4vtomat created this revision.
Herald added subscribers: jobnoorman, luke, VincentWu, ormris, vkmr,
frasercrmck, luismarques, apazos, sameer.abuasal, s.egerton, Jim, benna,
psnobl, jocewei, PkmX, the_o, brucehoult, MartinMosbeck, rogfer01, steven_wu,
edward-jones, zzheng, jrtc27, shiva0217, kito-cheng, niosHD, sabuasal,
simoncook, johnrusso, rbar, asb, hiraditya, arichardson.
Herald added a reviewer: aaron.ballman.
Herald added a project: All.
4vtomat requested review of this revision.
Herald added subscribers: llvm-commits, cfe-commits, wangpc, eopXD, MaskRay.
Herald added projects: clang, LLVM.
This is the vector calling convention based on
https://github.com/riscv-non-isa/riscv-elf-psabi-doc/pull/389,
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 future patch once the PR389 is ready.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D154576
Files:
clang/include/clang/Basic/Attr.td
clang/include/clang/Basic/AttrDocs.td
clang/include/clang/Basic/Specifiers.h
clang/lib/AST/ItaniumMangle.cpp
clang/lib/AST/Type.cpp
clang/lib/AST/TypePrinter.cpp
clang/lib/Basic/Targets/RISCV.cpp
clang/lib/Basic/Targets/RISCV.h
clang/lib/CodeGen/CGCall.cpp
clang/lib/Sema/SemaDeclAttr.cpp
clang/lib/Sema/SemaType.cpp
clang/test/CodeGen/RISCV/riscv-vector-cc-attr.c
llvm/include/llvm/AsmParser/LLToken.h
llvm/include/llvm/IR/CallingConv.h
llvm/lib/AsmParser/LLLexer.cpp
llvm/lib/AsmParser/LLParser.cpp
llvm/lib/IR/AsmWriter.cpp
llvm/lib/Target/RISCV/RISCVCallingConv.td
llvm/lib/Target/RISCV/RISCVFrameLowering.cpp
llvm/lib/Target/RISCV/RISCVISelLowering.cpp
llvm/lib/Target/RISCV/RISCVRegisterInfo.cpp
llvm/test/CodeGen/RISCV/rvv/callee-saved-regs.ll
Index: llvm/test/CodeGen/RISCV/rvv/callee-saved-regs.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/RISCV/rvv/callee-saved-regs.ll
@@ -0,0 +1,222 @@
+; 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: li a1, 14
+; SPILL-O2-NEXT: mul a0, a0, a1
+; 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: vs1r.v v2, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: li a1, 12
+; SPILL-O2-NEXT: mul a0, a0, a1
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vs1r.v v3, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: li a1, 11
+; SPILL-O2-NEXT: mul a0, a0, a1
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vs1r.v v4, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: li a1, 10
+; SPILL-O2-NEXT: mul a0, a0, a1
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vs1r.v v5, (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: vs1r.v v6, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 3
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vs1r.v v7, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a1, a0, 3
+; 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 v24, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: li a1, 6
+; SPILL-O2-NEXT: mul a0, a0, a1
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vs1r.v v25, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a1, a0, 2
+; SPILL-O2-NEXT: add a0, a1, a0
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vs1r.v v26, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 2
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vs1r.v v27, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a1, a0, 1
+; SPILL-O2-NEXT: add a0, a1, a0
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vs1r.v v28, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 1
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vs1r.v v29, (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: vs1r.v v30, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: addi a0, sp, 16
+; SPILL-O2-NEXT: vs1r.v v31, (a0) # Unknown-size Folded Spill
