[RISCV] Spilling for RISC-V V extension. (2nd version)
Differential Revision: https://reviews.llvm.org/D95148
diff --git a/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector-csr.ll b/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector-csr.ll
new file mode 100644
index 0000000..3588818
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector-csr.ll
@@ -0,0 +1,87 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+experimental-v,+d -mattr=+d -O0 < %s \
+; RUN: | FileCheck --check-prefix=SPILL-O0 %s
+; RUN: llc -mtriple=riscv32 -mattr=+experimental-v,+d -mattr=+d -O2 < %s \
+; RUN: | FileCheck --check-prefix=SPILL-O2 %s
+
+@.str = private unnamed_addr constant [6 x i8] c"hello\00", align 1
+
+define <vscale x 1 x double> @foo(<vscale x 1 x double> %a, <vscale x 1 x double> %b, <vscale x 1 x double> %c, i32 %gvl) nounwind
+; SPILL-O0-LABEL: foo:
+; SPILL-O0: # %bb.0:
+; SPILL-O0-NEXT: addi sp, sp, -16
+; SPILL-O0-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
+; SPILL-O0-NEXT: csrr a1, vlenb
+; SPILL-O0-NEXT: slli a1, a1, 1
+; SPILL-O0-NEXT: sub sp, sp, a1
+; SPILL-O0-NEXT: csrr a1, vlenb
+; SPILL-O0-NEXT: slli a1, a1, 1
+; SPILL-O0-NEXT: add a1, sp, a1
+; SPILL-O0-NEXT: sw a0, 8(a1) # 4-byte Folded Spill
+; SPILL-O0-NEXT: csrr a1, vlenb
+; SPILL-O0-NEXT: add a1, sp, a1
+; SPILL-O0-NEXT: vs1r.v v8, (a1) # Unknown-size Folded Spill
+; SPILL-O0-NEXT: vsetvli a0, a0, e64,m1,ta,mu
+; SPILL-O0-NEXT: vfadd.vv v25, v8, v9
+; SPILL-O0-NEXT: vs1r.v v25, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT: lui a0, %hi(.L.str)
+; SPILL-O0-NEXT: addi a0, a0, %lo(.L.str)
+; SPILL-O0-NEXT: call puts@plt
+; SPILL-O0-NEXT: vl1r.v v25, (sp) # Unknown-size Folded Reload
+; SPILL-O0-NEXT: csrr a1, vlenb
+; SPILL-O0-NEXT: add a1, sp, a1
+; SPILL-O0-NEXT: vl1r.v v8, (a1) # Unknown-size Folded Reload
+; SPILL-O0-NEXT: # kill: def $x11 killed $x10
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 1
+; SPILL-O0-NEXT: add a0, sp, a0
+; SPILL-O0-NEXT: lw a0, 8(a0) # 4-byte Folded Reload
+; SPILL-O0-NEXT: vsetvli a0, a0, e64,m1,ta,mu
+; SPILL-O0-NEXT: vfadd.vv v8, v8, v25
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 1
+; SPILL-O0-NEXT: add sp, sp, a0
+; SPILL-O0-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; SPILL-O0-NEXT: addi sp, sp, 16
+; SPILL-O0-NEXT: ret
+;
+; SPILL-O2-LABEL: foo:
+; SPILL-O2: # %bb.0:
+; SPILL-O2-NEXT: addi sp, sp, -16
+; SPILL-O2-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
+; SPILL-O2-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
+; SPILL-O2-NEXT: csrr a1, vlenb
+; SPILL-O2-NEXT: slli a1, a1, 1
+; SPILL-O2-NEXT: sub sp, sp, a1
+; SPILL-O2-NEXT: mv s0, a0
+; SPILL-O2-NEXT: vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: vsetvli a0, a0, e64,m1,ta,mu
+; SPILL-O2-NEXT: vfadd.vv v25, v8, v9
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: vs1r.v v25, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: lui a0, %hi(.L.str)
+; SPILL-O2-NEXT: addi a0, a0, %lo(.L.str)
+; SPILL-O2-NEXT: call puts@plt
+; SPILL-O2-NEXT: vsetvli a0, s0, e64,m1,ta,mu
