Skip to content

[LV] Improve the test coverage for strided access. nfc #155981

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[LV] Improve the test coverage for strided access. nfc #155981

wants to merge 1 commit into from

Conversation

Mel-Chen
Copy link
Contributor

Add tests for strided access with UF > 1, and introduce a new test case @constant_stride_reinterpret.

@Mel-Chen Mel-Chen requested review from fhahn and preames August 29, 2025 07:14
@llvmbot
Copy link
Member

llvmbot commented Aug 29, 2025 •
edited
Loading

@llvm/pr-subscribers-llvm-transforms

@llvm/pr-subscribers-backend-risc-v

Author: Mel Chen (Mel-Chen)

Changes

Add tests for strided access with UF > 1, and introduce a new test case @constant_stride_reinterpret.

Patch is 71.58 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/155981.diff

1 Files Affected:

  • (modified) llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll (+898)
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll b/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
index 251e014dbb795..4e687d7992b56 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
@@ -1,6 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -S | FileCheck --check-prefixes=CHECK,NOSTRIDED %s
+; RUN: opt < %s -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -force-vector-interleave=2 -S | FileCheck --check-prefixes=CHECK-UF2,NOSTRIDED-UF2 %s
 ; RUN: opt < %s -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -lv-strided-pointer-ivs=true -laa-speculate-unit-stride=false -S | FileCheck --check-prefixes=CHECK,STRIDED %s
+; RUN: opt < %s -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -lv-strided-pointer-ivs=true -laa-speculate-unit-stride=false -force-vector-interleave=2 -S | FileCheck --check-prefixes=CHECK-UF2,STRIDED-UF2 %s
 