+; 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 v8, (a0) # Unknown-size Folded Spill
+; SPILL-O2-NEXT: #APP
+; SPILL-O2-NEXT: #NO_APP
+; 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 v8, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: li a1, 14
+; SPILL-O2-NEXT: mul a0, a0, a1
+; 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: vl1r.v v2, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: li a1, 12
+; SPILL-O2-NEXT: mul a0, a0, a1
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vl1r.v v3, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: li a1, 11
+; SPILL-O2-NEXT: mul a0, a0, a1
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vl1r.v v4, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: li a1, 10
+; SPILL-O2-NEXT: mul a0, a0, a1
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vl1r.v v5, (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: vl1r.v v6, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 3
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vl1r.v v7, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a1, a0, 3
+; 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 v24, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: li a1, 6
+; SPILL-O2-NEXT: mul a0, a0, a1
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vl1r.v v25, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a1, a0, 2
+; SPILL-O2-NEXT: add a0, a1, a0
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vl1r.v v26, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 2
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vl1r.v v27, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a1, a0, 1
+; SPILL-O2-NEXT: add a0, a1, a0
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vl1r.v v28, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: csrr a0, vlenb
+; SPILL-O2-NEXT: slli a0, a0, 1
+; SPILL-O2-NEXT: add a0, sp, a0
+; SPILL-O2-NEXT: addi a0, a0, 16
+; SPILL-O2-NEXT: vl1r.v v29, (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: vl1r.v v30, (a0) # Unknown-size Folded Reload
+; SPILL-O2-NEXT: addi a0, sp, 16
+; SPILL-O2-NEXT: vl1r.v v31, (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
+}
Index: llvm/lib/Target/RISCV/RISCVRegisterInfo.cpp
===================================================================
--- llvm/lib/Target/RISCV/RISCVRegisterInfo.cpp
+++ llvm/lib/Target/RISCV/RISCVRegisterInfo.cpp
@@ -66,17 +66,26 @@
return CSR_Interrupt_SaveList;
}
+ bool HasVectorCSR = MF->getFunction().getCallingConv() ==
+ CallingConv::RISCV_VectorCall;
+
switch (Subtarget.getTargetABI()) {
default:
llvm_unreachable("Unrecognized ABI");
case RISCVABI::ABI_ILP32:
case RISCVABI::ABI_LP64:
+ if (HasVectorCSR)
+ return CSR_ILP32_LP64_V_SaveList;
return CSR_ILP32_LP64_SaveList;
case RISCVABI::ABI_ILP32F:
case RISCVABI::ABI_LP64F:
+ if (HasVectorCSR)
+ return CSR_ILP32F_LP64F_V_SaveList;
return CSR_ILP32F_LP64F_SaveList;
case RISCVABI::ABI_ILP32D:
case RISCVABI::ABI_LP64D:
+ if (HasVectorCSR)
+ return CSR_ILP32D_LP64D_V_SaveList;
return CSR_ILP32D_LP64D_SaveList;
}
}
@@ -636,12 +645,18 @@
llvm_unreachable("Unrecognized ABI");
case RISCVABI::ABI_ILP32:
case RISCVABI::ABI_LP64:
+ if (CC == CallingConv::RISCV_VectorCall)
+ return CSR_ILP32_LP64_V_RegMask;
return CSR_ILP32_LP64_RegMask;
case RISCVABI::ABI_ILP32F:
case RISCVABI::ABI_LP64F:
+ if (CC == CallingConv::RISCV_VectorCall)
+ return CSR_ILP32F_LP64F_V_RegMask;
return CSR_ILP32F_LP64F_RegMask;
case RISCVABI::ABI_ILP32D:
case RISCVABI::ABI_LP64D:
+ if (CC == CallingConv::RISCV_VectorCall)
+ return CSR_ILP32D_LP64D_V_RegMask;
return CSR_ILP32D_LP64D_RegMask;
}
}