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: vl1r.v v25, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: vl1r.v v26, (sp) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: vfadd.vv v8, v26, v25
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 1
+; SPILL-O2-NEXT: add sp, sp, a0
+; SPILL-O2-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
+; SPILL-O2-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; SPILL-O2-NEXT: addi sp, sp, 16
+; SPILL-O2-NEXT: ret
+{
+ %x = call <vscale x 1 x double> @llvm.riscv.vfadd.nxv1f64.nxv1f64(<vscale x 1 x double> %a, <vscale x 1 x double> %b, i32 %gvl)
+ %call = call signext i32 @puts(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i64 0, i64 0))
+ %z = call <vscale x 1 x double> @llvm.riscv.vfadd.nxv1f64.nxv1f64(<vscale x 1 x double> %a, <vscale x 1 x double> %x, i32 %gvl)
+ ret <vscale x 1 x double> %z
+}
+
+declare <vscale x 1 x double> @llvm.riscv.vfadd.nxv1f64.nxv1f64(<vscale x 1 x double> %a, <vscale x 1 x double> %b, i32 %gvl)
+declare i32 @puts(i8*);
diff --git a/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector.ll b/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector.ll
new file mode 100644
index 0000000..3058979
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector.ll
@@ -0,0 +1,172 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+experimental-v -O0 < %s \
+; RUN: | FileCheck --check-prefix=SPILL-O0 %s
+; RUN: llc -mtriple=riscv32 -mattr=+experimental-v -O2 < %s \
+; RUN: | FileCheck --check-prefix=SPILL-O2 %s
+
+define <vscale x 1 x i32> @spill_lmul_mf2(<vscale x 1 x i32> %va) nounwind {
+; SPILL-O0-LABEL: spill_lmul_mf2:
+; SPILL-O0: # %bb.0: # %entry
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: sub sp, sp, a0
+; SPILL-O0-NEXT: vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT: #APP
+; SPILL-O0-NEXT: #NO_APP
+; SPILL-O0-NEXT: vl1r.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: add sp, sp, a0
+; SPILL-O0-NEXT: ret
+;
+; SPILL-O2-LABEL: spill_lmul_mf2:
+; SPILL-O2: # %bb.0: # %entry
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: sub sp, sp, a0
+; SPILL-O2-NEXT: vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: #APP
+; SPILL-O2-NEXT: #NO_APP
+; SPILL-O2-NEXT: vl1r.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: add sp, sp, a0
+; SPILL-O2-NEXT: ret
+entry:
+ call void asm sideeffect "",
+ "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
+
+ ret <vscale x 1 x i32> %va
+}
+
+define <vscale x 2 x i32> @spill_lmul_1(<vscale x 2 x i32> %va) nounwind {
+; SPILL-O0-LABEL: spill_lmul_1:
+; SPILL-O0: # %bb.0: # %entry
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: sub sp, sp, a0
+; SPILL-O0-NEXT: vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT: #APP
+; SPILL-O0-NEXT: #NO_APP
+; SPILL-O0-NEXT: vl1r.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: add sp, sp, a0
+; SPILL-O0-NEXT: ret
+;
+; SPILL-O2-LABEL: spill_lmul_1:
+; SPILL-O2: # %bb.0: # %entry
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: sub sp, sp, a0
+; SPILL-O2-NEXT: vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: #APP
+; SPILL-O2-NEXT: #NO_APP
+; SPILL-O2-NEXT: vl1r.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: add sp, sp, a0
