[llvm] [DAGCombiner] Combine vp.strided.load with unit stride to vp.load (PR #66766)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Sep 19 05:25:44 PDT 2023
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-selectiondag
<details>
<summary>Changes</summary>
This is the VP equivalent of #<!-- -->65674. We already combine MGATHER loads with unit stride to MLOAD, so this extends it for EXPERIMENTAL_VP_STRIDED_LOAD.
I've added the tests in a separate commit in this PR so you can see the test diff.
---
Patch is 38.09 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/66766.diff
5 Files Affected:
- (modified) llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp (+21)
- (modified) llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-vpload.ll (+87-16)
- (modified) llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-vpstore.ll (+81-4)
- (modified) llvm/test/CodeGen/RISCV/rvv/strided-vpload.ll (+90-20)
- (modified) llvm/test/CodeGen/RISCV/rvv/strided-vpstore.ll (+87-10)
``````````diff
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 484a6231b7f65fe..df69dbb16042f7e 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -539,6 +539,7 @@ namespace {
SDValue visitMSCATTER(SDNode *N);
SDValue visitVPGATHER(SDNode *N);
SDValue visitVPSCATTER(SDNode *N);
+ SDValue visitVP_STRIDED_LOAD(SDNode *N);
SDValue visitFP_TO_FP16(SDNode *N);
SDValue visitFP16_TO_FP(SDNode *N);
SDValue visitFP_TO_BF16(SDNode *N);
@@ -11959,6 +11960,22 @@ SDValue DAGCombiner::visitMLOAD(SDNode *N) {
return SDValue();
}
+SDValue DAGCombiner::visitVP_STRIDED_LOAD(SDNode *N) {
+ auto *SLD = cast<VPStridedLoadSDNode>(N);
+ EVT EltVT = SLD->getValueType(0).getVectorElementType();
+ // Combine strided loads with unit-stride to a regular load.
+ if (auto *CStride = dyn_cast<ConstantSDNode>(SLD->getStride());
+ CStride && CStride->getZExtValue() == EltVT.getStoreSize()) {
+ SDValue NewLd = DAG.getLoadVP(
+ SLD->getAddressingMode(), SLD->getExtensionType(), SLD->getValueType(0),
+ SDLoc(N), SLD->getChain(), SLD->getBasePtr(), SLD->getOffset(),
+ SLD->getMask(), SLD->getVectorLength(), SLD->getMemoryVT(),
+ SLD->getMemOperand(), SLD->isExpandingLoad());
+ return CombineTo(N, NewLd, NewLd.getValue(1));
+ }
+ return SDValue();
+}
+
/// A vector select of 2 constant vectors can be simplified to math/logic to
/// avoid a variable select instruction and possibly avoid constant loads.
SDValue DAGCombiner::foldVSelectOfConstants(SDNode *N) {
@@ -25976,6 +25993,10 @@ SDValue DAGCombiner::visitVPOp(SDNode *N) {
if (SDValue SD = visitVPSCATTER(N))
return SD;
+ if (N->getOpcode() == ISD::EXPERIMENTAL_VP_STRIDED_LOAD)
+ if (SDValue SD = visitVP_STRIDED_LOAD(N))
+ return SD;
+
// VP operations in which all vector elements are disabled - either by
// determining that the mask is all false or that the EVL is 0 - can be
// eliminated.
