[RISCV] Add tests for concats of vectors that could become strided loads

These patterns of concat_vector nodes of loads can be combined into
widened vector loads or a strided vector loads.

Co-authored-by: Philip Reames <preames@rivosinc.com>
Differential Revision: https://reviews.llvm.org/D147712

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-load-combine.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-load-combine.ll
new file mode 100644 (file)
index 0000000..b99b51f
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-load-combine.ll
@@ -0,0 +1,501 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
+; RUN: llc -mtriple=riscv32 -mattr=+v,+zfh,+experimental-zvfh -verify-machineinstrs < %s | FileCheck %s -check-prefixes=CHECK,RV32
+; RUN: llc -mtriple=riscv64 -mattr=+v,+zfh,+experimental-zvfh -verify-machineinstrs < %s | FileCheck %s -check-prefixes=CHECK,RV64
+
+; The two loads are contigous and should be folded into one
+define void @widen_2xv4i16(ptr %x, ptr %z) {
+; CHECK-LABEL: widen_2xv4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    addi a0, a0, 8
+; CHECK-NEXT:    vle16.v v9, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v9, 4
+; CHECK-NEXT:    vse16.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x
+  %b.gep = getelementptr i8, ptr %x, i64 8
+  %b = load <4 x i16>, ptr %b.gep
+  %c = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <8 x i16> %c, ptr %z
+  ret void
+}
+
+define void @widen_3xv4i16(ptr %x, ptr %z) {
+; RV32-LABEL: widen_3xv4i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; RV32-NEXT:    vle16.v v8, (a0)
+; RV32-NEXT:    addi a2, a0, 8
+; RV32-NEXT:    vle16.v v10, (a2)
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vle16.v v12, (a0)
+; RV32-NEXT:    vsetivli zero, 8, e16, m2, tu, ma
+; RV32-NEXT:    vslideup.vi v8, v10, 4
+; RV32-NEXT:    addi a0, a1, 16
+; RV32-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; RV32-NEXT:    vse16.v v12, (a0)
+; RV32-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; RV32-NEXT:    vse16.v v8, (a1)
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: widen_3xv4i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; RV64-NEXT:    vle16.v v8, (a0)
+; RV64-NEXT:    addi a2, a0, 8
+; RV64-NEXT:    vle16.v v10, (a2)
+; RV64-NEXT:    addi a0, a0, 16
+; RV64-NEXT:    vle16.v v12, (a0)
+; RV64-NEXT:    vsetivli zero, 8, e16, m2, tu, ma
+; RV64-NEXT:    vslideup.vi v8, v10, 4
+; RV64-NEXT:    vsetivli zero, 12, e16, m2, tu, ma
+; RV64-NEXT:    vslideup.vi v8, v12, 8
+; RV64-NEXT:    vsetivli zero, 1, e64, m2, ta, ma
+; RV64-NEXT:    vslidedown.vi v10, v8, 2
+; RV64-NEXT:    addi a0, a1, 16
+; RV64-NEXT:    vse64.v v10, (a0)
+; RV64-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; RV64-NEXT:    vse16.v v8, (a1)
+; RV64-NEXT:    ret
+  %a = load <4 x i16>, ptr %x
+  %b.gep = getelementptr i8, ptr %x, i64 8
+  %b = load <4 x i16>, ptr %b.gep
+  %c.gep = getelementptr i8, ptr %b.gep, i64 8
+  %c = load <4 x i16>, ptr %c.gep
+  %d.0 = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %d.1 = shufflevector <4 x i16> %c, <4 x i16> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
+  %d.2 = shufflevector <8 x i16> %d.0, <8 x i16> %d.1, <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+  store <12 x i16> %d.2, ptr %z
+  ret void
+}
+
+define void @widen_4xv4i16(ptr %x, ptr %z) {
+; CHECK-LABEL: widen_4xv4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    addi a2, a0, 8
+; CHECK-NEXT:    vle16.v v10, (a2)
+; CHECK-NEXT:    addi a2, a0, 16
+; CHECK-NEXT:    vle16.v v12, (a2)
+; CHECK-NEXT:    addi a0, a0, 24
+; CHECK-NEXT:    vle16.v v14, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m2, tu, ma
+; CHECK-NEXT:    vslideup.vi v8, v10, 4
+; CHECK-NEXT:    vsetivli zero, 12, e16, m2, tu, ma
+; CHECK-NEXT:    vslideup.vi v8, v12, 8
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v14, 12
+; CHECK-NEXT:    vse16.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x
+  %b.gep = getelementptr i8, ptr %x, i64 8
+  %b = load <4 x i16>, ptr %b.gep
+  %c.gep = getelementptr i8, ptr %b.gep, i64 8
+  %c = load <4 x i16>, ptr %c.gep
+  %d.gep = getelementptr i8, ptr %c.gep, i64 8
+  %d = load <4 x i16>, ptr %d.gep
+  %e.0 = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %e.1 = shufflevector <4 x i16> %c, <4 x i16> %d, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %e.2 = shufflevector <8 x i16> %e.0, <8 x i16> %e.1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  store <16 x i16> %e.2, ptr %z
