[llvm] 77fc8da - [RISCV] Rematerialize vmv.v.x (#107993)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Sep 10 18:13:26 PDT 2024
Author: Luke Lau
Date: 2024-09-11T09:13:23+08:00
New Revision: 77fc8dae22ff1fa38c0271abc5521db76351f1fd
URL: https://github.com/llvm/llvm-project/commit/77fc8dae22ff1fa38c0271abc5521db76351f1fd
DIFF: https://github.com/llvm/llvm-project/commit/77fc8dae22ff1fa38c0271abc5521db76351f1fd.diff
LOG: [RISCV] Rematerialize vmv.v.x (#107993)
Even though vmv.v.x has a non constant scalar operand, we can still
rematerialize it because we have split register allocation between
vectors and scalars.
InlineSpiller will check to make sure that the scalar operand is live at
the point where the rematerialization occurs, so this won't extend any
scalar live ranges. However this also means we may not be able to
rematerialize in some cases, as shown in @vmv.v.x_needs_extended.
It might be worthwhile teaching InlineSpiller to extend scalar live
ranges in a future patch. I experimented with this locally and it
reduced spills on 531.deepsjeng_r by a further 3%.
Added:
Modified:
llvm/lib/Target/RISCV/RISCVInstrInfo.cpp
llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
llvm/test/CodeGen/RISCV/rvv/ctpop-vp.ll
llvm/test/CodeGen/RISCV/rvv/cttz-vp.ll
llvm/test/CodeGen/RISCV/rvv/remat.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfo.cpp b/llvm/lib/Target/RISCV/RISCVInstrInfo.cpp
index 325a50c9f48a1c..2bb9df4ead0e9c 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfo.cpp
@@ -169,6 +169,7 @@ Register RISCVInstrInfo::isStoreToStackSlot(const MachineInstr &MI,
bool RISCVInstrInfo::isReallyTriviallyReMaterializable(
const MachineInstr &MI) const {
switch (RISCV::getRVVMCOpcode(MI.getOpcode())) {
+ case RISCV::VMV_V_X:
case RISCV::VMV_V_I:
case RISCV::VID_V:
if (MI.getOperand(1).isUndef() &&
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td b/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
index e11f176bfe6041..c6cecb7d07182f 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
@@ -2475,6 +2475,7 @@ multiclass VPseudoUnaryVMV_V_X_I {
def "_V_" # mx : VPseudoUnaryNoMask<m.vrclass, m.vrclass>,
SchedUnary<"WriteVIMovV", "ReadVIMovV", mx,
forcePassthruRead=true>;
+ let isReMaterializable = 1 in
def "_X_" # mx : VPseudoUnaryNoMask<m.vrclass, GPR>,
SchedUnary<"WriteVIMovX", "ReadVIMovX", mx,
forcePassthruRead=true>;
diff --git a/llvm/test/CodeGen/RISCV/rvv/ctpop-vp.ll b/llvm/test/CodeGen/RISCV/rvv/ctpop-vp.ll
index 01aac122d5957d..7031f93edc2c3e 100644
--- a/llvm/test/CodeGen/RISCV/rvv/ctpop-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/ctpop-vp.ll
@@ -2022,14 +2022,9 @@ define <vscale x 16 x i64> @vp_ctpop_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: mul a1, a1, a2
; RV32-NEXT: sub sp, sp, a1
; RV32-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x38, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 56 * vlenb
-; RV32-NEXT: vmv1r.v v24, v0
+; RV32-NEXT: vmv1r.v v7, v0
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a1, a1, 5
-; RV32-NEXT: add a1, sp, a1
-; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
-; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a2, 48
+; RV32-NEXT: li a2, 40
; RV32-NEXT: mul a1, a1, a2
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
@@ -2045,7 +2040,7 @@ define <vscale x 16 x i64> @vp_ctpop_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; RV32-NEXT: vsrl.vi v8, v16, 1, v0.t
; RV32-NEXT: csrr a3, vlenb
-; RV32-NEXT: li a4, 40
+; RV32-NEXT: li a4, 48
; RV32-NEXT: mul a3, a3, a4
; RV32-NEXT: add a3, sp, a3
; RV32-NEXT: addi a3, a3, 16
@@ -2053,67 +2048,53 @@ define <vscale x 16 x i64> @vp_ctpop_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: lui a3, 349525
; RV32-NEXT: addi a3, a3, 1365
; RV32-NEXT: vsetvli a4, zero, e32, m8, ta, ma
-; RV32-NEXT: vmv.v.x v16, a3
-; RV32-NEXT: csrr a3, vlenb
-; RV32-NEXT: li a4, 24
-; RV32-NEXT: mul a3, a3, a4
-; RV32-NEXT: add a3, sp, a3
-; RV32-NEXT: addi a3, a3, 16
-; RV32-NEXT: vs8r.v v16, (a3) # Unknown-size Folded Spill
+; RV32-NEXT: vmv.v.x v8, a3
; RV32-NEXT: csrr a3, vlenb
-; RV32-NEXT: li a4, 40
