[llvm] [RISCV] Disable i1 fixed vectors with more than 1024 elements. (PR #133267)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Mar 27 08:28:30 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-risc-v
Author: Craig Topper (topperc)
<details>
<summary>Changes</summary>
v2048i1 is an MVT, but v2048i8 is not so we don't support i8 vectors with more than 1024 elements. Lowering a v2048i1 shufflevector would requires promoting to v2048i8. Since v2048i8 isn't legal and isn't an MVT this leads to a crash.
To fix the crash, this patch makes v2048i1 an illegal type.
---
Patch is 706.99 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/133267.diff
2 Files Affected:
- (modified) llvm/lib/Target/RISCV/RISCVISelLowering.cpp (+1-1)
- (added) llvm/test/CodeGen/RISCV/rvv/pr133217.ll (+19477)
``````````diff
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index 5b5dca4b541df..97186496a97f4 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -2631,7 +2631,7 @@ static bool useRVVForFixedLengthVectorVT(MVT VT,
// across all supported vector element types to avoid legalization issues.
// Therefore -- since the largest is v1024i8/v512i16/etc -- the largest
// fixed-length vector type we support is 1024 bytes.
- if (VT.getFixedSizeInBits() > 1024 * 8)
+ if (VT.getVectorNumElements() > 1024 || VT.getFixedSizeInBits() > 1024 * 8)
return false;
unsigned MinVLen = Subtarget.getRealMinVLen();
diff --git a/llvm/test/CodeGen/RISCV/rvv/pr133217.ll b/llvm/test/CodeGen/RISCV/rvv/pr133217.ll
new file mode 100644
index 0000000000000..dd81a84135069
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/pr133217.ll
@@ -0,0 +1,19477 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s -mtriple=riscv64 -mattr=+v,+zvl2048b | FileCheck %s
+
+define <2048 x i1> @foo(<1024 x i1> %x, <1024 x i1> %y) {
+; CHECK-LABEL: foo:
+; CHECK: # %bb.0:
+; CHECK-NEXT: addi sp, sp, -2032
+; CHECK-NEXT: .cfi_def_cfa_offset 2032
+; CHECK-NEXT: sd ra, 2024(sp) # 8-byte Folded Spill
+; CHECK-NEXT: sd s0, 2016(sp) # 8-byte Folded Spill
+; CHECK-NEXT: sd s2, 2008(sp) # 8-byte Folded Spill
+; CHECK-NEXT: sd s3, 2000(sp) # 8-byte Folded Spill
+; CHECK-NEXT: sd s4, 1992(sp) # 8-byte Folded Spill
+; CHECK-NEXT: sd s5, 1984(sp) # 8-byte Folded Spill
+; CHECK-NEXT: sd s6, 1976(sp) # 8-byte Folded Spill
+; CHECK-NEXT: sd s7, 1968(sp) # 8-byte Folded Spill
+; CHECK-NEXT: sd s8, 1960(sp) # 8-byte Folded Spill
+; CHECK-NEXT: sd s9, 1952(sp) # 8-byte Folded Spill
+; CHECK-NEXT: sd s10, 1944(sp) # 8-byte Folded Spill
+; CHECK-NEXT: sd s11, 1936(sp) # 8-byte Folded Spill
+; CHECK-NEXT: .cfi_offset ra, -8
+; CHECK-NEXT: .cfi_offset s0, -16
+; CHECK-NEXT: .cfi_offset s2, -24
+; CHECK-NEXT: .cfi_offset s3, -32
+; CHECK-NEXT: .cfi_offset s4, -40
+; CHECK-NEXT: .cfi_offset s5, -48
+; CHECK-NEXT: .cfi_offset s6, -56
+; CHECK-NEXT: .cfi_offset s7, -64
+; CHECK-NEXT: .cfi_offset s8, -72
+; CHECK-NEXT: .cfi_offset s9, -80
+; CHECK-NEXT: .cfi_offset s10, -88
+; CHECK-NEXT: .cfi_offset s11, -96
+; CHECK-NEXT: addi s0, sp, 2032
+; CHECK-NEXT: .cfi_def_cfa s0, 0
+; CHECK-NEXT: lui a0, 2
+; CHECK-NEXT: addiw a0, a0, 1040
+; CHECK-NEXT: sub sp, sp, a0
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: slli a0, a0, 1
+; CHECK-NEXT: mv a1, a0
+; CHECK-NEXT: slli a0, a0, 2
+; CHECK-NEXT: add a1, a1, a0
+; CHECK-NEXT: slli a0, a0, 2
+; CHECK-NEXT: add a1, a1, a0
+; CHECK-NEXT: slli a0, a0, 1
+; CHECK-NEXT: add a1, a1, a0
+; CHECK-NEXT: slli a0, a0, 2
+; CHECK-NEXT: add a0, a0, a1
+; CHECK-NEXT: sub sp, sp, a0
+; CHECK-NEXT: andi sp, sp, -1024
+; CHECK-NEXT: li s2, 1024
+; CHECK-NEXT: lui a0, 2
+; CHECK-NEXT: add a5, sp, a0
+; CHECK-NEXT: li a0, 3
+; CHECK-NEXT: slli a0, a0, 11
+; CHECK-NEXT: add t2, sp, a0
+; CHECK-NEXT: li s11, 127
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 2040
+; CHECK-NEXT: add a7, sp, a0
+; CHECK-NEXT: li s10, 126
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 2032
+; CHECK-NEXT: add t3, sp, a0
+; CHECK-NEXT: li s9, 125
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 2024
