[X86] EmitX86BuiltinExpr - attempt to convert SSE41/AVX1 roundps/d/ss/sd builtins to regular rounding modes

[RKSimon]

Certain rounding modes used for _mm_round_ps etc. can be translated to the generic equivalents:

llvm-project/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp

Lines 1254 to 1268 in 535f604

	switch (N->getOpcode()) {
	default: llvm_unreachable("Unexpected opcode!");
	case ISD::STRICT_FCEIL:
	case ISD::FCEIL: Imm = 0xA; break;
	case ISD::STRICT_FFLOOR:
	case ISD::FFLOOR: Imm = 0x9; break;
	case ISD::STRICT_FTRUNC:
	case ISD::FTRUNC: Imm = 0xB; break;
	case ISD::STRICT_FROUNDEVEN:
	case ISD::FROUNDEVEN: Imm = 0x8; break;
	case ISD::STRICT_FNEARBYINT:
	case ISD::FNEARBYINT: Imm = 0xC; break;
	case ISD::STRICT_FRINT:
	case ISD::FRINT: Imm = 0x4; break;
	}

We should be trying to convert these to the ceil/floor/trunc/roundeven/nearbyint/rint intrinsics (either regular or strict/constrained depending on fp strict mode).

The scalar cases are a bit trickier requiring extraction/insertion.

I don't expect AVX512 rndscale equivalents to be fully handled in this patch, which can be messier to deal with.

[stomfaig]

I'd be happy to work on this.

[llvmbot]

Hi!

This issue may be a good introductory issue for people new to working on LLVM. If you would like to work on this issue, your first steps are:

1. Check that no other contributor is working on this issue. If someone is assigned to the issue or claimed to be working on it, ping the person. After one week without a response, the assignee may be changed.
2. Leave a comment indicating that you are working on the issue, or just create a pull request after following the steps below. Mention this issue in the description of the pull request.
3. Fix the issue locally.
4. Run the test suite locally. Remember that the subdirectories under test/ create fine-grained testing targets, so you can e.g. use make check-clang-ast to only run Clang's AST tests.
5. Create a Git commit.
6. Run git clang-format HEAD~1 to format your changes.
7. Open a pull request to the upstream repository on GitHub. Detailed instructions can be found in GitHub's documentation. Mention this issue in the description of the pull request.

If you have any further questions about this issue, don't hesitate to ask via a comment in the thread below.

[llvmbot]

@llvm/issue-subscribers-good-first-issue

Author: Simon Pilgrim (RKSimon)

Certain rounding modes used for _mm_round_ps etc. can be translated to the generic equivalents:

llvm-project/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp

Lines 1254 to 1268 in 535f604

	switch (N->getOpcode()) {
	default: llvm_unreachable("Unexpected opcode!");
	case ISD::STRICT_FCEIL:
	case ISD::FCEIL: Imm = 0xA; break;
	case ISD::STRICT_FFLOOR:
	case ISD::FFLOOR: Imm = 0x9; break;
	case ISD::STRICT_FTRUNC:
	case ISD::FTRUNC: Imm = 0xB; break;
	case ISD::STRICT_FROUNDEVEN:
	case ISD::FROUNDEVEN: Imm = 0x8; break;
	case ISD::STRICT_FNEARBYINT:
	case ISD::FNEARBYINT: Imm = 0xC; break;
	case ISD::STRICT_FRINT:
	case ISD::FRINT: Imm = 0x4; break;
	}

We should be trying to convert these to the ceil/floor/trunc/roundeven/nearbyint/rint intrinsics (either regular or strict/constrained depending on fp strict mode).

The scalar cases are a bit trickier requiring extraction/insertion.

I don't expect AVX512 rndscale equivalents to be fully handled in this patch, which can be messier to deal with.

[llvmbot]

@llvm/issue-subscribers-clang-frontend

Author: Simon Pilgrim (RKSimon)

Certain rounding modes used for _mm_round_ps etc. can be translated to the generic equivalents:

llvm-project/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp

Lines 1254 to 1268 in 535f604

	switch (N->getOpcode()) {
	default: llvm_unreachable("Unexpected opcode!");
	case ISD::STRICT_FCEIL:
	case ISD::FCEIL: Imm = 0xA; break;
	case ISD::STRICT_FFLOOR:
	case ISD::FFLOOR: Imm = 0x9; break;
	case ISD::STRICT_FTRUNC:
	case ISD::FTRUNC: Imm = 0xB; break;
	case ISD::STRICT_FROUNDEVEN:
	case ISD::FROUNDEVEN: Imm = 0x8; break;
	case ISD::STRICT_FNEARBYINT:
	case ISD::FNEARBYINT: Imm = 0xC; break;
	case ISD::STRICT_FRINT:
	case ISD::FRINT: Imm = 0x4; break;
	}

We should be trying to convert these to the ceil/floor/trunc/roundeven/nearbyint/rint intrinsics (either regular or strict/constrained depending on fp strict mode).

The scalar cases are a bit trickier requiring extraction/insertion.

I don't expect AVX512 rndscale equivalents to be fully handled in this patch, which can be messier to deal with.

[llvmbot]

@llvm/issue-subscribers-backend-x86

Author: Simon Pilgrim (RKSimon)

Certain rounding modes used for _mm_round_ps etc. can be translated to the generic equivalents:

llvm-project/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp

Lines 1254 to 1268 in 535f604

	switch (N->getOpcode()) {
	default: llvm_unreachable("Unexpected opcode!");
	case ISD::STRICT_FCEIL:
	case ISD::FCEIL: Imm = 0xA; break;
	case ISD::STRICT_FFLOOR:
	case ISD::FFLOOR: Imm = 0x9; break;
	case ISD::STRICT_FTRUNC:
	case ISD::FTRUNC: Imm = 0xB; break;
	case ISD::STRICT_FROUNDEVEN:
	case ISD::FROUNDEVEN: Imm = 0x8; break;
	case ISD::STRICT_FNEARBYINT:
	case ISD::FNEARBYINT: Imm = 0xC; break;
	case ISD::STRICT_FRINT:
	case ISD::FRINT: Imm = 0x4; break;
	}

We should be trying to convert these to the ceil/floor/trunc/roundeven/nearbyint/rint intrinsics (either regular or strict/constrained depending on fp strict mode).

The scalar cases are a bit trickier requiring extraction/insertion.

I don't expect AVX512 rndscale equivalents to be fully handled in this patch, which can be messier to deal with.