[PATCH] D116534: [RISCV] Set getMinVectorRegisterBitWidth to 16 if enable fixed length vector code gen for RVV
Kito Cheng via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Mon Jan 3 05:09:21 PST 2022
kito-cheng created this revision.
Herald added subscribers: VincentWu, luke957, achieveartificialintelligence, vkmr, frasercrmck, evandro, luismarques, apazos, sameer.abuasal, s.egerton, Jim, benna, psnobl, jocewei, PkmX, the_o, brucehoult, MartinMosbeck, rogfer01, edward-jones, zzheng, jrtc27, niosHD, sabuasal, simoncook, johnrusso, rbar, asb, hiraditya.
kito-cheng requested review of this revision.
Herald added subscribers: llvm-commits, MaskRay.
Herald added a project: LLVM.
getMinVectorRegisterBitWidth means what vector types is supported in
this target, and actually RISC-V support all fixed length vector types with
vector length less than `getMinRVVVectorSizeInBits`, so set it to 16,
means 2 x i8, that is minimal fixed length vector size in theory.
That also fixed one issue, some testcase migth become non-vectorizable
when `-riscv-v-vector-bits-min` set to larger value, because the vector size is
smaller than `-riscv-v-vector-bits-min`.
For example, following code can vectorize by SLP with
`-riscv-v-vector-bits-min=128` or `-riscv-v-vector-bits-min=256`, but
can't vectorize `-riscv-v-vector-bits-min=512` or larger:
c
void foo(double *da) {
da[0] = 0;
da[1] = 1;
da[2] = 2;
da[3] = 3;
}
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D116534
Files:
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
llvm/test/Transforms/SLPVectorizer/RISCV/lit.local.cfg
llvm/test/Transforms/SLPVectorizer/RISCV/rvv-min-vector-size.ll
Index: llvm/test/Transforms/SLPVectorizer/RISCV/rvv-min-vector-size.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/SLPVectorizer/RISCV/rvv-min-vector-size.ll
@@ -0,0 +1,68 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -slp-vectorizer -mtriple=riscv64 -mattr=+experimental-v \
+; RUN: -riscv-v-vector-bits-min=128 -S | FileCheck %s --check-prefixes=CHECK,CHECK-128
+; RUN: opt < %s -slp-vectorizer -mtriple=riscv64 -mattr=+experimental-v \
+; RUN: -riscv-v-vector-bits-min=256 -S | FileCheck %s --check-prefixes=CHECK,CHECK-256
+; RUN: opt < %s -slp-vectorizer -mtriple=riscv64 -mattr=+experimental-v \
+; RUN: -riscv-v-vector-bits-min=512 -S | FileCheck %s --check-prefixes=CHECK,CHECK-512
+
+target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n64-S128"
+target triple = "riscv64"
+
+define void @foo(i64* nocapture writeonly %da) {
+; CHECK-128-LABEL: @foo(
+; CHECK-128-NEXT: entry:
+; CHECK-128-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[DA:%.*]], i64 1
+; CHECK-128-NEXT: [[TMP0:%.*]] = bitcast i64* [[DA]] to <2 x i64>*
+; CHECK-128-NEXT: store <2 x i64> <i64 0, i64 1>, <2 x i64>* [[TMP0]], align 8
+; CHECK-128-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i64, i64* [[DA]], i64 2
+; CHECK-128-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i64, i64* [[DA]], i64 3
+; CHECK-128-NEXT: [[TMP1:%.*]] = bitcast i64* [[ARRAYIDX2]] to <2 x i64>*
+; CHECK-128-NEXT: store <2 x i64> <i64 2, i64 3>, <2 x i64>* [[TMP1]], align 8
+; CHECK-128-NEXT: ret void
+;
+; CHECK-256-LABEL: @foo(
+; CHECK-256-NEXT: entry:
+; CHECK-256-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[DA:%.*]], i64 1
+; CHECK-256-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i64, i64* [[DA]], i64 2
+; CHECK-256-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i64, i64* [[DA]], i64 3
+; CHECK-256-NEXT: [[TMP0:%.*]] = bitcast i64* [[DA]] to <4 x i64>*
+; CHECK-256-NEXT: store <4 x i64> <i64 0, i64 1, i64 2, i64 3>, <4 x i64>* [[TMP0]], align 8
+; CHECK-256-NEXT: ret void
+;
+; CHECK-512-LABEL: @foo(
+; CHECK-512-NEXT: entry:
+; CHECK-512-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[DA:%.*]], i64 1
+; CHECK-512-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i64, i64* [[DA]], i64 2
+; CHECK-512-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i64, i64* [[DA]], i64 3
+; CHECK-512-NEXT: [[TMP0:%.*]] = bitcast i64* [[DA]] to <4 x i64>*
+; CHECK-512-NEXT: store <4 x i64> <i64 0, i64 1, i64 2, i64 3>, <4 x i64>* [[TMP0]], align 8
+; CHECK-512-NEXT: ret void
+;
+entry:
+ store i64 0, i64* %da, align 8
+ %arrayidx1 = getelementptr inbounds i64, i64* %da, i64 1
+ store i64 1, i64* %arrayidx1, align 8
+ %arrayidx2 = getelementptr inbounds i64, i64* %da, i64 2
+ store i64 2, i64* %arrayidx2, align 8
+ %arrayidx3 = getelementptr inbounds i64, i64* %da, i64 3
+ store i64 3, i64* %arrayidx3, align 8
+ ret void
+}
+
+define void @foo8(i8* nocapture writeonly %da) {
+; CHECK-LABEL: @foo8(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[DA:%.*]], i8 1
+; CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[DA]] to <2 x i8>*
+; CHECK-NEXT: store <2 x i8> <i8 0, i8 1>, <2 x i8>* [[TMP0]], align 8
+; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i8, i8* [[DA]], i8 2
+; CHECK-NEXT: ret void
+;
+entry:
+ store i8 0, i8* %da, align 8
+ %arrayidx1 = getelementptr inbounds i8, i8* %da, i8 1
+ store i8 1, i8* %arrayidx1, align 8
+ %arrayidx2 = getelementptr inbounds i8, i8* %da, i8 2
+ ret void
+}
Index: llvm/test/Transforms/SLPVectorizer/RISCV/lit.local.cfg
===================================================================
--- /dev/null
+++ llvm/test/Transforms/SLPVectorizer/RISCV/lit.local.cfg
@@ -0,0 +1,2 @@
+if not 'RISCV' in config.root.targets:
+ config.unsupported = True
Index: llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
===================================================================
--- llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
+++ llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
@@ -81,7 +81,7 @@
TTI::PeelingPreferences &PP);
unsigned getMinVectorRegisterBitWidth() const {
- return ST->hasVInstructions() ? ST->getMinRVVVectorSizeInBits() : 0;
+ return ST->useRVVForFixedLengthVectors() ? 16 : 0;
}
InstructionCost getGatherScatterOpCost(unsigned Opcode, Type *DataTy,
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D116534.397046.patch
Type: text/x-patch
Size: 4535 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220103/f6acecd7/attachment.bin>
More information about the llvm-commits
mailing list