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-vpload.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-vpload.ll
index 96100d2b62e41b2..2ae031798f5bd6c 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-vpload.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-vpload.ll
@@ -96,6 +96,16 @@ define <8 x i8> @strided_vpload_v8i8(ptr %ptr, i32 signext %stride, <8 x i1> %m,
ret <8 x i8> %load
}
+define <8 x i8> @strided_vpload_v8i8_unit_stride(ptr %ptr, <8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpload_v8i8_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a1, e8, mf2, ta, ma
+; CHECK-NEXT: vle8.v v8, (a0), v0.t
+; CHECK-NEXT: ret
+ %load = call <8 x i8> @llvm.experimental.vp.strided.load.v8i8.p0.i32(ptr %ptr, i32 1, <8 x i1> %m, i32 %evl)
+ ret <8 x i8> %load
+}
+
declare <2 x i16> @llvm.experimental.vp.strided.load.v2i16.p0.i32(ptr, i32, <2 x i1>, i32)
define <2 x i16> @strided_vpload_v2i16(ptr %ptr, i32 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
@@ -132,6 +142,16 @@ define <8 x i16> @strided_vpload_v8i16(ptr %ptr, i32 signext %stride, <8 x i1> %
ret <8 x i16> %load
}
+define <8 x i16> @strided_vpload_v8i16_unit_stride(ptr %ptr, <8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpload_v8i16_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT: vle16.v v8, (a0), v0.t
+; CHECK-NEXT: ret
+ %load = call <8 x i16> @llvm.experimental.vp.strided.load.v8i16.p0.i32(ptr %ptr, i32 2, <8 x i1> %m, i32 %evl)
+ ret <8 x i16> %load
+}
+
define <8 x i16> @strided_vpload_v8i16_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_v8i16_allones_mask:
; CHECK: # %bb.0:
@@ -168,6 +188,16 @@ define <4 x i32> @strided_vpload_v4i32(ptr %ptr, i32 signext %stride, <4 x i1> %
ret <4 x i32> %load
}
+define <4 x i32> @strided_vpload_v4i32_unit_stride(ptr %ptr, <4 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpload_v4i32_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a1, e32, m1, ta, ma
+; CHECK-NEXT: vle32.v v8, (a0), v0.t
+; CHECK-NEXT: ret
+ %load = call <4 x i32> @llvm.experimental.vp.strided.load.v4i32.p0.i32(ptr %ptr, i32 4, <4 x i1> %m, i32 %evl)
+ ret <4 x i32> %load
+}
+
declare <8 x i32> @llvm.experimental.vp.strided.load.v8i32.p0.i32(ptr, i32, <8 x i1>, i32)
define <8 x i32> @strided_vpload_v8i32(ptr %ptr, i32 signext %stride, <8 x i1> %m, i32 zeroext %evl) {
@@ -204,6 +234,16 @@ define <2 x i64> @strided_vpload_v2i64(ptr %ptr, i32 signext %stride, <2 x i1> %
ret <2 x i64> %load
}
+define <2 x i64> @strided_vpload_v2i64_unit_stride(ptr %ptr, <2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpload_v2i64_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a1, e64, m1, ta, ma
+; CHECK-NEXT: vle64.v v8, (a0), v0.t
+; CHECK-NEXT: ret
+ %load = call <2 x i64> @llvm.experimental.vp.strided.load.v2i64.p0.i32(ptr %ptr, i32 8, <2 x i1> %m, i32 %evl)
+ ret <2 x i64> %load
+}
+
declare <4 x i64> @llvm.experimental.vp.strided.load.v4i64.p0.i32(ptr, i32, <4 x i1>, i32)