+; SPILL-O2-NEXT: ret
+entry:
+ call void asm sideeffect "",
+ "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
+
+ ret <vscale x 2 x i32> %va
+}
+
+define <vscale x 4 x i32> @spill_lmul_2(<vscale x 4 x i32> %va) nounwind {
+; SPILL-O0-LABEL: spill_lmul_2:
+; SPILL-O0: # %bb.0: # %entry
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 1
+; SPILL-O0-NEXT: sub sp, sp, a0
+; SPILL-O0-NEXT: vs2r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT: #APP
+; SPILL-O0-NEXT: #NO_APP
+; SPILL-O0-NEXT: vl2re8.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 1
+; SPILL-O0-NEXT: add sp, sp, a0
+; SPILL-O0-NEXT: ret
+;
+; SPILL-O2-LABEL: spill_lmul_2:
+; SPILL-O2: # %bb.0: # %entry
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 1
+; SPILL-O2-NEXT: sub sp, sp, a0
+; SPILL-O2-NEXT: vs2r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: #APP
+; SPILL-O2-NEXT: #NO_APP
+; SPILL-O2-NEXT: vl2re8.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 1
+; SPILL-O2-NEXT: add sp, sp, a0
+; SPILL-O2-NEXT: ret
+entry:
+ call void asm sideeffect "",
+ "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
+
+ ret <vscale x 4 x i32> %va
+}
+
+define <vscale x 8 x i32> @spill_lmul_4(<vscale x 8 x i32> %va) nounwind {
+; SPILL-O0-LABEL: spill_lmul_4:
+; SPILL-O0: # %bb.0: # %entry
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 2
+; SPILL-O0-NEXT: sub sp, sp, a0
+; SPILL-O0-NEXT: vs4r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT: #APP
+; SPILL-O0-NEXT: #NO_APP
+; SPILL-O0-NEXT: vl4re8.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 2
+; SPILL-O0-NEXT: add sp, sp, a0
+; SPILL-O0-NEXT: ret
+;
+; SPILL-O2-LABEL: spill_lmul_4:
+; SPILL-O2: # %bb.0: # %entry
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 2
+; SPILL-O2-NEXT: sub sp, sp, a0
+; SPILL-O2-NEXT: vs4r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: #APP
+; SPILL-O2-NEXT: #NO_APP
+; SPILL-O2-NEXT: vl4re8.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 2
+; SPILL-O2-NEXT: add sp, sp, a0
+; SPILL-O2-NEXT: ret
+entry:
+ call void asm sideeffect "",
+ "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
+
+ ret <vscale x 8 x i32> %va
+}
+
+define <vscale x 16 x i32> @spill_lmul_8(<vscale x 16 x i32> %va) nounwind {
+; SPILL-O0-LABEL: spill_lmul_8:
+; SPILL-O0: # %bb.0: # %entry
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 3
+; SPILL-O0-NEXT: sub sp, sp, a0
+; SPILL-O0-NEXT: vs8r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT: #APP
+; SPILL-O0-NEXT: #NO_APP
+; SPILL-O0-NEXT: vl8re8.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 3
+; SPILL-O0-NEXT: add sp, sp, a0
+; SPILL-O0-NEXT: ret
+;
+; SPILL-O2-LABEL: spill_lmul_8:
+; SPILL-O2: # %bb.0: # %entry
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 3
+; SPILL-O2-NEXT: sub sp, sp, a0
+; SPILL-O2-NEXT: vs8r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: #APP
+; SPILL-O2-NEXT: #NO_APP
+; SPILL-O2-NEXT: vl8re8.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 3
+; SPILL-O2-NEXT: add sp, sp, a0
+; SPILL-O2-NEXT: ret
+entry:
+ call void asm sideeffect "",
+ "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