-; RV32-NEXT: mul a3, a3, a4
+; RV32-NEXT: slli a3, a3, 5
; RV32-NEXT: add a3, sp, a3
; RV32-NEXT: addi a3, a3, 16
-; RV32-NEXT: vl8r.v v8, (a3) # Unknown-size Folded Reload
-; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; RV32-NEXT: vand.vv v8, v8, v16, v0.t
+; RV32-NEXT: vs8r.v v8, (a3) # Unknown-size Folded Spill
; RV32-NEXT: csrr a3, vlenb
; RV32-NEXT: slli a3, a3, 5
; RV32-NEXT: add a3, sp, a3
; RV32-NEXT: addi a3, a3, 16
-; RV32-NEXT: vl8r.v v16, (a3) # Unknown-size Folded Reload
-; RV32-NEXT: vsub.vv v8, v16, v8, v0.t
+; RV32-NEXT: vl8r.v v8, (a3) # Unknown-size Folded Reload
; RV32-NEXT: csrr a3, vlenb
-; RV32-NEXT: slli a3, a3, 5
+; RV32-NEXT: li a4, 48
+; RV32-NEXT: mul a3, a3, a4
; RV32-NEXT: add a3, sp, a3
; RV32-NEXT: addi a3, a3, 16
-; RV32-NEXT: vs8r.v v8, (a3) # Unknown-size Folded Spill
+; RV32-NEXT: vl8r.v v24, (a3) # Unknown-size Folded Reload
+; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT: vand.vv v8, v24, v8, v0.t
+; RV32-NEXT: vsub.vv v16, v16, v8, v0.t
; RV32-NEXT: lui a3, 209715
; RV32-NEXT: addi a3, a3, 819
; RV32-NEXT: vsetvli a4, zero, e32, m8, ta, ma
-; RV32-NEXT: vmv.v.x v16, a3
-; RV32-NEXT: csrr a3, vlenb
-; RV32-NEXT: slli a3, a3, 5
-; RV32-NEXT: add a3, sp, a3
-; RV32-NEXT: addi a3, a3, 16
-; RV32-NEXT: vl8r.v v8, (a3) # Unknown-size Folded Reload
-; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; RV32-NEXT: vand.vv v8, v8, v16, v0.t
+; RV32-NEXT: vmv.v.x v8, a3
; RV32-NEXT: csrr a3, vlenb
-; RV32-NEXT: slli a3, a3, 4
+; RV32-NEXT: li a4, 48
+; RV32-NEXT: mul a3, a3, a4
; RV32-NEXT: add a3, sp, a3
; RV32-NEXT: addi a3, a3, 16
; RV32-NEXT: vs8r.v v8, (a3) # Unknown-size Folded Spill
; RV32-NEXT: csrr a3, vlenb
-; RV32-NEXT: slli a3, a3, 5
+; RV32-NEXT: li a4, 48
+; RV32-NEXT: mul a3, a3, a4
; RV32-NEXT: add a3, sp, a3
; RV32-NEXT: addi a3, a3, 16
; RV32-NEXT: vl8r.v v8, (a3) # Unknown-size Folded Reload
-; RV32-NEXT: vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT: vand.vv v8, v16, v8, v0.t
+; RV32-NEXT: vsrl.vi v16, v16, 2, v0.t
; RV32-NEXT: csrr a3, vlenb
-; RV32-NEXT: li a4, 40
+; RV32-NEXT: li a4, 48
; RV32-NEXT: mul a3, a3, a4
; RV32-NEXT: add a3, sp, a3
; RV32-NEXT: addi a3, a3, 16
-; RV32-NEXT: vs8r.v v16, (a3) # Unknown-size Folded Spill
-; RV32-NEXT: vand.vv v8, v8, v16, v0.t
-; RV32-NEXT: csrr a3, vlenb
-; RV32-NEXT: slli a3, a3, 4
-; RV32-NEXT: add a3, sp, a3
-; RV32-NEXT: addi a3, a3, 16
-; RV32-NEXT: vl8r.v v16, (a3) # Unknown-size Folded Reload
-; RV32-NEXT: vadd.vv v8, v16, v8, v0.t
+; RV32-NEXT: vl8r.v v24, (a3) # Unknown-size Folded Reload
+; RV32-NEXT: vand.vv v16, v16, v24, v0.t
+; RV32-NEXT: vadd.vv v8, v8, v16, v0.t
; RV32-NEXT: vsrl.vi v16, v8, 4, v0.t
; RV32-NEXT: vadd.vv v8, v8, v16, v0.t
; RV32-NEXT: lui a3, 61681
@@ -2121,25 +2102,26 @@ define <vscale x 16 x i64> @vp_ctpop_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: vsetvli a4, zero, e32, m8, ta, ma
; RV32-NEXT: vmv.v.x v16, a3
; RV32-NEXT: csrr a3, vlenb
-; RV32-NEXT: slli a3, a3, 5
+; RV32-NEXT: li a4, 24
+; RV32-NEXT: mul a3, a3, a4
; RV32-NEXT: add a3, sp, a3
; RV32-NEXT: addi a3, a3, 16
; RV32-NEXT: vs8r.v v16, (a3) # Unknown-size Folded Spill
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; RV32-NEXT: vand.vv v16, v8, v16, v0.t
+; RV32-NEXT: vand.vv v8, v8, v16, v0.t
; RV32-NEXT: lui a3, 4112
; RV32-NEXT: addi a3, a3, 257
; RV32-NEXT: vsetvli a4, zero, e32, m8, ta, ma
-; RV32-NEXT: vmv.v.x v8, a3
+; RV32-NEXT: vmv.v.x v16, a3
; RV32-NEXT: csrr a3, vlenb
; RV32-NEXT: slli a3, a3, 4
; RV32-NEXT: add a3, sp, a3
; RV32-NEXT: addi a3, a3, 16
-; RV32-NEXT: vs8r.v v8, (a3) # Unknown-size Folded Spill
+; RV32-NEXT: vs8r.v v16, (a3) # Unknown-size Folded Spill
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; RV32-NEXT: vmul.vv v16, v16, v8, v0.t
+; RV32-NEXT: vmul.vv v8, v8, v16, v0.t
; RV32-NEXT: li a2, 56
-; RV32-NEXT: vsrl.vx v8, v16, a2, v0.t
+; RV32-NEXT: vsrl.vx v8, v8, a2, v0.t
; RV32-NEXT: csrr a3, vlenb
; RV32-NEXT: slli a3, a3, 3
; RV32-NEXT: add a3, sp, a3
@@ -2149,8 +2131,8 @@ define <vscale x 16 x i64> @vp_ctpop_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a0, a1