+  ret void
+}
+
+; Should be a strided load - with type coercion to i64
+define void @strided_constant(ptr %x, ptr %z) {
+; CHECK-LABEL: strided_constant:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    vle16.v v9, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v9, 4
+; CHECK-NEXT:    vse16.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x
+  %b.gep = getelementptr i8, ptr %x, i64 16
+  %b = load <4 x i16>, ptr %b.gep
+  %c = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <8 x i16> %c, ptr %z
+  ret void
+}
+
+; Should be a strided load
+define void @strided_constant_64(ptr %x, ptr %z) {
+; CHECK-LABEL: strided_constant_64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    addi a0, a0, 64
+; CHECK-NEXT:    vle16.v v9, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v9, 4
+; CHECK-NEXT:    vse16.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x
+  %b.gep = getelementptr i8, ptr %x, i64 64
+  %b = load <4 x i16>, ptr %b.gep
+  %c = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <8 x i16> %c, ptr %z
+  ret void
+}
+
+; Vector is too large to fit into a single strided load
+define void @strided_constant_v4i32(ptr %x, ptr %z) {
+; CHECK-LABEL: strided_constant_v4i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    addi a0, a0, 32
+; CHECK-NEXT:    vle32.v v10, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v10, 4
+; CHECK-NEXT:    vse32.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i32>, ptr %x
+  %b.gep = getelementptr i8, ptr %x, i64 32
+  %b = load <4 x i32>, ptr %b.gep
+  %c = shufflevector <4 x i32> %a, <4 x i32> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <8 x i32> %c, ptr %z
+  ret void
+}
+
+; Interestingly, can be a stride 0 load
+define void @strided_constant_0(ptr %x, ptr %z) {
+; CHECK-LABEL: strided_constant_0:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vmv1r.v v9, v8
+; CHECK-NEXT:    vslideup.vi v9, v8, 4
+; CHECK-NEXT:    vse16.v v9, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x
+  %b = load <4 x i16>, ptr %x
+  %c = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <8 x i16> %c, ptr %z
+  ret void
+}
+
+; Stride isn't consistent, so shouldn't be combined
+define void @strided_constant_mismatch_4xv4i16(ptr %x, ptr %z) {
+; CHECK-LABEL: strided_constant_mismatch_4xv4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    addi a2, a0, 2
+; CHECK-NEXT:    vle16.v v10, (a2)
+; CHECK-NEXT:    addi a2, a0, 6
+; CHECK-NEXT:    vle16.v v12, (a2)
+; CHECK-NEXT:    addi a0, a0, 8
+; CHECK-NEXT:    vle16.v v14, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m2, tu, ma
+; CHECK-NEXT:    vslideup.vi v8, v10, 4
+; CHECK-NEXT:    vsetivli zero, 12, e16, m2, tu, ma
+; CHECK-NEXT:    vslideup.vi v8, v12, 8
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v14, 12
+; CHECK-NEXT:    vse16.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x
+  %b.gep = getelementptr i8, ptr %x, i64 2
+  %b = load <4 x i16>, ptr %b.gep
+  %c.gep = getelementptr i8, ptr %b.gep, i64 4
+  %c = load <4 x i16>, ptr %c.gep
+  %d.gep = getelementptr i8, ptr %c.gep, i64 2
+  %d = load <4 x i16>, ptr %d.gep
+  %e.0 = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %e.1 = shufflevector <4 x i16> %c, <4 x i16> %d, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %e.2 = shufflevector <8 x i16> %e.0, <8 x i16> %e.1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  store <16 x i16> %e.2, ptr %z
+  ret void
+}
+
+define void @strided_runtime(ptr %x, ptr %z, i64 %s) {
+; CHECK-LABEL: strided_runtime:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle16.v v9, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v9, 4
+; CHECK-NEXT:    vse16.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x
+  %b.gep = getelementptr i8, ptr %x, i64 %s
+  %b = load <4 x i16>, ptr %b.gep
+  %c = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <8 x i16> %c, ptr %z
+  ret void
+}
+
+define void @strided_runtime_4xv4i16(ptr %x, ptr %z, i64 %s) {
+; CHECK-LABEL: strided_runtime_4xv4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle16.v v10, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle16.v v12, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle16.v v14, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m2, tu, ma
