Skip to content

[llvm][CodeGen] Intrinsic llvm.powi.* code gen for vector arguments #118242

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.

Sign up for GitHub

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 7 commits into from
Dec 19, 2024
Merged

[llvm][CodeGen] Intrinsic llvm.powi.* code gen for vector arguments #118242

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
7f5a128
[llvm][CodeGen] Intrinsic `llvm.powi.*` code gen for vector arguments
ylzsx Nov 30, 2024
73281bc
Modify test file name. NFC
ylzsx Dec 2, 2024
e2c155d
Fixes for reviews.
ylzsx Dec 4, 2024
685192d
Fixes for review.
ylzsx Dec 4, 2024
2576758
code formatter
ylzsx Dec 4, 2024
5abe500
Intrinsic `llvm.ldexp.*` should not be affected.
ylzsx Dec 6, 2024
71a396e
Add comment.
ylzsx Dec 10, 2024
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
7 changes: 7 additions & 0 deletions llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2585,6 +2585,13 @@ SDValue DAGTypeLegalizer::PromoteIntOp_ExpOp(SDNode *N) {
: RTLIB::getLDEXP(N->getValueType(0));

if (LC == RTLIB::UNKNOWN_LIBCALL || !TLI.getLibcallName(LC)) {
// Scalarize vector FPOWI instead of promoting the type. This allows the
// scalar FPOWIs to be visited and converted to libcalls before promoting
// the type.
// FIXME: This should be done in LegalizeVectorOps/LegalizeDAG, but call
// lowering needs the unpromoted EVT.
if (IsPowI && N->getValueType(0).isVector())
return DAG.UnrollVectorOp(N);
SmallVector<SDValue, 3> NewOps(N->ops());
NewOps[1 + OpOffset] = SExtPromotedInteger(N->getOperand(1 + OpOffset));
return SDValue(DAG.UpdateNodeOperands(N, NewOps), 0);
Expand Down
142 changes: 142 additions & 0 deletions llvm/test/CodeGen/LoongArch/lasx/fpowi.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,142 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc --mtriple=loongarch64 --mattr=+lasx < %s | FileCheck %s

declare <8 x float> @llvm.powi.v8f32.i32(<8 x float>, i32)