; RV32-NEXT: .LBB46_2:
-; RV32-NEXT: vmv1r.v v0, v24
-; RV32-NEXT: li a3, 48
+; RV32-NEXT: vmv1r.v v0, v7
+; RV32-NEXT: li a3, 40
; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
@@ -2160,71 +2142,64 @@ define <vscale x 16 x i64> @vp_ctpop_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: addi a0, sp, 16
; RV32-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: li a1, 24
-; RV32-NEXT: mul a0, a0, a1
-; RV32-NEXT: add a0, sp, a0
-; RV32-NEXT: addi a0, a0, 16
-; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
-; RV32-NEXT: addi a0, sp, 16
-; RV32-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; RV32-NEXT: vand.vv v16, v8, v16, v0.t
-; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: li a1, 48
-; RV32-NEXT: mul a0, a0, a1
+; RV32-NEXT: slli a0, a0, 5
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; RV32-NEXT: vsub.vv v8, v8, v16, v0.t
+; RV32-NEXT: addi a0, sp, 16
+; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT: vand.vv v8, v16, v8, v0.t
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: li a1, 48
+; RV32-NEXT: li a1, 40
; RV32-NEXT: mul a0, a0, a1
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
-; RV32-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
+; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT: vsub.vv v8, v16, v8, v0.t
; RV32-NEXT: csrr a0, vlenb
; RV32-NEXT: li a1, 40
; RV32-NEXT: mul a0, a0, a1
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
-; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; RV32-NEXT: csrr a0, vlenb
; RV32-NEXT: li a1, 48
; RV32-NEXT: mul a0, a0, a1
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; RV32-NEXT: vand.vv v8, v8, v16, v0.t
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: li a1, 24
+; RV32-NEXT: li a1, 40
; RV32-NEXT: mul a0, a0, a1
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
-; RV32-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
+; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT: vand.vv v16, v16, v8, v0.t
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: li a1, 48
-; RV32-NEXT: mul a0, a0, a1
+; RV32-NEXT: slli a0, a0, 5
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
-; RV32-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; RV32-NEXT: vsrl.vi v16, v8, 2, v0.t
+; RV32-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
+; RV32-NEXT: vmv8r.v v16, v8
; RV32-NEXT: csrr a0, vlenb
; RV32-NEXT: li a1, 40
; RV32-NEXT: mul a0, a0, a1
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; RV32-NEXT: vand.vv v16, v16, v8, v0.t
+; RV32-NEXT: vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT: vand.vv v8, v8, v16, v0.t
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: li a1, 24
-; RV32-NEXT: mul a0, a0, a1
+; RV32-NEXT: slli a0, a0, 5
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
-; RV32-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; RV32-NEXT: vadd.vv v8, v8, v16, v0.t
+; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT: vadd.vv v8, v16, v8, v0.t
; RV32-NEXT: vsrl.vi v16, v8, 4, v0.t
; RV32-NEXT: vadd.vv v8, v8, v16, v0.t
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: li a1, 24
+; RV32-NEXT: mul a0, a0, a1
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
@@ -2386,23 +2361,23 @@ define <vscale x 16 x i64> @vp_ctpop_nxv16i64_unmasked(<vscale x 16 x i64> %va,
; RV32-NEXT: vs8r.v v0, (a3) # Unknown-size Folded Spill
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; RV32-NEXT: vand.vv v24, v24, v0
-; RV32-NEXT: vsub.vv v24, v16, v24
+; RV32-NEXT: vsub.vv v16, v16, v24
; RV32-NEXT: lui a3, 209715
; RV32-NEXT: addi a3, a3, 819
; RV32-NEXT: vsetvli a4, zero, e32, m8, ta, ma
; RV32-NEXT: vmv.v.x v0, a3
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; RV32-NEXT: vand.vv v16, v24, v0
-; RV32-NEXT: vsrl.vi v24, v24, 2
+; RV32-NEXT: vand.vv v24, v16, v0
+; RV32-NEXT: vsrl.vi v16, v16, 2
; RV32-NEXT: csrr a3, vlenb
; RV32-NEXT: slli a3, a3, 4
; RV32-NEXT: add a3, sp, a3
; RV32-NEXT: addi a3, a3, 16
; RV32-NEXT: vs8r.v v0, (a3) # Unknown-size Folded Spill
-; RV32-NEXT: vand.vv v24, v24, v0
-; RV32-NEXT: vadd.vv v24, v16, v24
