caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
6b5bde697bb6f2ec8564c9b35bbf9f2d5b703f13
clang-p2996/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-vp-intrinsics.ll
Luke Lau e23ab73335 [VPlan] Don't convert widen recipes to VP intrinsics in EVL transform (#127180) 
This is a copy of #126177, since it was automatically and permanently
closed because I messed up the source branch on my remote

This patch proposes to avoid converting widening recipes to VP
intrinsics during the EVL transform.

IIUC we initially did this to avoid `vl` toggles on RISC-V. However we
now have the RISCVVLOptimizer pass which mostly makes this redundant.

Emitting regular IR instead of VP intrinsics allows more generic
optimisations, both in the middle end and DAGCombiner, and we generally
have better patterns in the RISC-V backend for non-VP nodes. Sticking to
regular IR instructions is likely a lot less work than reimplementing
all of these optimisations for VP intrinsics, and on SPEC CPU 2017 we get
noticeably better code generation.
2025-02-22 19:38:11 +08:00

141 lines
8.5 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=loop-vectorize \
; RUN: -force-tail-folding-style=data-with-evl \
; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
; RUN: -mtriple=riscv64 -mattr=+v -S < %s | FileCheck --check-prefix=IF-EVL %s
; RUN: opt -passes=loop-vectorize \
; RUN: -force-tail-folding-style=none \
; RUN: -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue \
; RUN: -mtriple=riscv64 -mattr=+v -S < %s | FileCheck --check-prefix=NO-VP %s
define void @foo(ptr noalias %a, ptr noalias %b, ptr noalias %c, i64 %N) {
; IF-EVL-LABEL: @foo(
; IF-EVL-NEXT: entry:
; IF-EVL-NEXT: [[TMP0:%.*]] = sub i64 -1, [[N:%.*]]
; IF-EVL-NEXT: [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT: [[TMP2:%.*]] = mul i64 [[TMP1]], 4
; IF-EVL-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP0]], [[TMP2]]
; IF-EVL-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; IF-EVL: vector.ph:
; IF-EVL-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT: [[TMP5:%.*]] = mul i64 [[TMP4]], 4
; IF-EVL-NEXT: [[TMP8:%.*]] = sub i64 [[TMP5]], 1
; IF-EVL-NEXT: [[N_RND_UP:%.*]] = add i64 [[N]], [[TMP8]]
; IF-EVL-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP5]]
; IF-EVL-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; IF-EVL-NEXT: [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT: [[TMP10:%.*]] = mul i64 [[TMP9]], 4
; IF-EVL-NEXT: br label [[VECTOR_BODY:%.*]]
; IF-EVL: vector.body:
; IF-EVL-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-NEXT: [[TMP11:%.*]] = sub i64 [[N]], [[EVL_BASED_IV]]
; IF-EVL-NEXT: [[TMP12:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[TMP11]], i32 4, i1 true)
; IF-EVL-NEXT: [[TMP13:%.*]] = add i64 [[EVL_BASED_IV]], 0
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[B:%.*]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds i32, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[C:%.*]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD1:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
; IF-EVL-NEXT: [[VP_OP:%.*]] = add nsw <vscale x 4 x i32> [[VP_OP_LOAD1]], [[VP_OP_LOAD]]
; IF-EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP19:%.*]] = getelementptr inbounds i32, ptr [[TMP18]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[VP_OP]], ptr align 4 [[TMP19]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
; IF-EVL-NEXT: [[TMP20:%.*]] = zext i32 [[TMP12]] to i64
; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP20]], [[EVL_BASED_IV]]
; IF-EVL-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP10]]
; IF-EVL-NEXT: [[TMP21:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; IF-EVL-NEXT: br i1 [[TMP21]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; IF-EVL: middle.block:
; IF-EVL-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; IF-EVL: scalar.ph:
; IF-EVL-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; IF-EVL-NEXT: br label [[FOR_BODY:%.*]]
; IF-EVL: for.body:
; IF-EVL-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; IF-EVL-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[IV]]
; IF-EVL-NEXT: [[TMP22:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; IF-EVL-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, ptr [[C]], i64 [[IV]]
; IF-EVL-NEXT: [[TMP23:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
; IF-EVL-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP23]], [[TMP22]]
; IF-EVL-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IV]]
; IF-EVL-NEXT: store i32 [[ADD]], ptr [[ARRAYIDX4]], align 4
; IF-EVL-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; IF-EVL-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; IF-EVL: for.cond.cleanup:
; IF-EVL-NEXT: ret void
;
; NO-VP-LABEL: @foo(
; NO-VP-NEXT: entry:
; NO-VP-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; NO-VP-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; NO-VP-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N:%.*]], [[TMP1]]
; NO-VP-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; NO-VP: vector.ph:
; NO-VP-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; NO-VP-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 4
; NO-VP-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; NO-VP-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; NO-VP-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; NO-VP-NEXT: [[TMP5:%.*]] = mul i64 [[TMP4]], 4
; NO-VP-NEXT: br label [[VECTOR_BODY:%.*]]
; NO-VP: vector.body:
; NO-VP-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; NO-VP-NEXT: [[TMP6:%.*]] = add i64 [[INDEX]], 0
; NO-VP-NEXT: [[TMP7:%.*]] = getelementptr inbounds i32, ptr [[B:%.*]], i64 [[TMP6]]
; NO-VP-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, ptr [[TMP7]], i32 0
; NO-VP-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP8]], align 4
; NO-VP-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, ptr [[C:%.*]], i64 [[TMP6]]
; NO-VP-NEXT: [[TMP10:%.*]] = getelementptr inbounds i32, ptr [[TMP9]], i32 0
; NO-VP-NEXT: [[WIDE_LOAD1:%.*]] = load <vscale x 4 x i32>, ptr [[TMP10]], align 4
; NO-VP-NEXT: [[TMP11:%.*]] = add nsw <vscale x 4 x i32> [[WIDE_LOAD1]], [[WIDE_LOAD]]
; NO-VP-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP6]]
; NO-VP-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, ptr [[TMP12]], i32 0
; NO-VP-NEXT: store <vscale x 4 x i32> [[TMP11]], ptr [[TMP13]], align 4
; NO-VP-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
; NO-VP-NEXT: [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; NO-VP-NEXT: br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; NO-VP: middle.block:
; NO-VP-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
; NO-VP-NEXT: br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; NO-VP: scalar.ph:
; NO-VP-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; NO-VP-NEXT: br label [[FOR_BODY:%.*]]
; NO-VP: for.body:
; NO-VP-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; NO-VP-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[IV]]
; NO-VP-NEXT: [[TMP15:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; NO-VP-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, ptr [[C]], i64 [[IV]]
; NO-VP-NEXT: [[TMP16:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
; NO-VP-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP16]], [[TMP15]]
; NO-VP-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IV]]
; NO-VP-NEXT: store i32 [[ADD]], ptr [[ARRAYIDX4]], align 4
; NO-VP-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; NO-VP-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
; NO-VP-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; NO-VP: for.cond.cleanup:
; NO-VP-NEXT: ret void
;
entry:
br label %for.body
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%arrayidx = getelementptr inbounds i32, ptr %b, i64 %iv
%0 = load i32, ptr %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr %c, i64 %iv
%1 = load i32, ptr %arrayidx2, align 4
%add = add nsw i32 %1, %0
%arrayidx4 = getelementptr inbounds i32, ptr %a, i64 %iv
store i32 %add, ptr %arrayidx4, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, %N
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
for.cond.cleanup:
ret void
}
Reference in New Issue View Git Blame Copy Permalink