+
+ ret <vscale x 16 x i32> %va
+}
diff --git a/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector-csr.ll b/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector-csr.ll
new file mode 100644
index 0000000..7a55a29
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector-csr.ll
@@ -0,0 +1,87 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v,+d -mattr=+d -O0 < %s \
+; RUN: | FileCheck --check-prefix=SPILL-O0 %s
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v,+d -mattr=+d -O2 < %s \
+; RUN: | FileCheck --check-prefix=SPILL-O2 %s
+
+@.str = private unnamed_addr constant [6 x i8] c"hello\00", align 1
+
+define <vscale x 1 x double> @foo(<vscale x 1 x double> %a, <vscale x 1 x double> %b, <vscale x 1 x double> %c, i64 %gvl) nounwind
+; SPILL-O0-LABEL: foo:
+; SPILL-O0: # %bb.0:
+; SPILL-O0-NEXT: addi sp, sp, -16
+; SPILL-O0-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
+; SPILL-O0-NEXT: csrr a1, vlenb
+; SPILL-O0-NEXT: slli a1, a1, 1
+; SPILL-O0-NEXT: sub sp, sp, a1
+; SPILL-O0-NEXT: csrr a1, vlenb
+; SPILL-O0-NEXT: slli a1, a1, 1
+; SPILL-O0-NEXT: add a1, sp, a1
+; SPILL-O0-NEXT: sd a0, 0(a1) # 8-byte Folded Spill
+; SPILL-O0-NEXT: csrr a1, vlenb
+; SPILL-O0-NEXT: add a1, sp, a1
+; SPILL-O0-NEXT: vs1r.v v8, (a1) # Unknown-size Folded Spill
+; SPILL-O0-NEXT: vsetvli a0, a0, e64,m1,ta,mu
+; SPILL-O0-NEXT: vfadd.vv v25, v8, v9
+; SPILL-O0-NEXT: vs1r.v v25, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT: lui a0, %hi(.L.str)
+; SPILL-O0-NEXT: addi a0, a0, %lo(.L.str)
+; SPILL-O0-NEXT: call puts@plt
+; SPILL-O0-NEXT: vl1r.v v25, (sp) # Unknown-size Folded Reload
+; SPILL-O0-NEXT: csrr a1, vlenb
+; SPILL-O0-NEXT: add a1, sp, a1
+; SPILL-O0-NEXT: vl1r.v v8, (a1) # Unknown-size Folded Reload
+; SPILL-O0-NEXT: # kill: def $x11 killed $x10
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 1
+; SPILL-O0-NEXT: add a0, sp, a0
+; SPILL-O0-NEXT: ld a0, 0(a0) # 8-byte Folded Reload
+; SPILL-O0-NEXT: vsetvli a0, a0, e64,m1,ta,mu
+; SPILL-O0-NEXT: vfadd.vv v8, v8, v25
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 1
+; SPILL-O0-NEXT: add sp, sp, a0
+; SPILL-O0-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; SPILL-O0-NEXT: addi sp, sp, 16
+; SPILL-O0-NEXT: ret
+;
+; SPILL-O2-LABEL: foo:
+; SPILL-O2: # %bb.0:
+; SPILL-O2-NEXT: addi sp, sp, -16
+; SPILL-O2-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
+; SPILL-O2-NEXT: sd s0, 0(sp) # 8-byte Folded Spill
+; SPILL-O2-NEXT: csrr a1, vlenb
+; SPILL-O2-NEXT: slli a1, a1, 1
+; SPILL-O2-NEXT: sub sp, sp, a1
+; SPILL-O2-NEXT: mv s0, a0
+; SPILL-O2-NEXT: vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: vsetvli a0, a0, e64,m1,ta,mu
+; SPILL-O2-NEXT: vfadd.vv v25, v8, v9
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: vs1r.v v25, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: lui a0, %hi(.L.str)
+; SPILL-O2-NEXT: addi a0, a0, %lo(.L.str)
+; SPILL-O2-NEXT: call puts@plt
+; SPILL-O2-NEXT: vsetvli a0, s0, e64,m1,ta,mu
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: vl1r.v v25, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: vl1r.v v26, (sp) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: vfadd.vv v8, v26, v25