-; RV32-NEXT: vsrl.vi v16, v24, 4
+; RV32-NEXT: vand.vv v16, v16, v0
; RV32-NEXT: vadd.vv v16, v24, v16
+; RV32-NEXT: vsrl.vi v24, v16, 4
+; RV32-NEXT: vadd.vv v16, v16, v24
; RV32-NEXT: lui a3, 61681
; RV32-NEXT: addi a3, a3, -241
; RV32-NEXT: vsetvli a4, zero, e32, m8, ta, ma
@@ -2437,16 +2412,16 @@ define <vscale x 16 x i64> @vp_ctpop_nxv16i64_unmasked(<vscale x 16 x i64> %va,
; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vl8r.v v0, (a0) # Unknown-size Folded Reload
; RV32-NEXT: vand.vv v24, v24, v0
-; RV32-NEXT: vsub.vv v24, v8, v24
+; RV32-NEXT: vsub.vv v8, v8, v24
; RV32-NEXT: csrr a0, vlenb
; RV32-NEXT: slli a0, a0, 4
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vl8r.v v0, (a0) # Unknown-size Folded Reload
-; RV32-NEXT: vand.vv v8, v24, v0
-; RV32-NEXT: vsrl.vi v24, v24, 2
-; RV32-NEXT: vand.vv v24, v24, v0
-; RV32-NEXT: vadd.vv v8, v8, v24
+; RV32-NEXT: vand.vv v24, v8, v0
+; RV32-NEXT: vsrl.vi v8, v8, 2
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vadd.vv v8, v24, v8
; RV32-NEXT: vsrl.vi v24, v8, 4
; RV32-NEXT: vadd.vv v8, v8, v24
; RV32-NEXT: csrr a0, vlenb
diff --git a/llvm/test/CodeGen/RISCV/rvv/cttz-vp.ll b/llvm/test/CodeGen/RISCV/rvv/cttz-vp.ll
index 0ef0a431dabc43..d36240e493e41d 100644
--- a/llvm/test/CodeGen/RISCV/rvv/cttz-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/cttz-vp.ll
@@ -2266,7 +2266,7 @@ define <vscale x 16 x i64> @vp_cttz_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: vnot.v v16, v16, v0.t
; RV32-NEXT: vand.vv v8, v16, v8, v0.t
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: li a5, 40
+; RV32-NEXT: li a5, 24
; RV32-NEXT: mul a4, a4, a5
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
@@ -2283,12 +2283,18 @@ define <vscale x 16 x i64> @vp_cttz_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: vsetvli a5, zero, e32, m8, ta, ma
; RV32-NEXT: vmv.v.x v8, a4
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: li a5, 24
+; RV32-NEXT: li a5, 40
; RV32-NEXT: mul a4, a4, a5
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
; RV32-NEXT: vs8r.v v8, (a4) # Unknown-size Folded Spill
; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: li a5, 40
+; RV32-NEXT: mul a4, a4, a5
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 16
+; RV32-NEXT: vl8r.v v8, (a4) # Unknown-size Folded Reload
+; RV32-NEXT: csrr a4, vlenb
; RV32-NEXT: li a5, 48
; RV32-NEXT: mul a4, a4, a5
; RV32-NEXT: add a4, sp, a4
@@ -2297,55 +2303,51 @@ define <vscale x 16 x i64> @vp_cttz_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: vsetvli zero, a3, e64, m8, ta, ma
; RV32-NEXT: vand.vv v8, v16, v8, v0.t
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: li a5, 40
+; RV32-NEXT: li a5, 24
; RV32-NEXT: mul a4, a4, a5
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
; RV32-NEXT: vl8r.v v16, (a4) # Unknown-size Folded Reload
-; RV32-NEXT: vsub.vv v8, v16, v8, v0.t
+; RV32-NEXT: vsub.vv v16, v16, v8, v0.t
+; RV32-NEXT: lui a4, 209715
+; RV32-NEXT: addi a4, a4, 819
+; RV32-NEXT: vsetvli a5, zero, e32, m8, ta, ma
+; RV32-NEXT: vmv.v.x v8, a4
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: li a5, 40
+; RV32-NEXT: li a5, 48
; RV32-NEXT: mul a4, a4, a5
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
; RV32-NEXT: vs8r.v v8, (a4) # Unknown-size Folded Spill
-; RV32-NEXT: lui a4, 209715
-; RV32-NEXT: addi a4, a4, 819
-; RV32-NEXT: vsetvli a5, zero, e32, m8, ta, ma
-; RV32-NEXT: vmv.v.x v16, a4
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: li a5, 40
+; RV32-NEXT: li a5, 48
; RV32-NEXT: mul a4, a4, a5
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
; RV32-NEXT: vl8r.v v8, (a4) # Unknown-size Folded Reload
; RV32-NEXT: vsetvli zero, a3, e64, m8, ta, ma
-; RV32-NEXT: vand.vv v8, v8, v16, v0.t
+; RV32-NEXT: vand.vv v8, v16, v8, v0.t
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: slli a4, a4, 4
+; RV32-NEXT: li a5, 24
+; RV32-NEXT: mul a4, a4, a5
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
; RV32-NEXT: vs8r.v v8, (a4) # Unknown-size Folded Spill
+; RV32-NEXT: vsrl.vi v16, v16, 2, v0.t
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: li a5, 40
+; RV32-NEXT: li a5, 48