define <4 x i64> @strided_vpload_v4i64(ptr %ptr, i32 signext %stride, <4 x i1> %m, i32 zeroext %evl) {
@@ -288,6 +328,16 @@ define <8 x half> @strided_vpload_v8f16(ptr %ptr, i32 signext %stride, <8 x i1>
ret <8 x half> %load
}
+define <8 x half> @strided_vpload_v8f16_unit_stride(ptr %ptr, <8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpload_v8f16_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT: vle16.v v8, (a0), v0.t
+; CHECK-NEXT: ret
+ %load = call <8 x half> @llvm.experimental.vp.strided.load.v8f16.p0.i32(ptr %ptr, i32 2, <8 x i1> %m, i32 %evl)
+ ret <8 x half> %load
+}
+
declare <2 x float> @llvm.experimental.vp.strided.load.v2f32.p0.i32(ptr, i32, <2 x i1>, i32)
define <2 x float> @strided_vpload_v2f32(ptr %ptr, i32 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
@@ -312,6 +362,16 @@ define <4 x float> @strided_vpload_v4f32(ptr %ptr, i32 signext %stride, <4 x i1>
ret <4 x float> %load
}
+define <4 x float> @strided_vpload_v4f32_unit_stride(ptr %ptr, <4 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpload_v4f32_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a1, e32, m1, ta, ma
+; CHECK-NEXT: vle32.v v8, (a0), v0.t
+; CHECK-NEXT: ret
+ %load = call <4 x float> @llvm.experimental.vp.strided.load.v4f32.p0.i32(ptr %ptr, i32 4, <4 x i1> %m, i32 %evl)
+ ret <4 x float> %load
+}
+
declare <8 x float> @llvm.experimental.vp.strided.load.v8f32.p0.i32(ptr, i32, <8 x i1>, i32)
define <8 x float> @strided_vpload_v8f32(ptr %ptr, i32 signext %stride, <8 x i1> %m, i32 zeroext %evl) {
@@ -348,6 +408,17 @@ define <2 x double> @strided_vpload_v2f64(ptr %ptr, i32 signext %stride, <2 x i1
ret <2 x double> %load
}
+define <2 x double> @strided_vpload_v2f64_unit_stride(ptr %ptr, <2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpload_v2f64_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a1, e64, m1, ta, ma
+; CHECK-NEXT: vle64.v v8, (a0), v0.t
+; CHECK-NEXT: ret
+ %load = call <2 x double> @llvm.experimental.vp.strided.load.v2f64.p0.i32(ptr %ptr, i32 8, <2 x i1> %m, i32 %evl)
+ ret <2 x double> %load
+}
+
+
declare <4 x double> @llvm.experimental.vp.strided.load.v4f64.p0.i32(ptr, i32, <4 x i1>, i32)
define <4 x double> @strided_vpload_v4f64(ptr %ptr, i32 signext %stride, <4 x i1> %m, i32 zeroext %evl) {
@@ -416,10 +487,10 @@ define <32 x double> @strided_vpload_v32f64(ptr %ptr, i32 signext %stride, <32 x
; CHECK-NEXT: li a4, 16
; CHECK-NEXT: vmv1r.v v9, v0
; CHECK-NEXT: mv a3, a2
-; CHECK-NEXT: bltu a2, a4, .LBB33_2
+; CHECK-NEXT: bltu a2, a4, .LBB40_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: li a3, 16
-; CHECK-NEXT: .LBB33_2:
+; CHECK-NEXT: .LBB40_2:
; CHECK-NEXT: mul a4, a3, a1
; CHECK-NEXT: add a4, a0, a4
; CHECK-NEXT: addi a5, a2, -16
@@ -444,10 +515,10 @@ define <32 x double> @strided_vpload_v32f64_allones_mask(ptr %ptr, i32 signext %
; CHECK: # %bb.0:
; CHECK-NEXT: li a4, 16