 
 define void @single_constant_stride_int_scaled(ptr %p) {
@@ -46,6 +48,62 @@ define void @single_constant_stride_int_scaled(ptr %p) {
 ; CHECK:       exit:
 ; CHECK-NEXT:    ret void
 ;
+; CHECK-UF2-LABEL: @single_constant_stride_int_scaled(
+; CHECK-UF2-NEXT:  entry:
+; CHECK-UF2-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-UF2-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 3
+; CHECK-UF2-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ule i64 1024, [[TMP1]]
+; CHECK-UF2-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-UF2:       vector.ph:
+; CHECK-UF2-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-UF2-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 4
+; CHECK-UF2-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP3]], i64 0
+; CHECK-UF2-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
+; CHECK-UF2-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; CHECK-UF2-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
+; CHECK-UF2-NEXT:    [[TMP5:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
+; CHECK-UF2-NEXT:    [[TMP6:%.*]] = select i1 [[TMP5]], i64 [[TMP4]], i64 [[N_MOD_VF]]
+; CHECK-UF2-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[TMP6]]
+; CHECK-UF2-NEXT:    [[TMP7:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
+; CHECK-UF2-NEXT:    [[TMP8:%.*]] = mul <vscale x 4 x i64> [[TMP7]], splat (i64 1)
+; CHECK-UF2-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP8]]
+; CHECK-UF2-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK-UF2:       vector.body:
+; CHECK-UF2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-UF2-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 4 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-UF2-NEXT:    [[STEP_ADD:%.*]] = add <vscale x 4 x i64> [[VEC_IND]], [[BROADCAST_SPLAT]]
+; CHECK-UF2-NEXT:    [[TMP9:%.*]] = mul nuw nsw <vscale x 4 x i64> [[VEC_IND]], splat (i64 8)
+; CHECK-UF2-NEXT:    [[TMP10:%.*]] = mul nuw nsw <vscale x 4 x i64> [[STEP_ADD]], splat (i64 8)
+; CHECK-UF2-NEXT:    [[TMP11:%.*]] = getelementptr i32, ptr [[P:%.*]], <vscale x 4 x i64> [[TMP9]]
+; CHECK-UF2-NEXT:    [[TMP12:%.*]] = getelementptr i32, ptr [[P]], <vscale x 4 x i64> [[TMP10]]
+; CHECK-UF2-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP11]], i32 4, <vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> poison)
+; CHECK-UF2-NEXT:    [[WIDE_MASKED_GATHER1:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP12]], i32 4, <vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> poison)
+; CHECK-UF2-NEXT:    [[TMP13:%.*]] = add <vscale x 4 x i32> [[WIDE_MASKED_GATHER]], splat (i32 1)
+; CHECK-UF2-NEXT:    [[TMP14:%.*]] = add <vscale x 4 x i32> [[WIDE_MASKED_GATHER1]], splat (i32 1)
+; CHECK-UF2-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP13]], <vscale x 4 x ptr> [[TMP11]], i32 4, <vscale x 4 x i1> splat (i1 true))
+; CHECK-UF2-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP14]], <vscale x 4 x ptr> [[TMP12]], i32 4, <vscale x 4 x i1> splat (i1 true))
+; CHECK-UF2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; CHECK-UF2-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[STEP_ADD]], [[BROADCAST_SPLAT]]
+; CHECK-UF2-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-UF2-NEXT:    br i1 [[TMP15]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-UF2:       middle.block:
+; CHECK-UF2-NEXT:    br label [[SCALAR_PH]]
+; CHECK-UF2:       scalar.ph:
+; CHECK-UF2-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-UF2-NEXT:    br label [[LOOP:%.*]]
+; CHECK-UF2:       loop:
+; CHECK-UF2-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; CHECK-UF2-NEXT:    [[OFFSET:%.*]] = mul nuw nsw i64 [[I]], 8
+; CHECK-UF2-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
+; CHECK-UF2-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; CHECK-UF2-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; CHECK-UF2-NEXT:    store i32 [[Y0]], ptr [[Q0]], align 4
+; CHECK-UF2-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; CHECK-UF2-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; CHECK-UF2-NEXT:    br i1 [[DONE]], label [[EXIT:%.*]], label [[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK-UF2:       exit:
+; CHECK-UF2-NEXT:    ret void
+;
 entry:
   br label %loop
 loop:
@@ -108,6 +166,63 @@ define void @single_constant_stride_int_iv(ptr %p) {
 ; CHECK:       exit:
 ; CHECK-NEXT:    ret void
 ;
+; CHECK-UF2-LABEL: @single_constant_stride_int_iv(