Index: llvm/lib/Target/RISCV/RISCVISelLowering.cpp
===================================================================
--- llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -14890,6 +14890,7 @@
report_fatal_error("Unsupported calling convention");
case CallingConv::C:
case CallingConv::Fast:
+ case CallingConv::RISCV_VectorCall:
break;
case CallingConv::GHC:
if (!Subtarget.hasStdExtF() || !Subtarget.hasStdExtD())
Index: llvm/lib/Target/RISCV/RISCVFrameLowering.cpp
===================================================================
--- llvm/lib/Target/RISCV/RISCVFrameLowering.cpp
+++ llvm/lib/Target/RISCV/RISCVFrameLowering.cpp
@@ -302,7 +302,8 @@
for (auto &CS : CSI) {
int FI = CS.getFrameIdx();
- if (FI >= 0 && MFI.getStackID(FI) == TargetStackID::Default)
+ if (FI >= 0 && (MFI.getStackID(FI) == TargetStackID::Default ||
+ MFI.getStackID(FI) == TargetStackID::ScalableVector))
NonLibcallCSI.push_back(CS);
}
@@ -479,7 +480,13 @@
.addCFIIndex(CFIIndex)
.setMIFlag(MachineInstr::FrameSetup);
- const auto &CSI = MFI.getCalleeSavedInfo();
+ const auto &CSI = getNonLibcallCSI(MF, MFI.getCalleeSavedInfo());
+ size_t VectorCSISize = 0;
+ for (auto &CS : CSI) {
+ int FI = CS.getFrameIdx();
+ if (FI >= 0 && MFI.getStackID(FI) == TargetStackID::ScalableVector)
+ VectorCSISize++;
+ }
// The frame pointer is callee-saved, and code has been generated for us to
// save it to the stack. We need to skip over the storing of callee-saved
@@ -487,7 +494,7 @@
// to the stack, not before.
// FIXME: assumes exactly one instruction is used to save each callee-saved
// register.
- std::advance(MBBI, getNonLibcallCSI(MF, CSI).size());
+ std::advance(MBBI, CSI.size() - VectorCSISize);
// Iterate over list of callee-saved registers and emit .cfi_offset
// directives.
@@ -640,8 +647,12 @@
// FIXME: assumes exactly one instruction is used to restore each
// callee-saved register.
auto LastFrameDestroy = MBBI;
- if (!CSI.empty())
- LastFrameDestroy = std::prev(MBBI, CSI.size());
+ for (const auto &CS : CSI) {
+ int FI = CS.getFrameIdx();
+ if (FI < 0 || MFI.getStackID(FI) != TargetStackID::Default)
+ break;
+ LastFrameDestroy = std::prev(LastFrameDestroy);
+ }
uint64_t StackSize = getStackSizeWithRVVPadding(MF);
uint64_t RealStackSize = StackSize + RVFI->getLibCallStackSize();
@@ -727,7 +738,8 @@
MaxCSFI = CSI[CSI.size() - 1].getFrameIdx();
}
- if (FI >= MinCSFI && FI <= MaxCSFI) {
+ if (FI >= MinCSFI && FI <= MaxCSFI &&
+ StackID != TargetStackID::ScalableVector) {
FrameReg = RISCV::X2;
if (FirstSPAdjustAmount)
@@ -1261,20 +1273,53 @@
DL = MI->getDebugLoc();
// Manually restore values not restored by libcall.
- // Keep the same order as in the prologue. There is no need to reverse the
- // order in the epilogue. In addition, the return address will be restored
- // first in the epilogue. It increases the opportunity to avoid the
+ //
+ // We first change the restore order for scalar and vector
+ // callee-saved registers as the layout shown below:
+ //
+ // Epilog restore order (original):
+ // ----------------------------
+ // RVV objects
+ // ----------------------------
+ // Callee-saved regs(scalar)
+ // Callee-saved regs(vector)
+ // ----------------------------
+ //
+ // Epilog restore order (after):
+ // ----------------------------
+ // RVV objects
+ // ----------------------------
+ // Callee-saved regs(vector)
+ // Callee-saved regs(scalar)
+ // ----------------------------
+ //
+ // So that it is able to put all vector registers which need
+ // to be restored together. The return address will be restored
+ // first in the scalar regs. It increases the opportunity to avoid the
// load-to-use data hazard between loading RA and return by RA.