+; CHECK-NEXT:    vslideup.vi v8, v10, 4
+; CHECK-NEXT:    vsetivli zero, 12, e16, m2, tu, ma
+; CHECK-NEXT:    vslideup.vi v8, v12, 8
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v14, 12
+; CHECK-NEXT:    vse16.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x
+  %b.gep = getelementptr i8, ptr %x, i64 %s
+  %b = load <4 x i16>, ptr %b.gep
+  %c.gep = getelementptr i8, ptr %b.gep, i64 %s
+  %c = load <4 x i16>, ptr %c.gep
+  %d.gep = getelementptr i8, ptr %c.gep, i64 %s
+  %d = load <4 x i16>, ptr %d.gep
+  %e.0 = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %e.1 = shufflevector <4 x i16> %c, <4 x i16> %d, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %e.2 = shufflevector <8 x i16> %e.0, <8 x i16> %e.1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  store <16 x i16> %e.2, ptr %z
+  ret void
+}
+
+; Stride isn't consistent, so shouldn't be combined
+define void @strided_runtime_mismatch_4xv4i16(ptr %x, ptr %z, i64 %s, i64 %t) {
+; RV32-LABEL: strided_runtime_mismatch_4xv4i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; RV32-NEXT:    vle16.v v8, (a0)
+; RV32-NEXT:    add a0, a0, a2
+; RV32-NEXT:    vle16.v v10, (a0)
+; RV32-NEXT:    add a0, a0, a4
+; RV32-NEXT:    vle16.v v12, (a0)
+; RV32-NEXT:    add a0, a0, a2
+; RV32-NEXT:    vle16.v v14, (a0)
+; RV32-NEXT:    vsetivli zero, 8, e16, m2, tu, ma
+; RV32-NEXT:    vslideup.vi v8, v10, 4
+; RV32-NEXT:    vsetivli zero, 12, e16, m2, tu, ma
+; RV32-NEXT:    vslideup.vi v8, v12, 8
+; RV32-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
+; RV32-NEXT:    vslideup.vi v8, v14, 12
+; RV32-NEXT:    vse16.v v8, (a1)
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: strided_runtime_mismatch_4xv4i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; RV64-NEXT:    vle16.v v8, (a0)
+; RV64-NEXT:    add a0, a0, a2
+; RV64-NEXT:    vle16.v v10, (a0)
+; RV64-NEXT:    add a0, a0, a3
+; RV64-NEXT:    vle16.v v12, (a0)
+; RV64-NEXT:    add a0, a0, a2
+; RV64-NEXT:    vle16.v v14, (a0)
+; RV64-NEXT:    vsetivli zero, 8, e16, m2, tu, ma
+; RV64-NEXT:    vslideup.vi v8, v10, 4
+; RV64-NEXT:    vsetivli zero, 12, e16, m2, tu, ma
+; RV64-NEXT:    vslideup.vi v8, v12, 8
+; RV64-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
+; RV64-NEXT:    vslideup.vi v8, v14, 12
+; RV64-NEXT:    vse16.v v8, (a1)
+; RV64-NEXT:    ret
+  %a = load <4 x i16>, ptr %x
+  %b.gep = getelementptr i8, ptr %x, i64 %s
+  %b = load <4 x i16>, ptr %b.gep
+  %c.gep = getelementptr i8, ptr %b.gep, i64 %t
+  %c = load <4 x i16>, ptr %c.gep
+  %d.gep = getelementptr i8, ptr %c.gep, i64 %s
+  %d = load <4 x i16>, ptr %d.gep
+  %e.0 = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %e.1 = shufflevector <4 x i16> %c, <4 x i16> %d, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %e.2 = shufflevector <8 x i16> %e.0, <8 x i16> %e.1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  store <16 x i16> %e.2, ptr %z
+  ret void
+}
+
+define void @strided_runtime_4xv4f16(ptr %x, ptr %z, i64 %s) {
+; CHECK-LABEL: strided_runtime_4xv4f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle16.v v10, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle16.v v12, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle16.v v14, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m2, tu, ma
+; CHECK-NEXT:    vslideup.vi v8, v10, 4
+; CHECK-NEXT:    vsetivli zero, 12, e16, m2, tu, ma
+; CHECK-NEXT:    vslideup.vi v8, v12, 8
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v14, 12
+; CHECK-NEXT:    vse16.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x half>, ptr %x
+  %b.gep = getelementptr i8, ptr %x, i64 %s
+  %b = load <4 x half>, ptr %b.gep
+  %c.gep = getelementptr i8, ptr %b.gep, i64 %s
+  %c = load <4 x half>, ptr %c.gep
+  %d.gep = getelementptr i8, ptr %c.gep, i64 %s
+  %d = load <4 x half>, ptr %d.gep
+  %e.0 = shufflevector <4 x half> %a, <4 x half> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %e.1 = shufflevector <4 x half> %c, <4 x half> %d, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %e.2 = shufflevector <8 x half> %e.0, <8 x half> %e.1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  store <16 x half> %e.2, ptr %z
+  ret void
+}
+
+define void @strided_runtime_4xv2f32(ptr %x, ptr %z, i64 %s) {