define <8 x float> @powi_v8f32(<8 x float> %va, i32 %b) nounwind {
; CHECK-LABEL: powi_v8f32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi.d $sp, $sp, -80
; CHECK-NEXT: st.d $ra, $sp, 72 # 8-byte Folded Spill
; CHECK-NEXT: st.d $fp, $sp, 64 # 8-byte Folded Spill
; CHECK-NEXT: xvst $xr0, $sp, 0 # 32-byte Folded Spill
; CHECK-NEXT: addi.w $fp, $a0, 0
; CHECK-NEXT: xvpickve2gr.w $a0, $xr0, 0
; CHECK-NEXT: movgr2fr.w $fa0, $a0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powisf2)
; CHECK-NEXT: movfr2gr.s $a0, $fa0
; CHECK-NEXT: xvinsgr2vr.w $xr0, $a0, 0
; CHECK-NEXT: xvst $xr0, $sp, 32 # 32-byte Folded Spill
; CHECK-NEXT: xvld $xr0, $sp, 0 # 32-byte Folded Reload
; CHECK-NEXT: xvpickve2gr.w $a0, $xr0, 1
; CHECK-NEXT: movgr2fr.w $fa0, $a0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powisf2)
; CHECK-NEXT: movfr2gr.s $a0, $fa0
; CHECK-NEXT: xvld $xr0, $sp, 32 # 32-byte Folded Reload
; CHECK-NEXT: xvinsgr2vr.w $xr0, $a0, 1
; CHECK-NEXT: xvst $xr0, $sp, 32 # 32-byte Folded Spill
; CHECK-NEXT: xvld $xr0, $sp, 0 # 32-byte Folded Reload
; CHECK-NEXT: xvpickve2gr.w $a0, $xr0, 2
; CHECK-NEXT: movgr2fr.w $fa0, $a0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powisf2)
; CHECK-NEXT: movfr2gr.s $a0, $fa0
; CHECK-NEXT: xvld $xr0, $sp, 32 # 32-byte Folded Reload
; CHECK-NEXT: xvinsgr2vr.w $xr0, $a0, 2
; CHECK-NEXT: xvst $xr0, $sp, 32 # 32-byte Folded Spill
; CHECK-NEXT: xvld $xr0, $sp, 0 # 32-byte Folded Reload
; CHECK-NEXT: xvpickve2gr.w $a0, $xr0, 3
; CHECK-NEXT: movgr2fr.w $fa0, $a0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powisf2)
; CHECK-NEXT: movfr2gr.s $a0, $fa0
; CHECK-NEXT: xvld $xr0, $sp, 32 # 32-byte Folded Reload
; CHECK-NEXT: xvinsgr2vr.w $xr0, $a0, 3
; CHECK-NEXT: xvst $xr0, $sp, 32 # 32-byte Folded Spill
; CHECK-NEXT: xvld $xr0, $sp, 0 # 32-byte Folded Reload
; CHECK-NEXT: xvpickve2gr.w $a0, $xr0, 4
; CHECK-NEXT: movgr2fr.w $fa0, $a0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powisf2)
; CHECK-NEXT: movfr2gr.s $a0, $fa0
; CHECK-NEXT: xvld $xr0, $sp, 32 # 32-byte Folded Reload
; CHECK-NEXT: xvinsgr2vr.w $xr0, $a0, 4
; CHECK-NEXT: xvst $xr0, $sp, 32 # 32-byte Folded Spill
; CHECK-NEXT: xvld $xr0, $sp, 0 # 32-byte Folded Reload
; CHECK-NEXT: xvpickve2gr.w $a0, $xr0, 5
; CHECK-NEXT: movgr2fr.w $fa0, $a0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powisf2)
; CHECK-NEXT: movfr2gr.s $a0, $fa0
; CHECK-NEXT: xvld $xr0, $sp, 32 # 32-byte Folded Reload
; CHECK-NEXT: xvinsgr2vr.w $xr0, $a0, 5
; CHECK-NEXT: xvst $xr0, $sp, 32 # 32-byte Folded Spill
; CHECK-NEXT: xvld $xr0, $sp, 0 # 32-byte Folded Reload
; CHECK-NEXT: xvpickve2gr.w $a0, $xr0, 6
; CHECK-NEXT: movgr2fr.w $fa0, $a0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powisf2)
; CHECK-NEXT: movfr2gr.s $a0, $fa0
; CHECK-NEXT: xvld $xr0, $sp, 32 # 32-byte Folded Reload
; CHECK-NEXT: xvinsgr2vr.w $xr0, $a0, 6
; CHECK-NEXT: xvst $xr0, $sp, 32 # 32-byte Folded Spill
; CHECK-NEXT: xvld $xr0, $sp, 0 # 32-byte Folded Reload
; CHECK-NEXT: xvpickve2gr.w $a0, $xr0, 7
; CHECK-NEXT: movgr2fr.w $fa0, $a0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powisf2)
; CHECK-NEXT: movfr2gr.s $a0, $fa0
; CHECK-NEXT: xvld $xr0, $sp, 32 # 32-byte Folded Reload
; CHECK-NEXT: xvinsgr2vr.w $xr0, $a0, 7
; CHECK-NEXT: ld.d $fp, $sp, 64 # 8-byte Folded Reload
; CHECK-NEXT: ld.d $ra, $sp, 72 # 8-byte Folded Reload
; CHECK-NEXT: addi.d $sp, $sp, 80
; CHECK-NEXT: ret
entry:
%res = call <8 x float> @llvm.powi.v8f32.i32(<8 x float> %va, i32 %b)
ret <8 x float> %res
}

declare <4 x double> @llvm.powi.v4f64.i32(<4 x double>, i32)