; RV32-NEXT: mul a4, a4, a5
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
; RV32-NEXT: vl8r.v v8, (a4) # Unknown-size Folded Reload
-; RV32-NEXT: vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT: vand.vv v16, v16, v8, v0.t
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: li a5, 48
+; RV32-NEXT: li a5, 24
; RV32-NEXT: mul a4, a4, a5
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
-; RV32-NEXT: vs8r.v v16, (a4) # Unknown-size Folded Spill
-; RV32-NEXT: vand.vv v8, v8, v16, v0.t
-; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: slli a4, a4, 4
-; RV32-NEXT: add a4, sp, a4
-; RV32-NEXT: addi a4, a4, 16
-; RV32-NEXT: vl8r.v v16, (a4) # Unknown-size Folded Reload
-; RV32-NEXT: vadd.vv v8, v16, v8, v0.t
+; RV32-NEXT: vl8r.v v8, (a4) # Unknown-size Folded Reload
+; RV32-NEXT: vadd.vv v8, v8, v16, v0.t
; RV32-NEXT: vsrl.vi v16, v8, 4, v0.t
; RV32-NEXT: vadd.vv v8, v8, v16, v0.t
; RV32-NEXT: lui a4, 61681
@@ -2353,26 +2355,30 @@ define <vscale x 16 x i64> @vp_cttz_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: vsetvli a5, zero, e32, m8, ta, ma
; RV32-NEXT: vmv.v.x v16, a4
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: slli a4, a4, 4
+; RV32-NEXT: li a5, 24
+; RV32-NEXT: mul a4, a4, a5
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
; RV32-NEXT: vs8r.v v16, (a4) # Unknown-size Folded Spill
; RV32-NEXT: vsetvli zero, a3, e64, m8, ta, ma
-; RV32-NEXT: vand.vv v16, v8, v16, v0.t
+; RV32-NEXT: vand.vv v8, v8, v16, v0.t
; RV32-NEXT: lui a4, 4112
; RV32-NEXT: addi a4, a4, 257
; RV32-NEXT: vsetvli a5, zero, e32, m8, ta, ma
-; RV32-NEXT: vmv.v.x v8, a4
+; RV32-NEXT: vmv.v.x v16, a4
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: slli a4, a4, 3
+; RV32-NEXT: slli a4, a4, 4
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
-; RV32-NEXT: vs8r.v v8, (a4) # Unknown-size Folded Spill
+; RV32-NEXT: vs8r.v v16, (a4) # Unknown-size Folded Spill
; RV32-NEXT: vsetvli zero, a3, e64, m8, ta, ma
-; RV32-NEXT: vmul.vv v16, v16, v8, v0.t
+; RV32-NEXT: vmul.vv v8, v8, v16, v0.t
; RV32-NEXT: li a3, 56
-; RV32-NEXT: vsrl.vx v8, v16, a3, v0.t
-; RV32-NEXT: addi a4, sp, 16
+; RV32-NEXT: vsrl.vx v8, v8, a3, v0.t
+; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: slli a4, a4, 3
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 16
; RV32-NEXT: vs8r.v v8, (a4) # Unknown-size Folded Spill
; RV32-NEXT: bltu a0, a1, .LBB46_2
; RV32-NEXT: # %bb.1:
@@ -2382,40 +2388,32 @@ define <vscale x 16 x i64> @vp_cttz_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: slli a1, a1, 5
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
; RV32-NEXT: vsetvli zero, a0, e64, m8, ta, ma
-; RV32-NEXT: vsub.vx v16, v8, a2, v0.t
-; RV32-NEXT: vnot.v v8, v8, v0.t
-; RV32-NEXT: vand.vv v8, v8, v16, v0.t
-; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: slli a0, a0, 5
-; RV32-NEXT: add a0, sp, a0
-; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vsub.vx v8, v16, a2, v0.t
+; RV32-NEXT: vnot.v v16, v16, v0.t
+; RV32-NEXT: vand.vv v8, v16, v8, v0.t
+; RV32-NEXT: addi a0, sp, 16
; RV32-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; RV32-NEXT: vsrl.vi v8, v8, 1, v0.t
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: li a1, 40
-; RV32-NEXT: mul a0, a0, a1
+; RV32-NEXT: slli a0, a0, 5
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: li a1, 24
+; RV32-NEXT: li a1, 40
; RV32-NEXT: mul a0, a0, a1
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: li a1, 40
-; RV32-NEXT: mul a0, a0, a1
+; RV32-NEXT: slli a0, a0, 5
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
; RV32-NEXT: vand.vv v16, v8, v16, v0.t
-; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: slli a0, a0, 5
-; RV32-NEXT: add a0, sp, a0
-; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: addi a0, sp, 16
; RV32-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
; RV32-NEXT: vsub.vv v8, v8, v16, v0.t
; RV32-NEXT: csrr a0, vlenb
@@ -2442,6 +2440,7 @@ define <vscale x 16 x i64> @vp_cttz_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
+; RV32-NEXT: vmv8r.v v16, v8
; RV32-NEXT: csrr a0, vlenb
; RV32-NEXT: li a1, 40