// loadRegFromStackSlot can insert multiple instructions.
const auto &NonLibcallCSI = getNonLibcallCSI(*MF, CSI);
- for (auto &CS : NonLibcallCSI) {
- Register Reg = CS.getReg();
- const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
- TII.loadRegFromStackSlot(MBB, MI, Reg, CS.getFrameIdx(), RC, TRI,
- Register());
- assert(MI != MBB.begin() && "loadRegFromStackSlot didn't insert any code!");
+ const MachineFrameInfo &MFI = MF->getFrameInfo();
+ auto *It = NonLibcallCSI.begin();
+ while (It != NonLibcallCSI.end()) {
+ int FI = It->getFrameIdx();
+ if (MFI.getStackID(FI) == TargetStackID::ScalableVector)
+ break;
+ It++;
}
+ auto loadRegFromStackSlot = [&](decltype(It) CSBeg, decltype(It) CSEnd) {
+ for (auto CS = CSBeg; CS != CSEnd; CS++) {
+ Register Reg = CS->getReg();
+ const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
+ TII.loadRegFromStackSlot(MBB, MI, Reg, CS->getFrameIdx(), RC, TRI,
+ Register());
+ assert(MI != MBB.begin() && "loadRegFromStackSlot didn't insert any code!");
+ }
+ };
+ loadRegFromStackSlot(It, NonLibcallCSI.end());
+ loadRegFromStackSlot(NonLibcallCSI.begin(), It);
+
const char *RestoreLibCall = getRestoreLibCallName(*MF, CSI);
if (RestoreLibCall) {
// Add restore libcall via tail call.
Index: llvm/lib/Target/RISCV/RISCVCallingConv.td
===================================================================
--- llvm/lib/Target/RISCV/RISCVCallingConv.td
+++ llvm/lib/Target/RISCV/RISCVCallingConv.td
@@ -24,6 +24,17 @@
: CalleeSavedRegs<(add CSR_ILP32_LP64,
F8_D, F9_D, (sequence "F%u_D", 18, 27))>;
+defvar CSR_V = (add (sequence "V%u", 1, 7), (sequence "V%u", 24, 31));
+
+def CSR_ILP32_LP64_V
+ : CalleeSavedRegs<(add CSR_ILP32_LP64, CSR_V)>;
+
+def CSR_ILP32F_LP64F_V
+ : CalleeSavedRegs<(add CSR_ILP32F_LP64F, CSR_V)>;
+
+def CSR_ILP32D_LP64D_V
+ : CalleeSavedRegs<(add CSR_ILP32D_LP64D, CSR_V)>;
+
// Needed for implementation of RISCVRegisterInfo::getNoPreservedMask()
def CSR_NoRegs : CalleeSavedRegs<(add)>;
Index: llvm/lib/IR/AsmWriter.cpp
===================================================================
--- llvm/lib/IR/AsmWriter.cpp
+++ llvm/lib/IR/AsmWriter.cpp
@@ -350,6 +350,7 @@
break;
case CallingConv::AMDGPU_KERNEL: Out << "amdgpu_kernel"; break;
case CallingConv::AMDGPU_Gfx: Out << "amdgpu_gfx"; break;
+ case CallingConv::RISCV_VectorCall: Out << "riscv_vector_cc"; break;
}
}
Index: llvm/lib/AsmParser/LLParser.cpp
===================================================================
--- llvm/lib/AsmParser/LLParser.cpp
+++ llvm/lib/AsmParser/LLParser.cpp
@@ -2031,6 +2031,7 @@
/// ::= 'amdgpu_cs_chain_preserve'
/// ::= 'amdgpu_kernel'
/// ::= 'tailcc'
+/// ::= 'riscv_vector_cc'
/// ::= 'cc' UINT
///
bool LLParser::parseOptionalCallingConv(unsigned &CC) {
@@ -2099,6 +2100,7 @@
break;