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 1
+; SPILL-O2-NEXT: add sp, sp, a0
+; SPILL-O2-NEXT: ld s0, 0(sp) # 8-byte Folded Reload
+; SPILL-O2-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; SPILL-O2-NEXT: addi sp, sp, 16
+; SPILL-O2-NEXT: ret
+{
+ %x = call <vscale x 1 x double> @llvm.riscv.vfadd.nxv1f64.nxv1f64(<vscale x 1 x double> %a, <vscale x 1 x double> %b, i64 %gvl)
+ %call = call signext i32 @puts(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i64 0, i64 0))
+ %z = call <vscale x 1 x double> @llvm.riscv.vfadd.nxv1f64.nxv1f64(<vscale x 1 x double> %a, <vscale x 1 x double> %x, i64 %gvl)
+ ret <vscale x 1 x double> %z
+}
+
+declare <vscale x 1 x double> @llvm.riscv.vfadd.nxv1f64.nxv1f64(<vscale x 1 x double> %a, <vscale x 1 x double> %b, i64 %gvl)
+declare i32 @puts(i8*);
diff --git a/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector.ll b/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector.ll
new file mode 100644
index 0000000..260cf31
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector.ll
@@ -0,0 +1,141 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -O0 < %s \
+; RUN: | FileCheck --check-prefix=SPILL-O0 %s
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -O2 < %s \
+; RUN: | FileCheck --check-prefix=SPILL-O2 %s
+
+define <vscale x 1 x i64> @spill_lmul_1(<vscale x 1 x i64> %va) nounwind {
+; SPILL-O0-LABEL: spill_lmul_1:
+; SPILL-O0: # %bb.0: # %entry
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: sub sp, sp, a0
+; SPILL-O0-NEXT: vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT: #APP
+; SPILL-O0-NEXT: #NO_APP
+; SPILL-O0-NEXT: vl1r.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: add sp, sp, a0
+; SPILL-O0-NEXT: ret
+;
+; SPILL-O2-LABEL: spill_lmul_1:
+; SPILL-O2: # %bb.0: # %entry
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: sub sp, sp, a0
+; SPILL-O2-NEXT: vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: #APP
+; SPILL-O2-NEXT: #NO_APP
+; SPILL-O2-NEXT: vl1r.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: add sp, sp, a0
+; SPILL-O2-NEXT: ret
+entry:
+ call void asm sideeffect "",
+ "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
+
+ ret <vscale x 1 x i64> %va
+}
+
+define <vscale x 2 x i64> @spill_lmul_2(<vscale x 2 x i64> %va) nounwind {
+; SPILL-O0-LABEL: spill_lmul_2:
+; SPILL-O0: # %bb.0: # %entry
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 1
+; SPILL-O0-NEXT: sub sp, sp, a0
+; SPILL-O0-NEXT: vs2r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT: #APP
+; SPILL-O0-NEXT: #NO_APP
+; SPILL-O0-NEXT: vl2re8.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 1
+; SPILL-O0-NEXT: add sp, sp, a0
+; SPILL-O0-NEXT: ret
+;
+; SPILL-O2-LABEL: spill_lmul_2:
+; SPILL-O2: # %bb.0: # %entry
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 1
+; SPILL-O2-NEXT: sub sp, sp, a0
+; SPILL-O2-NEXT: vs2r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: #APP
+; SPILL-O2-NEXT: #NO_APP
+; SPILL-O2-NEXT: vl2re8.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 1
+; SPILL-O2-NEXT: add sp, sp, a0
+; SPILL-O2-NEXT: ret