define <4 x double> @powi_v4f64(<4 x double> %va, i32 %b) nounwind {
; CHECK-LABEL: powi_v4f64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi.d $sp, $sp, -80
; CHECK-NEXT: st.d $ra, $sp, 72 # 8-byte Folded Spill
; CHECK-NEXT: st.d $fp, $sp, 64 # 8-byte Folded Spill
; CHECK-NEXT: xvst $xr0, $sp, 0 # 32-byte Folded Spill
; CHECK-NEXT: addi.w $fp, $a0, 0
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 0
; CHECK-NEXT: movgr2fr.d $fa0, $a0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powidf2)
; CHECK-NEXT: movfr2gr.d $a0, $fa0
; CHECK-NEXT: xvinsgr2vr.d $xr0, $a0, 0
; CHECK-NEXT: xvst $xr0, $sp, 32 # 32-byte Folded Spill
; CHECK-NEXT: xvld $xr0, $sp, 0 # 32-byte Folded Reload
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 1
; CHECK-NEXT: movgr2fr.d $fa0, $a0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powidf2)
; CHECK-NEXT: movfr2gr.d $a0, $fa0
; CHECK-NEXT: xvld $xr0, $sp, 32 # 32-byte Folded Reload
; CHECK-NEXT: xvinsgr2vr.d $xr0, $a0, 1
; CHECK-NEXT: xvst $xr0, $sp, 32 # 32-byte Folded Spill
; CHECK-NEXT: xvld $xr0, $sp, 0 # 32-byte Folded Reload
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 2
; CHECK-NEXT: movgr2fr.d $fa0, $a0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powidf2)
; CHECK-NEXT: movfr2gr.d $a0, $fa0
; CHECK-NEXT: xvld $xr0, $sp, 32 # 32-byte Folded Reload
; CHECK-NEXT: xvinsgr2vr.d $xr0, $a0, 2
; CHECK-NEXT: xvst $xr0, $sp, 32 # 32-byte Folded Spill
; CHECK-NEXT: xvld $xr0, $sp, 0 # 32-byte Folded Reload
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 3
; CHECK-NEXT: movgr2fr.d $fa0, $a0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powidf2)
; CHECK-NEXT: movfr2gr.d $a0, $fa0
; CHECK-NEXT: xvld $xr0, $sp, 32 # 32-byte Folded Reload
; CHECK-NEXT: xvinsgr2vr.d $xr0, $a0, 3
; CHECK-NEXT: ld.d $fp, $sp, 64 # 8-byte Folded Reload
; CHECK-NEXT: ld.d $ra, $sp, 72 # 8-byte Folded Reload
; CHECK-NEXT: addi.d $sp, $sp, 80
; CHECK-NEXT: ret
entry:
%res = call <4 x double> @llvm.powi.v4f64.i32(<4 x double> %va, i32 %b)
ret <4 x double> %res
}
88 changes: 88 additions & 0 deletions llvm/test/CodeGen/LoongArch/lsx/fpowi.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,88 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc --mtriple=loongarch64 --mattr=+lsx < %s | FileCheck %s

declare <4 x float> @llvm.powi.v4f32.i32(<4 x float>, i32)

