From: Roland Froese Date: Fri, 26 Apr 2019 16:14:17 +0000 (+0000) Subject: [PowerPC] Update P9 vector costs for insert/extract element X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=61c60646999520b92267e6cbbb7513e9c109f298;p=llvm [PowerPC] Update P9 vector costs for insert/extract element The PPC vector cost model values for insert/extract element reflect older processors that lacked vector insert/extract and move-to/move-from VSR instructions. Update getVectorInstrCost to give appropriate values for when the newer instructions are present. Differential Revision: https://reviews.llvm.org/D60160 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@359313 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/lib/Target/PowerPC/PPCTargetTransformInfo.cpp b/lib/Target/PowerPC/PPCTargetTransformInfo.cpp index 6185355f419..1fdaec076b1 100644 --- a/lib/Target/PowerPC/PPCTargetTransformInfo.cpp +++ b/lib/Target/PowerPC/PPCTargetTransformInfo.cpp @@ -412,6 +412,35 @@ int PPCTTIImpl::getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index) { return 0; return Cost; + + } else if (Val->getScalarType()->isIntegerTy() && Index != -1U) { + if (ST->hasP9Altivec()) { + if (ISD == ISD::INSERT_VECTOR_ELT) + // A move-to VSR and a permute/insert. Assume vector operation cost + // for both (cost will be 2x on P9). + return vectorCostAdjustment(2, Opcode, Val, nullptr); + + // It's an extract. Maybe we can do a cheap move-from VSR. + unsigned EltSize = Val->getScalarSizeInBits(); + if (EltSize == 64) { + unsigned MfvsrdIndex = ST->isLittleEndian() ? 1 : 0; + if (Index == MfvsrdIndex) + return 1; + } else if (EltSize == 32) { + unsigned MfvsrwzIndex = ST->isLittleEndian() ? 2 : 1; + if (Index == MfvsrwzIndex) + return 1; + } + + // We need a vector extract (or mfvsrld). Assume vector operation cost. + // The cost of the load constant for a vector extract is disregarded + // (invariant, easily schedulable). + return vectorCostAdjustment(1, Opcode, Val, nullptr); + + } else if (ST->hasDirectMove()) + // Assume permute has standard cost. + // Assume move-to/move-from VSR have 2x standard cost. + return 3; } // Estimated cost of a load-hit-store delay. This was obtained diff --git a/test/Analysis/CostModel/PowerPC/insert_extract.ll b/test/Analysis/CostModel/PowerPC/insert_extract.ll index 030af67d66d..59dbd9411ef 100644 --- a/test/Analysis/CostModel/PowerPC/insert_extract.ll +++ b/test/Analysis/CostModel/PowerPC/insert_extract.ll @@ -14,15 +14,15 @@ define i32 @insert(i32 %arg) { ; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; CHECK-P8LE-LABEL: 'insert' -; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0 +; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0 ; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; CHECK-P9BE-LABEL: 'insert' -; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0 +; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0 ; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; CHECK-P9LE-LABEL: 'insert' -; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0 +; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0 ; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %x = insertelement <4 x i32> undef, i32 %arg, i32 0 @@ -40,11 +40,11 @@ define i32 @extract(<4 x i32> %arg) { ; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x ; ; CHECK-P9BE-LABEL: 'extract' -; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = extractelement <4 x i32> %arg, i32 0 +; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <4 x i32> %arg, i32 0 ; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x ; ; CHECK-P9LE-LABEL: 'extract' -; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = extractelement <4 x i32> %arg, i32 0 +; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <4 x i32> %arg, i32 0 ; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x ; %x = extractelement <4 x i32> %arg, i32 0 @@ -83,15 +83,15 @@ define void @test4xi32(<4 x i32> %v1, i32 %x1) { ; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; CHECK-P8LE-LABEL: 'test4xi32' -; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2 +; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2 ; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; CHECK-P9BE-LABEL: 'test4xi32' -; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2 +; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2 ; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; CHECK-P9LE-LABEL: 'test4xi32' -; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2 +; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2 ; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2 @@ -114,17 +114,17 @@ define void @vexti32(<4 x i32> %p1) { ; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; CHECK-P9BE-LABEL: 'vexti32' -; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i1 = extractelement <4 x i32> %p1, i32 0 -; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i2 = extractelement <4 x i32> %p1, i32 1 -; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i3 = extractelement <4 x i32> %p1, i32 2 -; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i4 = extractelement <4 x i32> %p1, i32 3 +; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <4 x i32> %p1, i32 0 +; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i2 = extractelement <4 x i32> %p1, i32 1 +; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i3 = extractelement <4 x i32> %p1, i32 2 +; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i4 = extractelement <4 x i32> %p1, i32 3 ; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; CHECK-P9LE-LABEL: 'vexti32' -; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i1 = extractelement <4 x i32> %p1, i32 0 -; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i2 = extractelement <4 x i32> %p1, i32 1 -; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i3 = extractelement <4 x i32> %p1, i32 2 -; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i4 = extractelement <4 x i32> %p1, i32 3 +; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <4 x i32> %p1, i32 0 +; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i2 = extractelement <4 x i32> %p1, i32 1 +; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i3 = extractelement <4 x i32> %p1, i32 2 +; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i4 = extractelement <4 x i32> %p1, i32 3 ; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; %i1 = extractelement <4 x i32> %p1, i32 0 @@ -146,13 +146,13 @@ define void @vexti64(<2 x i64> %p1) { ; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; CHECK-P9BE-LABEL: 'vexti64' -; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i1 = extractelement <2 x i64> %p1, i32 0 -; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i2 = extractelement <2 x i64> %p1, i32 1 +; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i1 = extractelement <2 x i64> %p1, i32 0 +; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i2 = extractelement <2 x i64> %p1, i32 1 ; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; CHECK-P9LE-LABEL: 'vexti64' -; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i1 = extractelement <2 x i64> %p1, i32 0 -; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i2 = extractelement <2 x i64> %p1, i32 1 +; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <2 x i64> %p1, i32 0 +; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i2 = extractelement <2 x i64> %p1, i32 1 ; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; %i1 = extractelement <2 x i64> %p1, i32 0 @@ -172,13 +172,13 @@ define void @vext(<8 x i16> %p1, <16 x i8> %p2) { ; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; CHECK-P9BE-LABEL: 'vext' -; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i1 = extractelement <8 x i16> %p1, i32 0 -; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i2 = extractelement <16 x i8> %p2, i32 0 +; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <8 x i16> %p1, i32 0 +; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i2 = extractelement <16 x i8> %p2, i32 0 ; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; CHECK-P9LE-LABEL: 'vext' -; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i1 = extractelement <8 x i16> %p1, i32 0 -; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i2 = extractelement <16 x i8> %p2, i32 0 +; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <8 x i16> %p1, i32 0 +; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i2 = extractelement <16 x i8> %p2, i32 0 ; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; %i1 = extractelement <8 x i16> %p1, i32 0