+entry:
+ call void asm sideeffect "",
+ "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
+
+ ret <vscale x 2 x i64> %va
+}
+
+define <vscale x 4 x i64> @spill_lmul_4(<vscale x 4 x i64> %va) nounwind {
+; SPILL-O0-LABEL: spill_lmul_4:
+; SPILL-O0: # %bb.0: # %entry
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 2
+; SPILL-O0-NEXT: sub sp, sp, a0
+; SPILL-O0-NEXT: vs4r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT: #APP
+; SPILL-O0-NEXT: #NO_APP
+; SPILL-O0-NEXT: vl4re8.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 2
+; SPILL-O0-NEXT: add sp, sp, a0
+; SPILL-O0-NEXT: ret
+;
+; SPILL-O2-LABEL: spill_lmul_4:
+; SPILL-O2: # %bb.0: # %entry
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 2
+; SPILL-O2-NEXT: sub sp, sp, a0
+; SPILL-O2-NEXT: vs4r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: #APP
+; SPILL-O2-NEXT: #NO_APP
+; SPILL-O2-NEXT: vl4re8.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 2
+; SPILL-O2-NEXT: add sp, sp, a0
+; SPILL-O2-NEXT: ret
+entry:
+ call void asm sideeffect "",
+ "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
+
+ ret <vscale x 4 x i64> %va
+}
+
+define <vscale x 8 x i64> @spill_lmul_8(<vscale x 8 x i64> %va) nounwind {
+; SPILL-O0-LABEL: spill_lmul_8:
+; SPILL-O0: # %bb.0: # %entry
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 3
+; SPILL-O0-NEXT: sub sp, sp, a0
+; SPILL-O0-NEXT: vs8r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT: #APP
+; SPILL-O0-NEXT: #NO_APP
+; SPILL-O0-NEXT: vl8re8.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O0-NEXT: csrr a0, vlenb
+; SPILL-O0-NEXT: slli a0, a0, 3
+; SPILL-O0-NEXT: add sp, sp, a0
+; SPILL-O0-NEXT: ret
+;
+; SPILL-O2-LABEL: spill_lmul_8:
+; SPILL-O2: # %bb.0: # %entry
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 3
+; SPILL-O2-NEXT: sub sp, sp, a0
+; SPILL-O2-NEXT: vs8r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: #APP
+; SPILL-O2-NEXT: #NO_APP
+; SPILL-O2-NEXT: vl8re8.v v8, (sp) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 3
+; SPILL-O2-NEXT: add sp, sp, a0
+; SPILL-O2-NEXT: ret
+entry:
+ call void asm sideeffect "",
+ "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
+
+ ret <vscale x 8 x i64> %va
+}
diff --git a/llvm/test/CodeGen/RISCV/spill-fpr-scalar.ll b/llvm/test/CodeGen/RISCV/spill-fpr-scalar.ll
new file mode 100644
index 0000000..bcfcec5
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/spill-fpr-scalar.ll
@@ -0,0 +1,75 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v,+d,+experimental-zfh \
+; RUN: -verify-machineinstrs --riscv-no-aliases < %s \
+; RUN: | FileCheck %s
+
+declare half @llvm.riscv.vfmv.f.s.nxv1f16(<vscale x 1 x half>)
+declare float @llvm.riscv.vfmv.f.s.nxv1f32(<vscale x 1 x float>)
+declare double @llvm.riscv.vfmv.f.s.nxv1f64(<vscale x 1 x double>)
+
+declare <vscale x 1 x half> @llvm.riscv.vfmv.v.f.nxv1f16(half, i64);
+declare <vscale x 1 x float> @llvm.riscv.vfmv.v.f.nxv1f32(float, i64);
+declare <vscale x 1 x double> @llvm.riscv.vfmv.v.f.nxv1f64(double, i64);
+
+define <vscale x 1 x half> @intrinsic_vfmv.f.s_s_nxv1f16(<vscale x 1 x half> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vfmv.f.s_s_nxv1f16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: vsetvli zero, zero, e16,mf4,ta,mu