+; CHECK-UF2-NEXT:  entry:
+; CHECK-UF2-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-UF2-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 3
+; CHECK-UF2-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; CHECK-UF2-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-UF2:       vector.ph:
+; CHECK-UF2-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-UF2-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 4
+; CHECK-UF2-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP3]], i64 0
+; CHECK-UF2-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
+; CHECK-UF2-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; CHECK-UF2-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
+; CHECK-UF2-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-UF2-NEXT:    [[TMP5:%.*]] = mul i64 [[N_VEC]], 64
+; CHECK-UF2-NEXT:    [[TMP6:%.*]] = mul <vscale x 4 x i64> [[BROADCAST_SPLAT]], splat (i64 64)
+; CHECK-UF2-NEXT:    [[TMP7:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
+; CHECK-UF2-NEXT:    [[TMP8:%.*]] = mul <vscale x 4 x i64> [[TMP7]], splat (i64 64)
+; CHECK-UF2-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP8]]
+; CHECK-UF2-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK-UF2:       vector.body:
+; CHECK-UF2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-UF2-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 4 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-UF2-NEXT:    [[STEP_ADD:%.*]] = add <vscale x 4 x i64> [[VEC_IND]], [[TMP6]]
+; CHECK-UF2-NEXT:    [[TMP9:%.*]] = getelementptr i32, ptr [[P:%.*]], <vscale x 4 x i64> [[VEC_IND]]
+; CHECK-UF2-NEXT:    [[TMP10:%.*]] = getelementptr i32, ptr [[P]], <vscale x 4 x i64> [[STEP_ADD]]
+; CHECK-UF2-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP9]], i32 4, <vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> poison)
+; CHECK-UF2-NEXT:    [[WIDE_MASKED_GATHER1:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP10]], i32 4, <vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> poison)
+; CHECK-UF2-NEXT:    [[TMP11:%.*]] = add <vscale x 4 x i32> [[WIDE_MASKED_GATHER]], splat (i32 1)
+; CHECK-UF2-NEXT:    [[TMP12:%.*]] = add <vscale x 4 x i32> [[WIDE_MASKED_GATHER1]], splat (i32 1)
+; CHECK-UF2-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP11]], <vscale x 4 x ptr> [[TMP9]], i32 4, <vscale x 4 x i1> splat (i1 true))
+; CHECK-UF2-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP12]], <vscale x 4 x ptr> [[TMP10]], i32 4, <vscale x 4 x i1> splat (i1 true))
+; CHECK-UF2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; CHECK-UF2-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[STEP_ADD]], [[TMP6]]
+; CHECK-UF2-NEXT:    [[TMP13:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-UF2-NEXT:    br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK-UF2:       middle.block:
+; CHECK-UF2-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-UF2-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK-UF2:       scalar.ph:
+; CHECK-UF2-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-UF2-NEXT:    [[BC_RESUME_VAL2:%.*]] = phi i64 [ [[TMP5]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ]
+; CHECK-UF2-NEXT:    br label [[LOOP:%.*]]
+; CHECK-UF2:       loop:
+; CHECK-UF2-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; CHECK-UF2-NEXT:    [[OFFSET:%.*]] = phi i64 [ [[BC_RESUME_VAL2]], [[SCALAR_PH]] ], [ [[OFFSET_NEXT:%.*]], [[LOOP]] ]
+; CHECK-UF2-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
+; CHECK-UF2-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; CHECK-UF2-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; CHECK-UF2-NEXT:    store i32 [[Y0]], ptr [[Q0]], align 4
+; CHECK-UF2-NEXT:    [[OFFSET_NEXT]] = add nuw nsw i64 [[OFFSET]], 64
+; CHECK-UF2-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; CHECK-UF2-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; CHECK-UF2-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK-UF2:       exit:
+; CHECK-UF2-NEXT:    ret void
+;
 entry:
   br label %loop
 loop:
@@ -168,6 +283,69 @@ define void @single_constant_stride_ptr_iv(ptr %p) {
 ; CHECK:       exit:
 ; CHECK-NEXT:    ret void
 ;
+; CHECK-UF2-LABEL: @single_constant_stride_ptr_iv(
+; CHECK-UF2-NEXT:  entry:
+; CHECK-UF2-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-UF2-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 3
+; CHECK-UF2-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ule i64 1024, [[TMP1]]