case lltok::kw_amdgpu_kernel: CC = CallingConv::AMDGPU_KERNEL; break;
case lltok::kw_tailcc: CC = CallingConv::Tail; break;
+ case lltok::kw_riscv_vector_cc:CC = CallingConv::RISCV_VectorCall; break;
case lltok::kw_cc: {
Lex.Lex();
return parseUInt32(CC);
Index: llvm/lib/AsmParser/LLLexer.cpp
===================================================================
--- llvm/lib/AsmParser/LLLexer.cpp
+++ llvm/lib/AsmParser/LLLexer.cpp
@@ -632,6 +632,7 @@
KEYWORD(amdgpu_kernel);
KEYWORD(amdgpu_gfx);
KEYWORD(tailcc);
+ KEYWORD(riscv_vector_cc);
KEYWORD(cc);
KEYWORD(c);
Index: llvm/include/llvm/IR/CallingConv.h
===================================================================
--- llvm/include/llvm/IR/CallingConv.h
+++ llvm/include/llvm/IR/CallingConv.h
@@ -245,6 +245,9 @@
/// placement. Preserves active lane values for input VGPRs.
AMDGPU_CS_ChainPreserve = 105,
+ /// Calling convention used for RISC-V V-extension.
+ RISCV_VectorCall = 106,
+
/// The highest possible ID. Must be some 2^k - 1.
MaxID = 1023
};
Index: llvm/include/llvm/AsmParser/LLToken.h
===================================================================
--- llvm/include/llvm/AsmParser/LLToken.h
+++ llvm/include/llvm/AsmParser/LLToken.h
@@ -175,6 +175,7 @@
kw_amdgpu_kernel,
kw_amdgpu_gfx,
kw_tailcc,
+ kw_riscv_vector_cc,
// Attributes:
kw_attributes,
Index: clang/test/CodeGen/RISCV/riscv-vector-cc-attr.c
===================================================================
--- /dev/null
+++ clang/test/CodeGen/RISCV/riscv-vector-cc-attr.c
@@ -0,0 +1,30 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
+// REQUIRES: riscv-registered-target
+// RUN: %clang_cc1 -triple riscv64 -target-feature +v \
+// RUN: -emit-llvm %s -o - | FileCheck %s
+
+#include <riscv_vector.h>
+
+vint32m1_t __attribute__((riscv_vector_cc)) bar(vint32m1_t input);
+
+// CHECK: call riscv_vector_cc <vscale x 2 x i32> @bar
+vint32m1_t test_vector_cc_attr(vint32m1_t input, int32_t *base, size_t vl) {
+ vint32m1_t ret;
+ vint32m1_t val;
+ val = vle32_v_i32m1(base, vl);
+ ret = bar(input);
+ vse32_v_i32m1(base, val, vl);
+ return ret;
+}
+
+vint32m1_t baz(vint32m1_t input);
+
+// CHECK: call <vscale x 2 x i32> @baz
+vint32m1_t test_no_vector_cc_attr(vint32m1_t input, int32_t *base, size_t vl) {
+ vint32m1_t ret;
+ vint32m1_t val;
+ val = vle32_v_i32m1(base, vl);
+ ret = baz(input);
+ vse32_v_i32m1(base, val, vl);
+ return ret;
+}
Index: clang/lib/Sema/SemaType.cpp
===================================================================
--- clang/lib/Sema/SemaType.cpp
+++ clang/lib/Sema/SemaType.cpp
@@ -135,7 +135,8 @@
case ParsedAttr::AT_Pcs: \
case ParsedAttr::AT_IntelOclBicc: \
case ParsedAttr::AT_PreserveMost: \
- case ParsedAttr::AT_PreserveAll
+ case ParsedAttr::AT_PreserveAll: \
+ case ParsedAttr::AT_RISCVVectorCC
// Function type attributes.