+; CHECK-NEXT: vfmv.f.s ft0, v8
+; CHECK-NEXT: fsh ft0, 14(sp) # 2-byte Folded Spill
+; CHECK-NEXT: #APP
+; CHECK-NEXT: #NO_APP
+; CHECK-NEXT: vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT: flh ft0, 14(sp) # 2-byte Folded Reload
+; CHECK-NEXT: vfmv.v.f v8, ft0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: jalr zero, 0(ra)
+entry:
+ %a = call half @llvm.riscv.vfmv.f.s.nxv1f16(<vscale x 1 x half> %0)
+ tail call void asm sideeffect "", "~{f0_d},~{f1_d},~{f2_d},~{f3_d},~{f4_d},~{f5_d},~{f6_d},~{f7_d},~{f8_d},~{f9_d},~{f10_d},~{f11_d},~{f12_d},~{f13_d},~{f14_d},~{f15_d},~{f16_d},~{f17_d},~{f18_d},~{f19_d},~{f20_d},~{f21_d},~{f22_d},~{f23_d},~{f24_d},~{f25_d},~{f26_d},~{f27_d},~{f28_d},~{f29_d},~{f30_d},~{f31_d}"()
+ %b = call <vscale x 1 x half> @llvm.riscv.vfmv.v.f.nxv1f16(half %a, i64 %1)
+ ret <vscale x 1 x half> %b
+}
+
+define <vscale x 1 x float> @intrinsic_vfmv.f.s_s_nxv1f32(<vscale x 1 x float> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vfmv.f.s_s_nxv1f32:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: vsetvli zero, zero, e32,mf2,ta,mu
+; CHECK-NEXT: vfmv.f.s ft0, v8
+; CHECK-NEXT: fsw ft0, 12(sp) # 4-byte Folded Spill
+; CHECK-NEXT: #APP
+; CHECK-NEXT: #NO_APP
+; CHECK-NEXT: vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT: flw ft0, 12(sp) # 4-byte Folded Reload
+; CHECK-NEXT: vfmv.v.f v8, ft0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: jalr zero, 0(ra)
+entry:
+ %a = call float @llvm.riscv.vfmv.f.s.nxv1f32(<vscale x 1 x float> %0)
+ tail call void asm sideeffect "", "~{f0_d},~{f1_d},~{f2_d},~{f3_d},~{f4_d},~{f5_d},~{f6_d},~{f7_d},~{f8_d},~{f9_d},~{f10_d},~{f11_d},~{f12_d},~{f13_d},~{f14_d},~{f15_d},~{f16_d},~{f17_d},~{f18_d},~{f19_d},~{f20_d},~{f21_d},~{f22_d},~{f23_d},~{f24_d},~{f25_d},~{f26_d},~{f27_d},~{f28_d},~{f29_d},~{f30_d},~{f31_d}"()
+ %b = call <vscale x 1 x float> @llvm.riscv.vfmv.v.f.nxv1f32(float %a, i64 %1)
+ ret <vscale x 1 x float> %b
+}
+
+define <vscale x 1 x double> @intrinsic_vfmv.f.s_s_nxv1f64(<vscale x 1 x double> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vfmv.f.s_s_nxv1f64:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: vsetvli zero, zero, e64,m1,ta,mu
+; CHECK-NEXT: vfmv.f.s ft0, v8
+; CHECK-NEXT: fsd ft0, 8(sp) # 8-byte Folded Spill
+; CHECK-NEXT: #APP
+; CHECK-NEXT: #NO_APP
+; CHECK-NEXT: vsetvli a0, a0, e64,m1,ta,mu
+; CHECK-NEXT: fld ft0, 8(sp) # 8-byte Folded Reload
+; CHECK-NEXT: vfmv.v.f v8, ft0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: jalr zero, 0(ra)
+entry:
+ %a = call double @llvm.riscv.vfmv.f.s.nxv1f64(<vscale x 1 x double> %0)
+ tail call void asm sideeffect "", "~{f0_d},~{f1_d},~{f2_d},~{f3_d},~{f4_d},~{f5_d},~{f6_d},~{f7_d},~{f8_d},~{f9_d},~{f10_d},~{f11_d},~{f12_d},~{f13_d},~{f14_d},~{f15_d},~{f16_d},~{f17_d},~{f18_d},~{f19_d},~{f20_d},~{f21_d},~{f22_d},~{f23_d},~{f24_d},~{f25_d},~{f26_d},~{f27_d},~{f28_d},~{f29_d},~{f30_d},~{f31_d}"()
+ %b = call <vscale x 1 x double> @llvm.riscv.vfmv.v.f.nxv1f64(double %a, i64 %1)
+ ret <vscale x 1 x double> %b
+}