+; CHECK-UF2-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-UF2:       vector.ph:
+; CHECK-UF2-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-UF2-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 4
+; CHECK-UF2-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP3]], i64 0
+; CHECK-UF2-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
+; CHECK-UF2-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; CHECK-UF2-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
+; CHECK-UF2-NEXT:    [[TMP5:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
+; CHECK-UF2-NEXT:    [[TMP6:%.*]] = select i1 [[TMP5]], i64 [[TMP4]], i64 [[N_MOD_VF]]
+; CHECK-UF2-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[TMP6]]
+; CHECK-UF2-NEXT:    [[TMP7:%.*]] = mul i64 [[N_VEC]], 8
+; CHECK-UF2-NEXT:    [[TMP8:%.*]] = getelementptr i8, ptr [[P:%.*]], i64 [[TMP7]]
+; CHECK-UF2-NEXT:    [[TMP9:%.*]] = mul <vscale x 4 x i64> [[BROADCAST_SPLAT]], splat (i64 8)
+; CHECK-UF2-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK-UF2:       vector.body:
+; CHECK-UF2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-UF2-NEXT:    [[POINTER_PHI:%.*]] = phi ptr [ [[P]], [[VECTOR_PH]] ], [ [[PTR_IND:%.*]], [[VECTOR_BODY]] ]
+; CHECK-UF2-NEXT:    [[TMP10:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
+; CHECK-UF2-NEXT:    [[TMP11:%.*]] = mul <vscale x 4 x i64> [[TMP10]], splat (i64 8)
+; CHECK-UF2-NEXT:    [[VECTOR_GEP:%.*]] = getelementptr i8, ptr [[POINTER_PHI]], <vscale x 4 x i64> [[TMP11]]
+; CHECK-UF2-NEXT:    [[STEP_ADD:%.*]] = getelementptr i8, <vscale x 4 x ptr> [[VECTOR_GEP]], <vscale x 4 x i64> [[TMP9]]
+; CHECK-UF2-NEXT:    [[TMP12:%.*]] = extractelement <vscale x 4 x ptr> [[VECTOR_GEP]], i32 0
+; CHECK-UF2-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 8 x i32>, ptr [[TMP12]], align 4
+; CHECK-UF2-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> [[WIDE_VEC]])
+; CHECK-UF2-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 0
+; CHECK-UF2-NEXT:    [[TMP14:%.*]] = extractelement <vscale x 4 x ptr> [[STEP_ADD]], i32 0
+; CHECK-UF2-NEXT:    [[WIDE_VEC1:%.*]] = load <vscale x 8 x i32>, ptr [[TMP14]], align 4
+; CHECK-UF2-NEXT:    [[STRIDED_VEC2:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> [[WIDE_VEC1]])
+; CHECK-UF2-NEXT:    [[TMP15:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC2]], 0
+; CHECK-UF2-NEXT:    [[TMP16:%.*]] = add <vscale x 4 x i32> [[TMP13]], splat (i32 1)
+; CHECK-UF2-NEXT:    [[TMP17:%.*]] = add <vscale x 4 x i32> [[TMP15]], splat (i32 1)
+; CHECK-UF2-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP16]], <vscale x 4 x ptr> [[VECTOR_GEP]], i32 4, <vscale x 4 x i1> splat (i1 true))
+; CHECK-UF2-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP17]], <vscale x 4 x ptr> [[STEP_ADD]], i32 4, <vscale x 4 x i1> splat (i1 true))
+; CHECK-UF2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; CHECK-UF2-NEXT:    [[TMP18:%.*]] = mul i64 8, [[TMP4]]
+; CHECK-UF2-NEXT:    [[PTR_IND]] = getelementptr i8, ptr [[POINTER_PHI]], i64 [[TMP18]]
+; CHECK-UF2-NEXT:    [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-UF2-NEXT:    br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK-UF2:       middle.block:
+; CHECK-UF2-NEXT:    br label [[SCALAR_PH]]
+; CHECK-UF2:       scalar.ph:
+; CHECK-UF2-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-UF2-NEXT:    [[BC_RESUME_VAL3:%.*]] = phi ptr [ [[TMP8]], [[MIDDLE_BLOCK]] ], [ [[P]], [[ENTRY]] ]
+; CHECK-UF2-NEXT:    br label [[LOOP:%.*]]
+; CHECK-UF2:       loop:
+; CHECK-UF2-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; CHECK-UF2-NEXT:    [[PTR:%.*]] = phi ptr [ [[BC_RESUME_VAL3]], [[SCALAR_PH]] ], [ [[PTR_NEXT:%.*]], [[LOOP]] ]
+; CHECK-UF2-NEXT:    [[X0:%.*]] = load i32, ptr [[PTR]], align 4
+; CHECK-UF2-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; CHECK-UF2-NEXT:    store i32 [[Y0]], ptr [[PTR]], align 4
+; CHECK-UF2-NEXT:    [[PTR_NEXT]] = getelementptr inbounds i8, ptr [[PTR]], i64 8
+; CHECK-UF2-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; CHECK-UF2-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; CHECK-UF2-NEXT:    br i1 [[DONE]], label [[EXIT:%.*]], label [[LOOP]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK-UF2:       exit:
+; CHECK-UF2-NEXT:    ret void
+;
 entry:
   br label %loop
 loop:
@@ -227,6 +405,58 @@ define void @single_stride_int_scaled(ptr %p, i64 %stride) {