; RV32-NEXT: mul a0, a0, a1
@@ -2449,12 +2448,6 @@ define <vscale x 16 x i64> @vp_cttz_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
; RV32-NEXT: vsrl.vi v8, v8, 2, v0.t
-; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: li a1, 48
-; RV32-NEXT: mul a0, a0, a1
-; RV32-NEXT: add a0, sp, a0
-; RV32-NEXT: addi a0, a0, 16
-; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; RV32-NEXT: vand.vv v8, v8, v16, v0.t
; RV32-NEXT: csrr a0, vlenb
; RV32-NEXT: slli a0, a0, 5
@@ -2465,19 +2458,23 @@ define <vscale x 16 x i64> @vp_cttz_nxv16i64(<vscale x 16 x i64> %va, <vscale x
; RV32-NEXT: vsrl.vi v16, v8, 4, v0.t
; RV32-NEXT: vadd.vv v8, v8, v16, v0.t
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: li a1, 24
+; RV32-NEXT: mul a0, a0, a1
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; RV32-NEXT: vand.vv v8, v8, v16, v0.t
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: slli a0, a0, 4
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; RV32-NEXT: vmul.vv v8, v8, v16, v0.t
; RV32-NEXT: vsrl.vx v8, v8, a3, v0.t
-; RV32-NEXT: addi a0, sp, 16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; RV32-NEXT: csrr a0, vlenb
; RV32-NEXT: li a1, 56
@@ -2608,15 +2605,9 @@ define <vscale x 16 x i64> @vp_cttz_nxv16i64_unmasked(<vscale x 16 x i64> %va, i
; RV32-NEXT: addi sp, sp, -16
; RV32-NEXT: .cfi_def_cfa_offset 16
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a2, 40
-; RV32-NEXT: mul a1, a1, a2
-; RV32-NEXT: sub sp, sp, a1
-; RV32-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x28, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 40 * vlenb
-; RV32-NEXT: csrr a1, vlenb
; RV32-NEXT: slli a1, a1, 5
-; RV32-NEXT: add a1, sp, a1
-; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
+; RV32-NEXT: sub sp, sp, a1
+; RV32-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 32 * vlenb
; RV32-NEXT: csrr a1, vlenb
; RV32-NEXT: sub a2, a0, a1
; RV32-NEXT: sltu a3, a0, a2
@@ -2624,22 +2615,22 @@ define <vscale x 16 x i64> @vp_cttz_nxv16i64_unmasked(<vscale x 16 x i64> %va, i
; RV32-NEXT: and a3, a3, a2
; RV32-NEXT: li a2, 1
; RV32-NEXT: vsetvli zero, a3, e64, m8, ta, ma
-; RV32-NEXT: vsub.vx v8, v16, a2
+; RV32-NEXT: vsub.vx v24, v16, a2
; RV32-NEXT: vnot.v v16, v16
-; RV32-NEXT: vand.vv v16, v16, v8
+; RV32-NEXT: vand.vv v16, v16, v24
; RV32-NEXT: vsrl.vi v24, v16, 1
; RV32-NEXT: lui a4, 349525
; RV32-NEXT: addi a4, a4, 1365
; RV32-NEXT: vsetvli a5, zero, e32, m8, ta, ma
-; RV32-NEXT: vmv.v.x v8, a4
+; RV32-NEXT: vmv.v.x v0, a4
; RV32-NEXT: csrr a4, vlenb
; RV32-NEXT: li a5, 24
; RV32-NEXT: mul a4, a4, a5
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
-; RV32-NEXT: vs8r.v v8, (a4) # Unknown-size Folded Spill
+; RV32-NEXT: vs8r.v v0, (a4) # Unknown-size Folded Spill
; RV32-NEXT: vsetvli zero, a3, e64, m8, ta, ma
-; RV32-NEXT: vand.vv v24, v24, v8
+; RV32-NEXT: vand.vv v24, v24, v0
; RV32-NEXT: vsub.vv v16, v16, v24
; RV32-NEXT: lui a4, 209715
; RV32-NEXT: addi a4, a4, 819
@@ -2648,6 +2639,11 @@ define <vscale x 16 x i64> @vp_cttz_nxv16i64_unmasked(<vscale x 16 x i64> %va, i
; RV32-NEXT: vsetvli zero, a3, e64, m8, ta, ma
; RV32-NEXT: vand.vv v24, v16, v0
; RV32-NEXT: vsrl.vi v16, v16, 2
+; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: slli a4, a4, 4
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 16
+; RV32-NEXT: vs8r.v v0, (a4) # Unknown-size Folded Spill
; RV32-NEXT: vand.vv v16, v16, v0
; RV32-NEXT: vadd.vv v16, v24, v16
; RV32-NEXT: vsrl.vi v24, v16, 4
@@ -2655,50 +2651,46 @@ define <vscale x 16 x i64> @vp_cttz_nxv16i64_unmasked(<vscale x 16 x i64> %va, i
; RV32-NEXT: lui a4, 61681
; RV32-NEXT: addi a4, a4, -241
; RV32-NEXT: vsetvli a5, zero, e32, m8, ta, ma
-; RV32-NEXT: vmv.v.x v8, a4
+; RV32-NEXT: vmv.v.x v24, a4
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: slli a4, a4, 4
+; RV32-NEXT: slli a4, a4, 3
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
-; RV32-NEXT: vs8r.v v8, (a4) # Unknown-size Folded Spill
+; RV32-NEXT: vs8r.v v24, (a4) # Unknown-size Folded Spill
; RV32-NEXT: vsetvli zero, a3, e64, m8, ta, ma
-; RV32-NEXT: vand.vv v8, v16, v8
+; RV32-NEXT: vand.vv v16, v16, v24