+; CHECK-NEXT: add a2, sp, a0
+; CHECK-NEXT: li s8, 124
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 2016
+; CHECK-NEXT: add t1, sp, a0
+; CHECK-NEXT: li s7, 123
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 2008
+; CHECK-NEXT: add a3, sp, a0
+; CHECK-NEXT: li s6, 122
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 2000
+; CHECK-NEXT: add t0, sp, a0
+; CHECK-NEXT: li s5, 121
+; CHECK-NEXT: li s4, 120
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1984
+; CHECK-NEXT: add a4, sp, a0
+; CHECK-NEXT: li s3, 119
+; CHECK-NEXT: li t6, 118
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1968
+; CHECK-NEXT: add a6, sp, a0
+; CHECK-NEXT: li t5, 117
+; CHECK-NEXT: li t4, 116
+; CHECK-NEXT: vsetvli zero, s2, e8, m4, ta, ma
+; CHECK-NEXT: vmv.v.i v16, 0
+; CHECK-NEXT: vmerge.vim v12, v16, 1, v0
+; CHECK-NEXT: vse8.v v12, (a5)
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1952
+; CHECK-NEXT: add a1, sp, a0
+; CHECK-NEXT: vmv1r.v v0, v8
+; CHECK-NEXT: vmerge.vim v8, v16, 1, v0
+; CHECK-NEXT: vse8.v v8, (t2)
+; CHECK-NEXT: li a0, 115
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vslidedown.vx v10, v12, s11
+; CHECK-NEXT: vslidedown.vx v11, v8, s11
+; CHECK-NEXT: lui a5, 1
+; CHECK-NEXT: addiw a5, a5, 1944
+; CHECK-NEXT: add a5, sp, a5
+; CHECK-NEXT: vslidedown.vx v25, v12, s10
+; CHECK-NEXT: vslidedown.vx v14, v8, s10
+; CHECK-NEXT: li s10, 114
+; CHECK-NEXT: vslidedown.vx v26, v12, s9
+; CHECK-NEXT: vslidedown.vx v15, v8, s9
+; CHECK-NEXT: lui t2, 1
+; CHECK-NEXT: addiw t2, t2, 1936
+; CHECK-NEXT: add s2, sp, t2
+; CHECK-NEXT: vslidedown.vx v27, v12, s8
+; CHECK-NEXT: vslidedown.vx v16, v8, s8
+; CHECK-NEXT: li s8, 113
+; CHECK-NEXT: vslidedown.vx v28, v12, s7
+; CHECK-NEXT: vslidedown.vx v17, v8, s7
+; CHECK-NEXT: lui t2, 1
+; CHECK-NEXT: addiw t2, t2, 1928
+; CHECK-NEXT: add s7, sp, t2
+; CHECK-NEXT: vslidedown.vx v29, v12, s6
+; CHECK-NEXT: vslidedown.vx v18, v8, s6
+; CHECK-NEXT: li s6, 112
+; CHECK-NEXT: vslidedown.vx v30, v12, s5
+; CHECK-NEXT: vslidedown.vx v19, v8, s5
+; CHECK-NEXT: lui t2, 1
+; CHECK-NEXT: addiw t2, t2, 1920
+; CHECK-NEXT: add t2, sp, t2
+; CHECK-NEXT: vslidedown.vx v31, v12, s4
+; CHECK-NEXT: vslidedown.vx v20, v8, s4
+; CHECK-NEXT: li s4, 111
+; CHECK-NEXT: vslidedown.vx v7, v12, s3
+; CHECK-NEXT: vslidedown.vx v21, v8, s3
+; CHECK-NEXT: vslidedown.vx v6, v12, t6
+; CHECK-NEXT: vslidedown.vx v22, v8, t6
+; CHECK-NEXT: li s11, 110
+; CHECK-NEXT: vslidedown.vx v5, v12, t5
+; CHECK-NEXT: vslidedown.vx v23, v8, t5
+; CHECK-NEXT: lui t5, 1
+; CHECK-NEXT: addiw t5, t5, 1904
+; CHECK-NEXT: add s5, sp, t5
+; CHECK-NEXT: vslidedown.vx v4, v12, t4
+; CHECK-NEXT: vslidedown.vx v24, v8, t4
+; CHECK-NEXT: li ra, 109
+; CHECK-NEXT: vse8.v v10, (a7)
+; CHECK-NEXT: lui a7, 1
+; CHECK-NEXT: addiw a7, a7, 1896
+; CHECK-NEXT: add a7, sp, a7
+; CHECK-NEXT: vse8.v v25, (t3)
+; CHECK-NEXT: li t6, 108
+; CHECK-NEXT: vslidedown.vx v3, v12, a0
+; CHECK-NEXT: vslidedown.vx v10, v8, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1888
+; CHECK-NEXT: add t3, sp, a0
+; CHECK-NEXT: vse8.v v26, (a2)
+; CHECK-NEXT: li t4, 107
+; CHECK-NEXT: vse8.v v27, (t1)
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1880
+; CHECK-NEXT: add a2, sp, a0
+; CHECK-NEXT: vslidedown.vx v2, v12, s10
+; CHECK-NEXT: vslidedown.vx v25, v8, s10
+; CHECK-NEXT: li t1, 106
+; CHECK-NEXT: vse8.v v28, (a3)
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1872
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vse8.v v29, (t0)
+; CHECK-NEXT: vslidedown.vx v1, v12, s8
+; CHECK-NEXT: vslidedown.vx v26, v8, s8
+; CHECK-NEXT: lui a3, 1
+; CHECK-NEXT: addiw a3, a3, 2041
+; CHECK-NEXT: add t0, sp, a3
+; CHECK-NEXT: lui a3, 1
+; CHECK-NEXT: addiw a3, a3, 1992
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: vse8.v v30, (a3)
+; CHECK-NEXT: vse8.v v31, (a4)
+; CHECK-NEXT: lui a3, 1
+; CHECK-NEXT: addiw a3, a3, 2033
+; CHECK-NEXT: add s9, sp, a3
+; CHECK-NEXT: vslidedown.vx v31, v12, s6
+; CHECK-NEXT: vslidedown.vx v27, v8, s6