 ; NOSTRIDED:       exit:
 ; NOSTRIDED-NEXT:    ret void
 ;
+; NOSTRIDED-UF2-LABEL: @single_stride_int_scaled(
+; NOSTRIDED-UF2-NEXT:  entry:
+; NOSTRIDED-UF2-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-UF2-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 3
+; NOSTRIDED-UF2-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; NOSTRIDED-UF2-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
+; NOSTRIDED-UF2:       vector.scevcheck:
+; NOSTRIDED-UF2-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
+; NOSTRIDED-UF2-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; NOSTRIDED-UF2:       vector.ph:
+; NOSTRIDED-UF2-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-UF2-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 8
+; NOSTRIDED-UF2-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; NOSTRIDED-UF2-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; NOSTRIDED-UF2-NEXT:    br label [[VECTOR_BODY:%.*]]
+; NOSTRIDED-UF2:       vector.body:
+; NOSTRIDED-UF2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; NOSTRIDED-UF2-NEXT:    [[TMP4:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[INDEX]]
+; NOSTRIDED-UF2-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-UF2-NEXT:    [[TMP6:%.*]] = shl nuw i64 [[TMP5]], 2
+; NOSTRIDED-UF2-NEXT:    [[TMP7:%.*]] = getelementptr i32, ptr [[TMP4]], i64 [[TMP6]]
+; NOSTRIDED-UF2-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP4]], align 4
+; NOSTRIDED-UF2-NEXT:    [[WIDE_LOAD1:%.*]] = load <vscale x 4 x i32>, ptr [[TMP7]], align 4
+; NOSTRIDED-UF2-NEXT:    [[TMP8:%.*]] = add <vscale x 4 x i32> [[WIDE_LOAD]], splat (i32 1)
+; NOSTRIDED-UF2-NEXT:    [[TMP9:%.*]] = add <vscale x 4 x i32> [[WIDE_LOAD1]], splat (i32 1)
+; NOSTRIDED-UF2-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-UF2-NEXT:    [[TMP11:%.*]] = shl nuw i64 [[TMP10]], 2
+; NOSTRIDED-UF2-NEXT:    [[TMP12:%.*]] = getelementptr i32, ptr [[TMP4]], i64 [[TMP11]]
+; NOSTRIDED-UF2-NEXT:    store <vscale x 4 x i32> [[TMP8]], ptr [[TMP4]], align 4
+; NOSTRIDED-UF2-NEXT:    store <vscale x 4 x i32> [[TMP9]], ptr [[TMP12]], align 4
+; NOSTRIDED-UF2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]]
+; NOSTRIDED-UF2-NEXT:    [[TMP13:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; NOSTRIDED-UF2-NEXT:    br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; NOSTRIDED-UF2:       middle.block:
+; NOSTRIDED-UF2-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; NOSTRIDED-UF2-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; NOSTRIDED-UF2:       scalar.ph:
+; NOSTRIDED-UF2-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
+; NOSTRIDED-UF2-NEXT:    br label [[LOOP:%.*]]
+; NOSTRIDED-UF2:       loop:
+; NOSTRIDED-UF2-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; NOSTRIDED-UF2-NEXT:    [[OFFSET:%.*]] = mul nuw nsw i64 [[I]], [[STRIDE]]
+; NOSTRIDED-UF2-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
+; NOSTRIDED-UF2-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; NOSTRIDED-UF2-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; NOSTRIDED-UF2-NEXT:    store i32 [[Y0]], ptr [[Q0]], align 4
+; NOSTRIDED-UF2-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; NOSTRIDED-UF2-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; NOSTRIDED-UF2-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP9:![0-9]+]]
+; NOSTRIDED-UF2:       exit:
+; NOSTRIDED-UF2-NEXT:    ret void
+;
 ; STRIDED-LABEL: @single_stride_int_scaled(
 ; STRIDED-NEXT:  entry:
 ; STRIDED-NEXT:    br label [[LOOP:%.*]]
@@ -243,6 +473,22 @@ define void @single_stride_int_scaled(ptr %p, i64 %stride) {
 ; STRIDED:       exit:
 ; STRIDED-NEXT:    ret void
 ;
+; STRIDED-UF2-LABEL: @single_stride_int_scaled(
+; STRIDED-UF2-NEXT:  entry:
+; STRIDED-UF2-NEXT:    br label [[LOOP:%.*]]
+; STRIDED-UF2:       loop:
+; STRIDED-UF2-NEXT:    [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; STRIDED-UF2-NEXT:    [[OFFSET:%.*]] = mul nuw nsw i64 [[I]], [[STRIDE:%.*]]
+; STRIDED-UF2-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[OFFSET]]
+; STRIDED-UF2-NEXT:    [[X0...
[truncated]

@Mel-Chen Mel-Chen mentioned this pull request Aug 29, 2025
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@fhahn fhahn Awaiting requested review from fhahn

@preames preames Awaiting requested review from preames

Assignees
No one assigned
Labels
backend:RISC-V llvm:transforms
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@Mel-Chen @llvmbot