diff options
author | Brandon Wu <brandon.wu@sifive.com> | 2024-03-27 23:03:13 +0800 |
---|---|---|
committer | GitHub <noreply@github.com> | 2024-03-27 23:03:13 +0800 |
commit | 91896607ffb84561a7a2e466a00fdf1938c5bb63 (patch) | |
tree | cfea81458e2249e96e367b4c1ddbf9015de30165 /llvm/test/CodeGen/RISCV | |
parent | 6d3ec56d3ce1478ac42a400a80532b8f732477fe (diff) | |
download | llvm-91896607ffb84561a7a2e466a00fdf1938c5bb63.zip llvm-91896607ffb84561a7a2e466a00fdf1938c5bb63.tar.gz llvm-91896607ffb84561a7a2e466a00fdf1938c5bb63.tar.bz2 |
[RISCV] RISCV vector calling convention (1/2) (#77560)
[RISCV] RISCV vector calling convention (1/2)
This is the vector calling convention based on
https://github.com/riscv-non-isa/riscv-elf-psabi-doc,
the idea is to split between "scalar" callee-saved registers
and "vector" callee-saved registers. "scalar" ones remain the
original strategy, however, "vector" ones are handled together
with RVV objects.
The stack layout would be:
|--------------------------| <-- FP
| callee-allocated save |
| area for register varargs|
|--------------------------|
| callee-saved registers | <-- scalar callee-saved
| (scalar) |
|--------------------------|
| RVV alignment padding |
|--------------------------|
| callee-saved registers | <-- vector callee-saved
| (vector) |
|--------------------------|
| RVV objects |
|--------------------------|
| padding before RVV |
|--------------------------|
| scalar local variables |
|--------------------------| <-- BP
| variable size objects |
|--------------------------| <-- SP
Note: This patch doesn't contain "tuple" type, e.g. vint32m1x2.
It will be handled in https://github.com/riscv-non-isa/riscv-elf-psabi-doc (2/2).
Differential Revision: https://reviews.llvm.org/D154576
Diffstat (limited to 'llvm/test/CodeGen/RISCV')
-rw-r--r-- | llvm/test/CodeGen/RISCV/rvv/callee-saved-regs.ll | 95 |
1 files changed, 95 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/RISCV/rvv/callee-saved-regs.ll b/llvm/test/CodeGen/RISCV/rvv/callee-saved-regs.ll new file mode 100644 index 0000000..84936d8 --- /dev/null +++ b/llvm/test/CodeGen/RISCV/rvv/callee-saved-regs.ll @@ -0,0 +1,95 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc -mtriple=riscv32 -mattr=+m -mattr=+v -O2 < %s \ +; RUN: | FileCheck --check-prefix=SPILL-O2 %s + +define <vscale x 1 x i32> @test_vector_std(<vscale x 1 x i32> %va) nounwind { +; SPILL-O2-LABEL: test_vector_std: +; SPILL-O2: # %bb.0: # %entry +; SPILL-O2-NEXT: addi sp, sp, -16 +; SPILL-O2-NEXT: csrr a0, vlenb +; SPILL-O2-NEXT: slli a0, a0, 1 +; SPILL-O2-NEXT: sub sp, sp, a0 +; SPILL-O2-NEXT: addi a0, sp, 16 +; SPILL-O2-NEXT: vs1r.v v8, (a0) # Unknown-size Folded Spill +; SPILL-O2-NEXT: #APP +; SPILL-O2-NEXT: #NO_APP +; SPILL-O2-NEXT: vl1r.v v8, (a0) # 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: addi sp, sp, 16 +; 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 riscv_vector_cc <vscale x 1 x i32> @test_vector_callee(<vscale x 1 x i32> %va) nounwind { +; SPILL-O2-LABEL: test_vector_callee: +; SPILL-O2: # %bb.0: # %entry +; SPILL-O2-NEXT: addi sp, sp, -16 +; SPILL-O2-NEXT: csrr a0, vlenb +; SPILL-O2-NEXT: slli a0, a0, 4 +; SPILL-O2-NEXT: sub sp, sp, a0 +; SPILL-O2-NEXT: csrr a0, vlenb +; SPILL-O2-NEXT: slli a1, a0, 4 +; SPILL-O2-NEXT: sub a0, a1, a0 +; SPILL-O2-NEXT: add a0, sp, a0 +; SPILL-O2-NEXT: addi a0, a0, 16 +; SPILL-O2-NEXT: vs1r.v v1, (a0) # Unknown-size Folded Spill +; SPILL-O2-NEXT: csrr a0, vlenb +; SPILL-O2-NEXT: li a1, 13 +; SPILL-O2-NEXT: mul a0, a0, a1 +; SPILL-O2-NEXT: add a0, sp, a0 +; SPILL-O2-NEXT: addi a0, a0, 16 +; SPILL-O2-NEXT: vs2r.v v2, (a0) # Unknown-size Folded Spill +; SPILL-O2-NEXT: csrr a0, vlenb +; SPILL-O2-NEXT: slli a1, a0, 3 +; SPILL-O2-NEXT: add a0, a1, a0 +; SPILL-O2-NEXT: add a0, sp, a0 +; SPILL-O2-NEXT: addi a0, a0, 16 +; SPILL-O2-NEXT: vs4r.v v4, (a0) # Unknown-size Folded Spill +; SPILL-O2-NEXT: csrr a0, vlenb +; SPILL-O2-NEXT: add a0, sp, a0 +; SPILL-O2-NEXT: addi a0, a0, 16 +; SPILL-O2-NEXT: vs8r.v v24, (a0) # Unknown-size Folded Spill +; SPILL-O2-NEXT: addi a0, sp, 16 +; SPILL-O2-NEXT: vs1r.v v8, (a0) # Unknown-size Folded Spill +; SPILL-O2-NEXT: #APP +; SPILL-O2-NEXT: #NO_APP +; SPILL-O2-NEXT: vl1r.v v8, (a0) # Unknown-size Folded Reload +; SPILL-O2-NEXT: csrr a0, vlenb +; SPILL-O2-NEXT: slli a1, a0, 4 +; SPILL-O2-NEXT: sub a0, a1, a0 +; SPILL-O2-NEXT: add a0, sp, a0 +; SPILL-O2-NEXT: addi a0, a0, 16 +; SPILL-O2-NEXT: vl1r.v v1, (a0) # Unknown-size Folded Reload +; SPILL-O2-NEXT: csrr a0, vlenb +; SPILL-O2-NEXT: li a1, 13 +; SPILL-O2-NEXT: mul a0, a0, a1 +; SPILL-O2-NEXT: add a0, sp, a0 +; SPILL-O2-NEXT: addi a0, a0, 16 +; SPILL-O2-NEXT: vl2r.v v2, (a0) # Unknown-size Folded Reload +; SPILL-O2-NEXT: csrr a0, vlenb +; SPILL-O2-NEXT: slli a1, a0, 3 +; SPILL-O2-NEXT: add a0, a1, a0 +; SPILL-O2-NEXT: add a0, sp, a0 +; SPILL-O2-NEXT: addi a0, a0, 16 +; SPILL-O2-NEXT: vl4r.v v4, (a0) # Unknown-size Folded Reload +; SPILL-O2-NEXT: csrr a0, vlenb +; SPILL-O2-NEXT: add a0, sp, a0 +; SPILL-O2-NEXT: addi a0, a0, 16 +; SPILL-O2-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload +; SPILL-O2-NEXT: csrr a0, vlenb +; SPILL-O2-NEXT: slli a0, a0, 4 +; SPILL-O2-NEXT: add sp, sp, a0 +; SPILL-O2-NEXT: addi sp, sp, 16 +; 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 +} |