; CHECK-NEXT: mv a3, a2
-; CHECK-NEXT: bltu a2, a4, .LBB34_2
+; CHECK-NEXT: bltu a2, a4, .LBB41_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: li a3, 16
-; CHECK-NEXT: .LBB34_2:
+; CHECK-NEXT: .LBB41_2:
; CHECK-NEXT: mul a4, a3, a1
; CHECK-NEXT: add a4, a0, a4
; CHECK-NEXT: addi a5, a2, -16
@@ -474,10 +545,10 @@ define <33 x double> @strided_load_v33f64(ptr %ptr, i64 %stride, <33 x i1> %mask
; CHECK-RV32-NEXT: li a5, 32
; CHECK-RV32-NEXT: vmv1r.v v8, v0
; CHECK-RV32-NEXT: mv a3, a4
-; CHECK-RV32-NEXT: bltu a4, a5, .LBB35_2
+; CHECK-RV32-NEXT: bltu a4, a5, .LBB42_2
; CHECK-RV32-NEXT: # %bb.1:
; CHECK-RV32-NEXT: li a3, 32
-; CHECK-RV32-NEXT: .LBB35_2:
+; CHECK-RV32-NEXT: .LBB42_2:
; CHECK-RV32-NEXT: mul a5, a3, a2
; CHECK-RV32-NEXT: addi a6, a4, -32
; CHECK-RV32-NEXT: sltu a4, a4, a6
@@ -485,10 +556,10 @@ define <33 x double> @strided_load_v33f64(ptr %ptr, i64 %stride, <33 x i1> %mask
; CHECK-RV32-NEXT: and a6, a4, a6
; CHECK-RV32-NEXT: li a4, 16
; CHECK-RV32-NEXT: add a5, a1, a5
-; CHECK-RV32-NEXT: bltu a6, a4, .LBB35_4
+; CHECK-RV32-NEXT: bltu a6, a4, .LBB42_4
; CHECK-RV32-NEXT: # %bb.3:
; CHECK-RV32-NEXT: li a6, 16
-; CHECK-RV32-NEXT: .LBB35_4:
+; CHECK-RV32-NEXT: .LBB42_4:
; CHECK-RV32-NEXT: vsetivli zero, 4, e8, mf2, ta, ma
; CHECK-RV32-NEXT: vslidedown.vi v0, v8, 4
; CHECK-RV32-NEXT: vsetvli zero, a6, e64, m8, ta, ma
@@ -497,10 +568,10 @@ define <33 x double> @strided_load_v33f64(ptr %ptr, i64 %stride, <33 x i1> %mask
; CHECK-RV32-NEXT: sltu a6, a3, a5
; CHECK-RV32-NEXT: addi a6, a6, -1
; CHECK-RV32-NEXT: and a5, a6, a5
-; CHECK-RV32-NEXT: bltu a3, a4, .LBB35_6
+; CHECK-RV32-NEXT: bltu a3, a4, .LBB42_6
; CHECK-RV32-NEXT: # %bb.5:
; CHECK-RV32-NEXT: li a3, 16
-; CHECK-RV32-NEXT: .LBB35_6:
+; CHECK-RV32-NEXT: .LBB42_6:
; CHECK-RV32-NEXT: mul a4, a3, a2
; CHECK-RV32-NEXT: add a4, a1, a4
; CHECK-RV32-NEXT: vsetivli zero, 2, e8, mf4, ta, ma
@@ -524,10 +595,10 @@ define <33 x double> @strided_load_v33f64(ptr %ptr, i64 %stride, <33 x i1> %mask
; CHECK-RV64-NEXT: li a5, 32
; CHECK-RV64-NEXT: vmv1r.v v8, v0
; CHECK-RV64-NEXT: mv a4, a3
-; CHECK-RV64-NEXT: bltu a3, a5, .LBB35_2
+; CHECK-RV64-NEXT: bltu a3, a5, .LBB42_2
; CHECK-RV64-NEXT: # %bb.1:
; CHECK-RV64-NEXT: li a4, 32
-; CHECK-RV64-NEXT: .LBB35_2:
+; CHECK-RV64-NEXT: .LBB42_2:
; CHECK-RV64-NEXT: mul a5, a4, a2
; CHECK-RV64-NEXT: addi a6, a3, -32
; CHECK-RV64-NEXT: sltu a3, a3, a6
@@ -535,10 +606,10 @@ define <33 x double> @strided_load_v33f64(ptr %ptr, i64 %stride, <33 x i1> %mask
; CHECK-RV64-NEXT: and a6, a3, a6
; CHECK-RV64-NEXT: li a3, 16
; CHECK-RV64-NEXT: add a5, a1, a5
-; CHECK-RV64-NEXT: bltu a6, a3, .LBB35_4
+; CHECK-RV64-NEXT: bltu a6, a3, .LBB42_4
; CHECK-RV64-NEXT: # %bb.3:
; CHECK-RV64-NEXT: li a6, 16
-; CHECK-RV64-NEXT: .LBB35_4:
+; CHECK-RV64-NEXT: .LBB42_4:
; CHECK-RV64-NEXT: vsetivli zero, 4, e8, mf2, ta, ma
; CHECK-RV64-NEXT: vslidedown.vi v0, v8, 4
; CHECK-RV64-NEXT: vsetvli zero, a6, e64, m8, ta, ma
