Skip to content

AMDGPU: Make v2f16 minimum/maximum legal for gfx950 #117738

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 26, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions llvm/lib/Target/AMDGPU/SIISelLowering.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -859,6 +859,9 @@ SITargetLowering::SITargetLowering(const TargetMachine &TM,
// FIXME: For nnan fmaximum, emit the fmaximum3 instead of fmaxnum
if (Subtarget->hasMinimum3Maximum3F32())
setOperationAction({ISD::FMAXIMUM, ISD::FMINIMUM}, MVT::f32, Legal);

if (Subtarget->hasMinimum3Maximum3PKF16())
setOperationAction({ISD::FMAXIMUM, ISD::FMINIMUM}, MVT::v2f16, Legal);
}

setOperationAction(ISD::INTRINSIC_WO_CHAIN,
Expand Down
11 changes: 11 additions & 0 deletions llvm/lib/Target/AMDGPU/VOP3PInstructions.td
Original file line number Diff line number Diff line change
Expand Up @@ -255,6 +255,17 @@ multiclass MadFmaMixPats<SDPatternOperator fma_like,
>;
}

class MinimumMaximumByMinimum3Maximum3VOP3P<SDPatternOperator node,
Instruction inst> : GCNPat<
(v2f16 (node (VOP3PMods v2f16:$src0, i32:$src0_mods), (VOP3PMods v2f16:$src1, i32:$src1_mods))),
(inst $src0_mods, $src0, $src1_mods, $src1, $src1_mods, $src1)
>;

let SubtargetPredicate = HasMinimum3Maximum3PKF16 in {
def : MinimumMaximumByMinimum3Maximum3VOP3P<fminimum, V_PK_MINIMUM3_F16>;
def : MinimumMaximumByMinimum3Maximum3VOP3P<fmaximum, V_PK_MAXIMUM3_F16>;
}

let SubtargetPredicate = HasMadMixInsts, OtherPredicates = [NoFP32Denormals] in {

// These are VOP3a-like opcodes which accept no omod.
Expand Down
Loading