+; CHECK-NEXT: li t5, 381
+; CHECK-NEXT: lui a3, 1
+; CHECK-NEXT: addiw a3, a3, 1976
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: vse8.v v7, (a3)
+; CHECK-NEXT: lui a3, 1
+; CHECK-NEXT: addiw a3, a3, 2025
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: vse8.v v6, (a6)
+; CHECK-NEXT: li s3, 380
+; CHECK-NEXT: vslidedown.vx v7, v12, s4
+; CHECK-NEXT: vslidedown.vx v28, v8, s4
+; CHECK-NEXT: lui a4, 1
+; CHECK-NEXT: addiw a4, a4, 2017
+; CHECK-NEXT: add a6, sp, a4
+; CHECK-NEXT: lui a4, 1
+; CHECK-NEXT: addiw a4, a4, 1960
+; CHECK-NEXT: add a4, sp, a4
+; CHECK-NEXT: vse8.v v5, (a4)
+; CHECK-NEXT: li a4, 379
+; CHECK-NEXT: vse8.v v4, (a1)
+; CHECK-NEXT: lui a1, 1
+; CHECK-NEXT: addiw a1, a1, 2009
+; CHECK-NEXT: add a1, sp, a1
+; CHECK-NEXT: vslidedown.vx v6, v12, s11
+; CHECK-NEXT: vslidedown.vx v29, v8, s11
+; CHECK-NEXT: li s10, 378
+; CHECK-NEXT: vse8.v v3, (a5)
+; CHECK-NEXT: lui a5, 1
+; CHECK-NEXT: addiw a5, a5, 2001
+; CHECK-NEXT: add a5, sp, a5
+; CHECK-NEXT: vse8.v v2, (s2)
+; CHECK-NEXT: li s8, 377
+; CHECK-NEXT: vslidedown.vx v5, v12, ra
+; CHECK-NEXT: vslidedown.vx v30, v8, ra
+; CHECK-NEXT: lui s2, 1
+; CHECK-NEXT: addiw s2, s2, 1993
+; CHECK-NEXT: add s2, sp, s2
+; CHECK-NEXT: vse8.v v1, (s7)
+; CHECK-NEXT: li s7, 376
+; CHECK-NEXT: vse8.v v31, (t2)
+; CHECK-NEXT: lui t2, 1
+; CHECK-NEXT: addiw t2, t2, 1985
+; CHECK-NEXT: add t2, sp, t2
+; CHECK-NEXT: vslidedown.vx v4, v12, t6
+; CHECK-NEXT: vslidedown.vx v31, v8, t6
+; CHECK-NEXT: li s6, 375
+; CHECK-NEXT: lui t6, 1
+; CHECK-NEXT: addiw t6, t6, 1912
+; CHECK-NEXT: add t6, sp, t6
+; CHECK-NEXT: vse8.v v7, (t6)
+; CHECK-NEXT: lui t6, 1
+; CHECK-NEXT: addiw t6, t6, 1977
+; CHECK-NEXT: add t6, sp, t6
+; CHECK-NEXT: vse8.v v6, (s5)
+; CHECK-NEXT: li s5, 374
+; CHECK-NEXT: vslidedown.vx v3, v12, t4
+; CHECK-NEXT: vslidedown.vx v7, v8, t4
+; CHECK-NEXT: lui t4, 1
+; CHECK-NEXT: addiw t4, t4, 1969
+; CHECK-NEXT: add t4, sp, t4
+; CHECK-NEXT: vse8.v v5, (a7)
+; CHECK-NEXT: li s4, 373
+; CHECK-NEXT: vse8.v v4, (t3)
+; CHECK-NEXT: lui a7, 1
+; CHECK-NEXT: addiw a7, a7, 1961
+; CHECK-NEXT: add a7, sp, a7
+; CHECK-NEXT: vslidedown.vx v5, v12, t1
+; CHECK-NEXT: vslidedown.vx v6, v8, t1
+; CHECK-NEXT: li t3, 372
+; CHECK-NEXT: vse8.v v3, (a2)
+; CHECK-NEXT: lui a2, 1
+; CHECK-NEXT: addiw a2, a2, 1953
+; CHECK-NEXT: add a2, sp, a2
+; CHECK-NEXT: vse8.v v5, (a0)
+; CHECK-NEXT: li t1, 371
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: li a0, 383
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (t0)
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1945
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: li t0, 382
+; CHECK-NEXT: vslidedown.vx v4, v12, t0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (s9)
+; CHECK-NEXT: li t0, 370
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, t5
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a3)
+; CHECK-NEXT: lui a3, 1
+; CHECK-NEXT: addiw a3, a3, 1937
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, s3
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a6)
+; CHECK-NEXT: li t5, 369
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a4
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a1)
+; CHECK-NEXT: lui a1, 1
+; CHECK-NEXT: addiw a1, a1, 1929
+; CHECK-NEXT: add a1, sp, a1
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, s10
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a5)
+; CHECK-NEXT: li s3, 368
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, s8
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (s2)
+; CHECK-NEXT: lui a4, 1
+; CHECK-NEXT: addiw a4, a4, 1921
+; CHECK-NEXT: add a4, sp, a4
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, s7
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (t2)
+; CHECK-NEXT: li t2, 367
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, s6
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (t6)
+; CHECK-NEXT: lui a5, 1
+; CHECK-NEXT: addiw a5, a5, 1913
+; CHECK-NEXT: add a5, sp, a5
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, s5