define <4 x float> @powi_v4f32(<4 x float> %va, i32 %b) nounwind {
; CHECK-LABEL: powi_v4f32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi.d $sp, $sp, -48
; CHECK-NEXT: st.d $ra, $sp, 40 # 8-byte Folded Spill
; CHECK-NEXT: st.d $fp, $sp, 32 # 8-byte Folded Spill
; CHECK-NEXT: vst $vr0, $sp, 0 # 16-byte Folded Spill
; CHECK-NEXT: addi.w $fp, $a0, 0
; CHECK-NEXT: vreplvei.w $vr0, $vr0, 0
; CHECK-NEXT: # kill: def $f0 killed $f0 killed $vr0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powisf2)
; CHECK-NEXT: movfr2gr.s $a0, $fa0
; CHECK-NEXT: vinsgr2vr.w $vr0, $a0, 0
; CHECK-NEXT: vst $vr0, $sp, 16 # 16-byte Folded Spill
; CHECK-NEXT: vld $vr0, $sp, 0 # 16-byte Folded Reload
; CHECK-NEXT: vreplvei.w $vr0, $vr0, 1
; CHECK-NEXT: # kill: def $f0 killed $f0 killed $vr0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powisf2)
; CHECK-NEXT: movfr2gr.s $a0, $fa0
; CHECK-NEXT: vld $vr0, $sp, 16 # 16-byte Folded Reload
; CHECK-NEXT: vinsgr2vr.w $vr0, $a0, 1
; CHECK-NEXT: vst $vr0, $sp, 16 # 16-byte Folded Spill
; CHECK-NEXT: vld $vr0, $sp, 0 # 16-byte Folded Reload
; CHECK-NEXT: vreplvei.w $vr0, $vr0, 2
; CHECK-NEXT: # kill: def $f0 killed $f0 killed $vr0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powisf2)
; CHECK-NEXT: movfr2gr.s $a0, $fa0
; CHECK-NEXT: vld $vr0, $sp, 16 # 16-byte Folded Reload
; CHECK-NEXT: vinsgr2vr.w $vr0, $a0, 2
; CHECK-NEXT: vst $vr0, $sp, 16 # 16-byte Folded Spill
; CHECK-NEXT: vld $vr0, $sp, 0 # 16-byte Folded Reload
; CHECK-NEXT: vreplvei.w $vr0, $vr0, 3
; CHECK-NEXT: # kill: def $f0 killed $f0 killed $vr0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powisf2)
; CHECK-NEXT: movfr2gr.s $a0, $fa0
; CHECK-NEXT: vld $vr0, $sp, 16 # 16-byte Folded Reload
; CHECK-NEXT: vinsgr2vr.w $vr0, $a0, 3
; CHECK-NEXT: ld.d $fp, $sp, 32 # 8-byte Folded Reload
; CHECK-NEXT: ld.d $ra, $sp, 40 # 8-byte Folded Reload
; CHECK-NEXT: addi.d $sp, $sp, 48
; CHECK-NEXT: ret
entry:
%res = call <4 x float> @llvm.powi.v4f32.i32(<4 x float> %va, i32 %b)
ret <4 x float> %res
}

declare <2 x double> @llvm.powi.v2f64.i32(<2 x double>, i32)

define <2 x double> @powi_v2f64(<2 x double> %va, i32 %b) nounwind {
; CHECK-LABEL: powi_v2f64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi.d $sp, $sp, -48
; CHECK-NEXT: st.d $ra, $sp, 40 # 8-byte Folded Spill
; CHECK-NEXT: st.d $fp, $sp, 32 # 8-byte Folded Spill
; CHECK-NEXT: vst $vr0, $sp, 0 # 16-byte Folded Spill
; CHECK-NEXT: addi.w $fp, $a0, 0
; CHECK-NEXT: vreplvei.d $vr0, $vr0, 0
; CHECK-NEXT: # kill: def $f0_64 killed $f0_64 killed $vr0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powidf2)
; CHECK-NEXT: movfr2gr.d $a0, $fa0
; CHECK-NEXT: vinsgr2vr.d $vr0, $a0, 0
; CHECK-NEXT: vst $vr0, $sp, 16 # 16-byte Folded Spill
; CHECK-NEXT: vld $vr0, $sp, 0 # 16-byte Folded Reload
; CHECK-NEXT: vreplvei.d $vr0, $vr0, 1
; CHECK-NEXT: # kill: def $f0_64 killed $f0_64 killed $vr0
; CHECK-NEXT: move $a0, $fp
; CHECK-NEXT: bl %plt(__powidf2)
; CHECK-NEXT: movfr2gr.d $a0, $fa0
; CHECK-NEXT: vld $vr0, $sp, 16 # 16-byte Folded Reload
; CHECK-NEXT: vinsgr2vr.d $vr0, $a0, 1
; CHECK-NEXT: ld.d $fp, $sp, 32 # 8-byte Folded Reload
; CHECK-NEXT: ld.d $ra, $sp, 40 # 8-byte Folded Reload
; CHECK-NEXT: addi.d $sp, $sp, 48
; CHECK-NEXT: ret
entry:
%res = call <2 x double> @llvm.powi.v2f64.i32(<2 x double> %va, i32 %b)
ret <2 x double> %res
}
Loading
Loading