@@ -547,10 +618,10 @@ define <33 x double> @strided_load_v33f64(ptr %ptr, i64 %stride, <33 x i1> %mask
; CHECK-RV64-NEXT: sltu a6, a4, a5
; CHECK-RV64-NEXT: addi a6, a6, -1
; CHECK-RV64-NEXT: and a5, a6, a5
-; CHECK-RV64-NEXT: bltu a4, a3, .LBB35_6
+; CHECK-RV64-NEXT: bltu a4, a3, .LBB42_6
; CHECK-RV64-NEXT: # %bb.5:
; CHECK-RV64-NEXT: li a4, 16
-; CHECK-RV64-NEXT: .LBB35_6:
+; CHECK-RV64-NEXT: .LBB42_6:
; CHECK-RV64-NEXT: mul a3, a4, a2
; CHECK-RV64-NEXT: add a3, a1, a3
; CHECK-RV64-NEXT: vsetivli zero, 2, e8, mf4, ta, ma
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-vpstore.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-vpstore.ll
index 781be5f607da162..c8abb69837875b8 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-vpstore.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-vpstore.ll
@@ -84,6 +84,17 @@ define void @strided_vpstore_v8i8(<8 x i8> %val, ptr %ptr, i32 signext %stride,
ret void
}
+define void @strided_vpstore_v8i8_unit_stride(<8 x i8> %val, ptr %ptr, <8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpstore_v8i8_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: li a2, 1
+; CHECK-NEXT: vsetvli zero, a1, e8, mf2, ta, ma
+; CHECK-NEXT: vsse8.v v8, (a0), a2, v0.t
+; CHECK-NEXT: ret
+ call void @llvm.experimental.vp.strided.store.v8i8.p0.i32(<8 x i8> %val, ptr %ptr, i32 1, <8 x i1> %m, i32 %evl)
+ ret void
+}
+
declare void @llvm.experimental.vp.strided.store.v2i16.p0.i32(<2 x i16>, ptr, i32, <2 x i1>, i32)
define void @strided_vpstore_v2i16(<2 x i16> %val, ptr %ptr, i32 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
@@ -120,6 +131,17 @@ define void @strided_vpstore_v8i16(<8 x i16> %val, ptr %ptr, i32 signext %stride
ret void
}
+define void @strided_vpstore_v8i16_unit_stride(<8 x i16> %val, ptr %ptr, <8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpstore_v8i16_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: li a2, 2
+; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT: vsse16.v v8, (a0), a2, v0.t
+; CHECK-NEXT: ret
+ call void @llvm.experimental.vp.strided.store.v8i16.p0.i32(<8 x i16> %val, ptr %ptr, i32 2, <8 x i1> %m, i32 %evl)
+ ret void
+}
+
declare void @llvm.experimental.vp.strided.store.v2i32.p0.i32(<2 x i32>, ptr, i32, <2 x i1>, i32)
define void @strided_vpstore_v2i32(<2 x i32> %val, ptr %ptr, i32 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
@@ -144,6 +166,17 @@ define void @strided_vpstore_v4i32(<4 x i32> %val, ptr %ptr, i32 signext %stride
ret void
}
+define void @strided_vpstore_v4i32_unit_stride(<4 x i32> %val, ptr %ptr, <4 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpstore_v4i32_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: li a2, 4
+; CHECK-NEXT: vsetvli zero, a1, e32, m1, ta, ma
+; CHECK-NEXT: vsse32.v v8, (a0), a2, v0.t
+; CHECK-NEXT: ret
+ call void @llvm.experimental.vp.strided.store.v4i32.p0.i32(<4 x i32> %val, ptr %ptr, i32 4, <4 x i1> %m, i32 %evl)