+; CHECK-LABEL: strided_runtime_4xv2f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle32.v v10, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle32.v v12, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle32.v v14, (a0)
+; CHECK-NEXT:    vsetivli zero, 4, e32, m2, tu, ma
+; CHECK-NEXT:    vslideup.vi v8, v10, 2
+; CHECK-NEXT:    vsetivli zero, 6, e32, m2, tu, ma
+; CHECK-NEXT:    vslideup.vi v8, v12, 4
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v14, 6
+; CHECK-NEXT:    vse32.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <2 x float>, ptr %x
+  %b.gep = getelementptr i8, ptr %x, i64 %s
+  %b = load <2 x float>, ptr %b.gep
+  %c.gep = getelementptr i8, ptr %b.gep, i64 %s
+  %c = load <2 x float>, ptr %c.gep
+  %d.gep = getelementptr i8, ptr %c.gep, i64 %s
+  %d = load <2 x float>, ptr %d.gep
+  %e.0 = shufflevector <2 x float> %a, <2 x float> %b, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  %e.1 = shufflevector <2 x float> %c, <2 x float> %d, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  %e.2 = shufflevector <4 x float> %e.0, <4 x float> %e.1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <8 x float> %e.2, ptr %z
+  ret void
+}
+
+; Shouldn't be combined because the resulting load would not be aligned
+define void @strided_unaligned(ptr %x, ptr %z, i64 %s) {
+; CHECK-LABEL: strided_unaligned:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vle8.v v8, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle8.v v9, (a0)
+; CHECK-NEXT:    vslideup.vi v8, v9, 4
+; CHECK-NEXT:    vse16.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x, align 1
+  %b.gep = getelementptr i8, ptr %x, i64 %s
+  %b = load <4 x i16>, ptr %b.gep, align 1
+  %c = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <8 x i16> %c, ptr %z
+  ret void
+}
+
+; Shouldn't be combined because the loads have different alignments
+define void @strided_mismatched_alignments(ptr %x, ptr %z, i64 %s) {
+; CHECK-LABEL: strided_mismatched_alignments:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle16.v v9, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v9, 4
+; CHECK-NEXT:    vse16.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x, align 8
+  %b.gep = getelementptr i8, ptr %x, i64 %s
+  %b = load <4 x i16>, ptr %b.gep, align 16
+  %c = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <8 x i16> %c, ptr %z
+  ret void
+}
+
+define void @strided_ok_alignments_8(ptr %x, ptr %z, i64 %s) {
+; CHECK-LABEL: strided_ok_alignments_8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle16.v v9, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v9, 4
+; CHECK-NEXT:    vse16.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x, align 8
+  %b.gep = getelementptr i8, ptr %x, i64 %s
+  %b = load <4 x i16>, ptr %b.gep, align 8
+  %c = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <8 x i16> %c, ptr %z
+  ret void
+}
+
+define void @strided_ok_alignments_16(ptr %x, ptr %z, i64 %s) {
+; CHECK-LABEL: strided_ok_alignments_16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle16.v v9, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v9, 4
+; CHECK-NEXT:    vse16.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x, align 16
+  %b.gep = getelementptr i8, ptr %x, i64 %s
+  %b = load <4 x i16>, ptr %b.gep, align 16
+  %c = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <8 x i16> %c, ptr %z
+  ret void
+}
+
+; Shouldn't be combined because one of the loads is not simple
+define void @strided_non_simple_load(ptr %x, ptr %z, i64 %s) {
+; CHECK-LABEL: strided_non_simple_load:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    add a0, a0, a2
+; CHECK-NEXT:    vle16.v v9, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vslideup.vi v8, v9, 4
+; CHECK-NEXT:    vse16.v v8, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x
+  %b.gep = getelementptr i8, ptr %x, i64 %s
+  %b = load volatile <4 x i16>, ptr %b.gep
+  %c = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <8 x i16> %c, ptr %z
+  ret void
+}
+
+; Shouldn't be combined because one of the operands is not a load
+define void @strided_non_load(ptr %x, ptr %z, <4 x i16> %b) {
+; CHECK-LABEL: strided_non_load:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v9, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vslideup.vi v9, v8, 4
+; CHECK-NEXT:    vse16.v v9, (a1)
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, ptr %x
+  %c = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <8 x i16> %c, ptr %z
+  ret void
+}