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (t4)
+; CHECK-NEXT: li t4, 366
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, s4
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a7)
+; CHECK-NEXT: lui a6, 1
+; CHECK-NEXT: addiw a6, a6, 1905
+; CHECK-NEXT: add a6, sp, a6
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, t3
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a2)
+; CHECK-NEXT: li a7, 365
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, t1
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1897
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, t0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a3)
+; CHECK-NEXT: li a3, 364
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, t5
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a1)
+; CHECK-NEXT: lui a1, 1
+; CHECK-NEXT: addiw a1, a1, 1889
+; CHECK-NEXT: add a1, sp, a1
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, s3
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a4)
+; CHECK-NEXT: li a4, 363
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, t2
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a5)
+; CHECK-NEXT: lui a2, 1
+; CHECK-NEXT: addiw a2, a2, 1881
+; CHECK-NEXT: add a2, sp, a2
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, t4
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a6)
+; CHECK-NEXT: li a5, 362
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a7
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1873
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a3
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a1)
+; CHECK-NEXT: li a3, 361
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a4
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a2)
+; CHECK-NEXT: lui a1, 1
+; CHECK-NEXT: addiw a1, a1, 1865
+; CHECK-NEXT: add a1, sp, a1
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a5
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a2, 360
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a3
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a1)
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1857
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a2
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 359
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1849
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 358
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1841
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 357
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1833
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 356
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1825
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 355
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1817
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 354
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1809
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 353
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1801
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 352
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1793
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 351
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1785
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 350
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1777
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 349
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1769
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 348
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1761
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 347
+; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v4, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: addiw a0, a0, 1753
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT: vse8.v v4, (a0)
+; CHECK-NEXT: li a0, 346
+; CHECK-NEXT: vsetivli zero, 1, ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/133267
More information about the llvm-commits
mailing list