; RV32-NEXT: lui a4, 4112
; RV32-NEXT: addi a4, a4, 257
; RV32-NEXT: vsetvli a5, zero, e32, m8, ta, ma
-; RV32-NEXT: vmv.v.x v16, a4
-; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: slli a4, a4, 3
-; RV32-NEXT: add a4, sp, a4
-; RV32-NEXT: addi a4, a4, 16
-; RV32-NEXT: vs8r.v v16, (a4) # Unknown-size Folded Spill
+; RV32-NEXT: vmv.v.x v24, a4
+; RV32-NEXT: addi a4, sp, 16
+; RV32-NEXT: vs8r.v v24, (a4) # Unknown-size Folded Spill
; RV32-NEXT: vsetvli zero, a3, e64, m8, ta, ma
-; RV32-NEXT: vmul.vv v8, v8, v16
+; RV32-NEXT: vmul.vv v16, v16, v24
; RV32-NEXT: li a3, 56
-; RV32-NEXT: vsrl.vx v8, v8, a3
-; RV32-NEXT: addi a4, sp, 16
-; RV32-NEXT: vs8r.v v8, (a4) # Unknown-size Folded Spill
+; RV32-NEXT: vsrl.vx v16, v16, a3
; RV32-NEXT: bltu a0, a1, .LBB47_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a0, a1
; RV32-NEXT: .LBB47_2:
-; RV32-NEXT: slli a1, a1, 5
-; RV32-NEXT: add a1, sp, a1
-; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v24, (a1) # Unknown-size Folded Reload
; RV32-NEXT: vsetvli zero, a0, e64, m8, ta, ma
-; RV32-NEXT: vsub.vx v8, v24, a2
-; RV32-NEXT: vnot.v v24, v24
-; RV32-NEXT: vand.vv v8, v24, v8
+; RV32-NEXT: vsub.vx v24, v8, a2
+; RV32-NEXT: vnot.v v8, v8
+; RV32-NEXT: vand.vv v8, v8, v24
; RV32-NEXT: vsrl.vi v24, v8, 1
; RV32-NEXT: csrr a0, vlenb
; RV32-NEXT: li a1, 24
; RV32-NEXT: mul a0, a0, a1
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
-; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
-; RV32-NEXT: vand.vv v24, v24, v16
+; RV32-NEXT: vl8r.v v0, (a0) # Unknown-size Folded Reload
+; RV32-NEXT: vand.vv v24, v24, v0
; RV32-NEXT: vsub.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v0, (a0) # Unknown-size Folded Reload
; RV32-NEXT: vand.vv v24, v8, v0
; RV32-NEXT: vsrl.vi v8, v8, 2
; RV32-NEXT: vand.vv v8, v8, v0
@@ -2706,23 +2698,17 @@ define <vscale x 16 x i64> @vp_cttz_nxv16i64_unmasked(<vscale x 16 x i64> %va, i
; RV32-NEXT: vsrl.vi v24, v8, 4
; RV32-NEXT: vadd.vv v8, v8, v24
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: slli a0, a0, 4
-; RV32-NEXT: add a0, sp, a0
-; RV32-NEXT: addi a0, a0, 16
-; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
-; RV32-NEXT: vand.vv v8, v8, v16
-; RV32-NEXT: csrr a0, vlenb
; RV32-NEXT: slli a0, a0, 3
; RV32-NEXT: add a0, sp, a0
; RV32-NEXT: addi a0, a0, 16
-; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
-; RV32-NEXT: vmul.vv v8, v8, v16
-; RV32-NEXT: vsrl.vx v8, v8, a3
+; RV32-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v24
; RV32-NEXT: addi a0, sp, 16
-; RV32-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v24
+; RV32-NEXT: vsrl.vx v8, v8, a3
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: li a1, 40
-; RV32-NEXT: mul a0, a0, a1
+; RV32-NEXT: slli a0, a0, 5
; RV32-NEXT: add sp, sp, a0
; RV32-NEXT: addi sp, sp, 16
; RV32-NEXT: ret
diff --git a/llvm/test/CodeGen/RISCV/rvv/remat.ll b/llvm/test/CodeGen/RISCV/rvv/remat.ll
index 2b12249378eb1f..514612cd0525d8 100644
--- a/llvm/test/CodeGen/RISCV/rvv/remat.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/remat.ll
@@ -171,3 +171,144 @@ define void @vmv.v.i(ptr %p) {
store volatile <vscale x 8 x i64> %vmv.v.i, ptr %p
ret void
}
+
+; The live range of %x needs extended down to the use of vmv.v.x at the end of
+; the block.
+define void @vmv.v.x_needs_extended(ptr %p, i64 %x) {
+; POSTRA-LABEL: vmv.v.x_needs_extended:
+; POSTRA: # %bb.0:
+; POSTRA-NEXT: addi sp, sp, -16
+; POSTRA-NEXT: .cfi_def_cfa_offset 16
+; POSTRA-NEXT: csrr a2, vlenb
+; POSTRA-NEXT: slli a2, a2, 3
+; POSTRA-NEXT: sub sp, sp, a2
+; POSTRA-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
+; POSTRA-NEXT: vsetvli a2, zero, e64, m8, ta, ma
+; POSTRA-NEXT: vmv.v.x v8, a1
+; POSTRA-NEXT: addi a1, sp, 16
+; POSTRA-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
+; POSTRA-NEXT: vs8r.v v8, (a0)
+; POSTRA-NEXT: vl8re64.v v16, (a0)
+; POSTRA-NEXT: vl8re64.v v24, (a0)
+; POSTRA-NEXT: vl8re64.v v0, (a0)
+; POSTRA-NEXT: vl8re64.v v8, (a0)
+; POSTRA-NEXT: vs8r.v v8, (a0)
+; POSTRA-NEXT: vs8r.v v0, (a0)
+; POSTRA-NEXT: vs8r.v v24, (a0)
+; POSTRA-NEXT: vs8r.v v16, (a0)