+ ret void
+}
+
declare void @llvm.experimental.vp.strided.store.v8i32.p0.i32(<8 x i32>, ptr, i32, <8 x i1>, i32)
define void @strided_vpstore_v8i32(<8 x i32> %val, ptr %ptr, i32 signext %stride, <8 x i1> %m, i32 zeroext %evl) {
@@ -168,6 +201,17 @@ define void @strided_vpstore_v2i64(<2 x i64> %val, ptr %ptr, i32 signext %stride
ret void
}
+define void @strided_vpstore_v2i64_unit_stride(<2 x i64> %val, ptr %ptr, <2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpstore_v2i64_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: li a2, 8
+; CHECK-NEXT: vsetvli zero, a1, e64, m1, ta, ma
+; CHECK-NEXT: vsse64.v v8, (a0), a2, v0.t
+; CHECK-NEXT: ret
+ call void @llvm.experimental.vp.strided.store.v2i64.p0.i32(<2 x i64> %val, ptr %ptr, i32 8, <2 x i1> %m, i32 %evl)
+ ret void
+}
+
declare void @llvm.experimental.vp.strided.store.v4i64.p0.i32(<4 x i64>, ptr, i32, <4 x i1>, i32)
define void @strided_vpstore_v4i64(<4 x i64> %val, ptr %ptr, i32 signext %stride, <4 x i1> %m, i32 zeroext %evl) {
@@ -228,6 +272,17 @@ define void @strided_vpstore_v8f16(<8 x half> %val, ptr %ptr, i32 signext %strid
ret void
}
+define void @strided_vpstore_v8f16_unit_stride(<8 x half> %val, ptr %ptr, <8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpstore_v8f16_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: li a2, 2
+; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT: vsse16.v v8, (a0), a2, v0.t
+; CHECK-NEXT: ret
+ call void @llvm.experimental.vp.strided.store.v8f16.p0.i32(<8 x half> %val, ptr %ptr, i32 2, <8 x i1> %m, i32 %evl)
+ ret void
+}
+
declare void @llvm.experimental.vp.strided.store.v2f32.p0.i32(<2 x float>, ptr, i32, <2 x i1>, i32)
define void @strided_vpstore_v2f32(<2 x float> %val, ptr %ptr, i32 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
@@ -252,6 +307,17 @@ define void @strided_vpstore_v4f32(<4 x float> %val, ptr %ptr, i32 signext %stri
ret void
}
+define void @strided_vpstore_v4f32_unit_stride(<4 x float> %val, ptr %ptr, <4 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpstore_v4f32_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: li a2, 4
+; CHECK-NEXT: vsetvli zero, a1, e32, m1, ta, ma
+; CHECK-NEXT: vsse32.v v8, (a0), a2, v0.t
+; CHECK-NEXT: ret
+ call void @llvm.experimental.vp.strided.store.v4f32.p0.i32(<4 x float> %val, ptr %ptr, i32 4, <4 x i1> %m, i32 %evl)
+ ret void
+}
+
declare void @llvm.experimental.vp.strided.store.v8f32.p0.i32(<8 x float>, ptr, i32, <8 x i1>, i32)
define void @strided_vpstore_v8f32(<8 x float> %val, ptr %ptr, i32 signext %stride, <8 x i1> %m, i32 zeroext %evl) {
@@ -276,6 +342,17 @@ define void @strided_vpstore_v2f64(<2 x double> %val, ptr %ptr, i32 signext %str
ret void
}
+define void @strided_vpstore_v2f64_unit_stride(<2 x double> %val, ptr %ptr, <2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpstore_v2f64_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: li a2, 8
