend, %T0_20* %storeaddr) {
+ %v0 = load %T0_20* %loadaddr
+ %v1 = load %T0_20* %loadaddr2
+ %c = load %T1_20* %blend
+; CHECK: strb
+; CHECK: strb
+; CHECK: strb
+; CHECK: strb
+; COST: func_blend20
+; COST: cost of 100 {{.*}} select
+ %r = select %T1_20 %c, %T0_20 %v0, %T0_20 %v1
+ store %T0_20 %r, %T0_20* %storeaddr
+ ret void
+}
More information about the llvm-commits
mailing list