+; POSTRA-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
+; POSTRA-NEXT: vs8r.v v8, (a0)
+; POSTRA-NEXT: csrr a0, vlenb
+; POSTRA-NEXT: slli a0, a0, 3
+; POSTRA-NEXT: add sp, sp, a0
+; POSTRA-NEXT: addi sp, sp, 16
+; POSTRA-NEXT: ret
+;
+; PRERA-LABEL: vmv.v.x_needs_extended:
+; PRERA: # %bb.0:
+; PRERA-NEXT: addi sp, sp, -16
+; PRERA-NEXT: .cfi_def_cfa_offset 16
+; PRERA-NEXT: csrr a2, vlenb
+; PRERA-NEXT: slli a2, a2, 3
+; PRERA-NEXT: sub sp, sp, a2
+; PRERA-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
+; PRERA-NEXT: vsetvli a2, zero, e64, m8, ta, ma
+; PRERA-NEXT: vmv.v.x v8, a1
+; PRERA-NEXT: vs8r.v v8, (a0)
+; PRERA-NEXT: vl8re64.v v16, (a0)
+; PRERA-NEXT: addi a1, sp, 16
+; PRERA-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
+; PRERA-NEXT: vl8re64.v v24, (a0)
+; PRERA-NEXT: vl8re64.v v0, (a0)
+; PRERA-NEXT: vl8re64.v v16, (a0)
+; PRERA-NEXT: vs8r.v v16, (a0)
+; PRERA-NEXT: vs8r.v v0, (a0)
+; PRERA-NEXT: vs8r.v v24, (a0)
+; PRERA-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
+; PRERA-NEXT: vs8r.v v16, (a0)
+; PRERA-NEXT: vs8r.v v8, (a0)
+; PRERA-NEXT: csrr a0, vlenb
+; PRERA-NEXT: slli a0, a0, 3
+; PRERA-NEXT: add sp, sp, a0
+; PRERA-NEXT: addi sp, sp, 16
+; PRERA-NEXT: ret
+ %vmv.v.x = call <vscale x 8 x i64> @llvm.riscv.vmv.v.x.nxv8i64(<vscale x 8 x i64> poison, i64 %x, i64 -1)
+ store volatile <vscale x 8 x i64> %vmv.v.x, ptr %p
+
+ %a = load volatile <vscale x 8 x i64>, ptr %p
+ %b = load volatile <vscale x 8 x i64>, ptr %p
+ %c = load volatile <vscale x 8 x i64>, ptr %p
+ %d = load volatile <vscale x 8 x i64>, ptr %p
+ store volatile <vscale x 8 x i64> %d, ptr %p
+ store volatile <vscale x 8 x i64> %c, ptr %p
+ store volatile <vscale x 8 x i64> %b, ptr %p
+ store volatile <vscale x 8 x i64> %a, ptr %p
+
+ store volatile <vscale x 8 x i64> %vmv.v.x, ptr %p
+ ret void
+}
+
+define void @vmv.v.x_live(ptr %p, i64 %x) {
+; POSTRA-LABEL: vmv.v.x_live:
+; POSTRA: # %bb.0:
+; POSTRA-NEXT: vsetvli a2, zero, e64, m8, ta, ma
+; POSTRA-NEXT: vmv.v.x v8, a1
+; POSTRA-NEXT: vs8r.v v8, (a0)
+; POSTRA-NEXT: vl8re64.v v16, (a0)
+; POSTRA-NEXT: vl8re64.v v24, (a0)
+; POSTRA-NEXT: vl8re64.v v0, (a0)
+; POSTRA-NEXT: vl8re64.v v8, (a0)
+; POSTRA-NEXT: vs8r.v v8, (a0)
+; POSTRA-NEXT: vs8r.v v0, (a0)
+; POSTRA-NEXT: vs8r.v v24, (a0)
+; POSTRA-NEXT: vs8r.v v16, (a0)
+; POSTRA-NEXT: vmv.v.x v8, a1
+; POSTRA-NEXT: vs8r.v v8, (a0)
+; POSTRA-NEXT: sd a1, 0(a0)
+; POSTRA-NEXT: ret
+;
+; PRERA-LABEL: vmv.v.x_live:
+; PRERA: # %bb.0:
+; PRERA-NEXT: addi sp, sp, -16
+; PRERA-NEXT: .cfi_def_cfa_offset 16
+; PRERA-NEXT: csrr a2, vlenb
+; PRERA-NEXT: slli a2, a2, 3
+; PRERA-NEXT: sub sp, sp, a2
+; PRERA-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
+; PRERA-NEXT: vsetvli a2, zero, e64, m8, ta, ma
+; PRERA-NEXT: vmv.v.x v8, a1
+; PRERA-NEXT: vs8r.v v8, (a0)
+; PRERA-NEXT: vl8re64.v v16, (a0)
+; PRERA-NEXT: addi a2, sp, 16
+; PRERA-NEXT: vs8r.v v16, (a2) # Unknown-size Folded Spill
+; PRERA-NEXT: vl8re64.v v24, (a0)
+; PRERA-NEXT: vl8re64.v v0, (a0)
+; PRERA-NEXT: vl8re64.v v16, (a0)
+; PRERA-NEXT: vs8r.v v16, (a0)
+; PRERA-NEXT: vs8r.v v0, (a0)
+; PRERA-NEXT: vs8r.v v24, (a0)
+; PRERA-NEXT: vl8r.v v16, (a2) # Unknown-size Folded Reload
+; PRERA-NEXT: vs8r.v v16, (a0)
+; PRERA-NEXT: vs8r.v v8, (a0)
+; PRERA-NEXT: sd a1, 0(a0)
+; PRERA-NEXT: csrr a0, vlenb
+; PRERA-NEXT: slli a0, a0, 3
+; PRERA-NEXT: add sp, sp, a0
+; PRERA-NEXT: addi sp, sp, 16
+; PRERA-NEXT: ret
+ %vmv.v.x = call <vscale x 8 x i64> @llvm.riscv.vmv.v.x.nxv8i64(<vscale x 8 x i64> poison, i64 %x, i64 -1)
+ store volatile <vscale x 8 x i64> %vmv.v.x, ptr %p
+
+ %a = load volatile <vscale x 8 x i64>, ptr %p
+ %b = load volatile <vscale x 8 x i64>, ptr %p
+ %c = load volatile <vscale x 8 x i64>, ptr %p
+ %d = load volatile <vscale x 8 x i64>, ptr %p
+ store volatile <vscale x 8 x i64> %d, ptr %p
+ store volatile <vscale x 8 x i64> %c, ptr %p
+ store volatile <vscale x 8 x i64> %b, ptr %p
+ store volatile <vscale x 8 x i64> %a, ptr %p
+
+ store volatile <vscale x 8 x i64> %vmv.v.x, ptr %p
+ store volatile i64 %x, ptr %p
+ ret void
+}
More information about the llvm-commits
mailing list