#define FUNCTION_TYPE_ATTRS_CASELIST \
@@ -7768,6 +7769,8 @@
return createSimpleAttr<PreserveMostAttr>(Ctx, Attr);
case ParsedAttr::AT_PreserveAll:
return createSimpleAttr<PreserveAllAttr>(Ctx, Attr);
+ case ParsedAttr::AT_RISCVVectorCC:
+ return createSimpleAttr<RISCVVectorCCAttr>(Ctx, Attr);
}
llvm_unreachable("unexpected attribute kind!");
}
Index: clang/lib/Sema/SemaDeclAttr.cpp
===================================================================
--- clang/lib/Sema/SemaDeclAttr.cpp
+++ clang/lib/Sema/SemaDeclAttr.cpp
@@ -5194,6 +5194,9 @@
case ParsedAttr::AT_PreserveAll:
D->addAttr(::new (S.Context) PreserveAllAttr(S.Context, AL));
return;
+ case ParsedAttr::AT_RISCVVectorCC:
+ D->addAttr(::new (S.Context) RISCVVectorCCAttr(S.Context, AL));
+ return;
default:
llvm_unreachable("unexpected attribute kind");
}
@@ -5393,6 +5396,9 @@
case ParsedAttr::AT_PreserveAll:
CC = CC_PreserveAll;
break;
+ case ParsedAttr::AT_RISCVVectorCC:
+ CC = CC_RISCVVectorCall;
+ break;
default: llvm_unreachable("unexpected attribute kind");
}
@@ -9229,6 +9235,7 @@
case ParsedAttr::AT_AArch64VectorPcs:
case ParsedAttr::AT_AArch64SVEPcs:
case ParsedAttr::AT_AMDGPUKernelCall:
+ case ParsedAttr::AT_RISCVVectorCC:
handleCallConvAttr(S, D, AL);
break;
case ParsedAttr::AT_Suppress:
Index: clang/lib/CodeGen/CGCall.cpp
===================================================================
--- clang/lib/CodeGen/CGCall.cpp
+++ clang/lib/CodeGen/CGCall.cpp
@@ -71,6 +71,7 @@
case CC_PreserveAll: return llvm::CallingConv::PreserveAll;
case CC_Swift: return llvm::CallingConv::Swift;
case CC_SwiftAsync: return llvm::CallingConv::SwiftTail;
+ case CC_RISCVVectorCall: return llvm::CallingConv::RISCV_VectorCall;
}
}
@@ -252,6 +253,9 @@
if (D->hasAttr<PreserveAllAttr>())
return CC_PreserveAll;
+ if (D->hasAttr<RISCVVectorCCAttr>())
+ return CC_RISCVVectorCall;
+
return CC_C;
}
Index: clang/lib/Basic/Targets/RISCV.h
===================================================================
--- clang/lib/Basic/Targets/RISCV.h
+++ clang/lib/Basic/Targets/RISCV.h
@@ -101,6 +101,8 @@
bool hasBitIntType() const override { return true; }
+ CallingConvCheckResult checkCallingConvention(CallingConv CC) const override;
+
bool useFP16ConversionIntrinsics() const override {
return false;
}
Index: clang/lib/Basic/Targets/RISCV.cpp
===================================================================
--- clang/lib/Basic/Targets/RISCV.cpp
+++ clang/lib/Basic/Targets/RISCV.cpp
@@ -346,3 +346,14 @@
bool Is64Bit = getTriple().isArch64Bit();
llvm::RISCV::fillValidTuneCPUArchList(Values, Is64Bit);
}
+
+TargetInfo::CallingConvCheckResult
+RISCVTargetInfo::checkCallingConvention(CallingConv CC) const {
+ switch (CC) {
+ default:
+ return CCCR_Warning;
+ case CC_C:
+ case CC_RISCVVectorCall:
+ return CCCR_OK;
+ }
+}
Index: clang/lib/AST/TypePrinter.cpp
===================================================================
--- clang/lib/AST/TypePrinter.cpp
+++ clang/lib/AST/TypePrinter.cpp
@@ -1035,6 +1035,9 @@
case CC_PreserveAll:
OS << " __attribute__((preserve_all))";
break;
+ case CC_RISCVVectorCall:
+ OS << "__attribute__((riscv_vector_cc))";
+ break;
}
}
@@ -1855,6 +1858,9 @@
case attr::PreserveAll:
OS << "preserve_all";
break;
+ case attr::RISCVVectorCC:
+ OS << "riscv_vector_cc";
+ break;
case attr::NoDeref:
OS << "noderef";
break;
Index: clang/lib/AST/Type.cpp
===================================================================
--- clang/lib/AST/Type.cpp
+++ clang/lib/AST/Type.cpp
@@ -3350,6 +3350,7 @@
case CC_SwiftAsync: return "swiftasynccall";
case CC_PreserveMost: return "preserve_most";
case CC_PreserveAll: return "preserve_all";
+ case CC_RISCVVectorCall: return "riscv_vector_cc";
}
llvm_unreachable("Invalid calling convention.");
@@ -3818,6 +3819,7 @@
case attr::IntelOclBicc:
case attr::PreserveMost:
case attr::PreserveAll:
+ case attr::RISCVVectorCC:
return true;
}
llvm_unreachable("invalid attr kind");
Index: clang/lib/AST/ItaniumMangle.cpp
===================================================================
--- clang/lib/AST/ItaniumMangle.cpp
+++ clang/lib/AST/ItaniumMangle.cpp
@@ -3264,6 +3264,7 @@
case CC_OpenCLKernel:
case CC_PreserveMost:
case CC_PreserveAll:
+ case CC_RISCVVectorCall:
// FIXME: we should be mangling all of the above.
return "";
Index: clang/include/clang/Basic/Specifiers.h
===================================================================
--- clang/include/clang/Basic/Specifiers.h
+++ clang/include/clang/Basic/Specifiers.h
@@ -288,6 +288,7 @@
CC_AArch64VectorCall, // __attribute__((aarch64_vector_pcs))
CC_AArch64SVEPCS, // __attribute__((aarch64_sve_pcs))
CC_AMDGPUKernelCall, // __attribute__((amdgpu_kernel))
+ CC_RISCVVectorCall, // __attribute__((riscv_vector_cc))
};
/// Checks whether the given calling convention supports variadic
Index: clang/include/clang/Basic/AttrDocs.td
===================================================================
--- clang/include/clang/Basic/AttrDocs.td
+++ clang/include/clang/Basic/AttrDocs.td
@@ -5193,6 +5193,16 @@
}];
}
+def RISCVVectorCCDocs : Documentation {
+ let Category = DocCatCallingConvs;
+ let Content = [{
+The ``riscv_vector_cc`` attribute can be applied to a function. It preserves 15
+registers namely, v1-v7 and v24-v31 as callee-saved. Callers thus don't need
+to save these registers before function calls, and callees only need to save
+them only if they use them.
+ }];
+}
+
def PreferredNameDocs : Documentation {
let Category = DocCatDecl;
let Content = [{
Index: clang/include/clang/Basic/Attr.td
===================================================================
--- clang/include/clang/Basic/Attr.td
+++ clang/include/clang/Basic/Attr.td
@@ -2748,6 +2748,11 @@
let Documentation = [PreserveAllDocs];
}
+def RISCVVectorCC: DeclOrTypeAttr {
+ let Spellings = [Clang<"riscv_vector_cc">];
+ let Documentation = [RISCVVectorCCDocs];
+}
+
def Target : InheritableAttr {
let Spellings = [GCC<"target">];
let Args = [StringArgument<"featuresStr">];
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