+; CHECK-NEXT: vsetvli zero, a1, e64, m1, ta, ma
+; CHECK-NEXT: vsse64.v v8, (a0), a2, v0.t
+; CHECK-NEXT: ret
+ call void @llvm.experimental.vp.strided.store.v2f64.p0.i32(<2 x double> %val, ptr %ptr, i32 8, <2 x i1> %m, i32 %evl)
+ ret void
+}
+
declare void @llvm.experimental.vp.strided.store.v4f64.p0.i32(<4 x double>, ptr, i32, <4 x i1>, i32)
define void @strided_vpstore_v4f64(<4 x double> %val, ptr %ptr, i32 signext %stride, <4 x i1> %m, i32 zeroext %evl) {
@@ -343,10 +420,10 @@ define void @strided_store_v32f64(<32 x double> %v, ptr %ptr, i32 signext %strid
; CHECK: # %bb.0:
; CHECK-NEXT: li a4, 16
; CHECK-NEXT: mv a3, a2
-; CHECK-NEXT: bltu a2, a4, .LBB27_2
+; CHECK-NEXT: bltu a2, a4, .LBB34_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: li a3, 16
-; CHECK-NEXT: .LBB27_2:
+; CHECK-NEXT: .LBB34_2:
; CHECK-NEXT: vsetvli zero, a3, e64, m8, ta, ma
; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
; CHECK-NEXT: mul a3, a3, a1
@@ -369,10 +446,10 @@ define void @strided_store_v32f64_allones_mask(<32 x double> %v, ptr %ptr, i32 s
; CHECK: # %bb.0:
; CHECK-NEXT: li a4, 16
; CHECK-NEXT: mv a3, a2
-; CHECK-NEXT: bltu a2, a4, .LBB28_2
+; CHECK-NEXT: bltu a2, a4, .LBB35_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: li a3, 16
-; CHECK-NEXT: .LBB28_2:
+; CHECK-NEXT: .LBB35_2:
; CHECK-NEXT: vsetvli zero, a3, e64, m8, ta, ma
; CHECK-NEXT: vsse64.v v8, (a0), a1
; CHECK-NEXT: mul a3, a3, a1
diff --git a/llvm/test/CodeGen/RISCV/rvv/strided-vpload.ll b/llvm/test/CodeGen/RISCV/rvv/strided-vpload.ll
index d8431ad7662d923..47074d612bb646d 100644
--- a/llvm/test/CodeGen/RISCV/rvv/strided-vpload.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/strided-vpload.ll
@@ -126,6 +126,16 @@ define <vscale x 8 x i8> @strided_vpload_nxv8i8(ptr %ptr, i32 signext %stride, <
ret <vscale x 8 x i8> %load
}
+define <vscale x 8 x i8> @strided_vpload_nxv8i8_unit_stride(ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpload_nxv8i8_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a1, e8, m1, ta, ma
+; CHECK-NEXT: vle8.v v8, (a0), v0.t
+; CHECK-NEXT: ret
+ %load = call <vscale x 8 x i8> @llvm.experimental.vp.strided.load.nxv8i8.p0.i32(ptr %ptr, i32 1, <vscale x 8 x i1> %m, i32 %evl)
+ ret <vscale x 8 x i8> %load
+}
+
define <vscale x 8 x i8> @strided_vpload_nxv8i8_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv8i8_allones_mask:
; CHECK: # %bb.0:
@@ -186,6 +196,16 @@ define <vscale x 4 x i16> @strided_vpload_nxv4i16(ptr %ptr, i32 signext %stride,
ret <vscale x 4 x i16> %load
}
+define <vscale x 4 x i16> @strided_vpload_nxv4i16_unit_stride(ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: strided_vpload_nxv4i16_unit_stride:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT: vle16.v v8, (a0), v0.t
+; CHECK-NEXT: ret
+ %load = call <vscale x 4 x i...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/66766
More information about the llvm-commits
mailing list