[llvm] [GlobalISel][AArch64] Add libcall lowering for fpowi. (PR #67114)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Sep 22 04:03:53 PDT 2023
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-aarch64
<details>
<summary>Changes</summary>
This adds legalization, notably libcall lowering for fpowi. It is a little different to other methods as the function takes both a float and integer register. Otherwise all vectors get scalarized and fp16 is promoted to fp32.
---
Patch is 63.91 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/67114.diff
4 Files Affected:
- (modified) llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp (+22)
- (modified) llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp (+4)
- (modified) llvm/test/CodeGen/AArch64/GlobalISel/legalizer-info-validation.mir (+2-2)
- (added) llvm/test/CodeGen/AArch64/fpowi.ll (+1422)
``````````diff
diff --git a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
index 0c3f558ac2a6419..8178a9291877360 100644
--- a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
@@ -531,6 +531,8 @@ static RTLIB::Libcall getRTLibDesc(unsigned Opcode, unsigned Size) {
RTLIBCASE(REM_F);
case TargetOpcode::G_FPOW:
RTLIBCASE(POW_F);
+ case TargetOpcode::G_FPOWI:
+ RTLIBCASE(POWI_F);
case TargetOpcode::G_FMA:
RTLIBCASE(FMA_F);
case TargetOpcode::G_FSIN:
@@ -851,6 +853,24 @@ LegalizerHelper::libcall(MachineInstr &MI, LostDebugLocObserver &LocObserver) {
return Status;
break;
}
+ case TargetOpcode::G_FPOWI: {
+ Type *HLTy = getFloatTypeForLLT(Ctx, LLTy);
+ Type *ITy = IntegerType::get(
+ Ctx, MRI.getType(MI.getOperand(2).getReg()).getSizeInBits());
+ if (!HLTy || (Size != 32 && Size != 64 && Size != 80 && Size != 128)) {
+ LLVM_DEBUG(dbgs() << "No libcall available for type " << LLTy << ".\n");
+ return UnableToLegalize;
+ }
+ auto Libcall = getRTLibDesc(MI.getOpcode(), Size);
+ SmallVector<CallLowering::ArgInfo, 2> Args;
+ Args.push_back({MI.getOperand(1).getReg(), HLTy, 0});
+ Args.push_back({MI.getOperand(2).getReg(), ITy, 1});
+ LegalizeResult Status = createLibcall(
+ MIRBuilder, Libcall, {MI.getOperand(0).getReg(), HLTy, 0}, Args);
+ if (Status != Legalized)
+ return Status;
+ break;
+ }
case TargetOpcode::G_FPEXT:
case TargetOpcode::G_FPTRUNC: {
Type *FromTy = getFloatTypeForLLT(Ctx, MRI.getType(MI.getOperand(1).getReg()));
@@ -4344,6 +4364,8 @@ LegalizerHelper::fewerElementsVector(MachineInstr &MI, unsigned TypeIdx,
return fewerElementsVectorReductions(MI, TypeIdx, NarrowTy);
case G_SHUFFLE_VECTOR:
return fewerElementsVectorShuffle(MI, TypeIdx, NarrowTy);
+ case G_FPOWI:
+ return fewerElementsVectorMultiEltType(GMI, NumElts, {2 /*pow*/});
default:
return UnableToLegalize;
}
diff --git a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
index d07de82de1335af..08d73bacd15e73c 100644
--- a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
+++ b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
@@ -284,6 +284,10 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST)
// Regardless of FP16 support, widen 16-bit elements to 32-bits.
.minScalar(0, s32)
.libcallFor({s32, s64});
+ getActionDefinitionsBuilder(G_FPOWI)
+ .scalarize(0)
+ .minScalar(0, s32)
+ .libcallFor({{s32, s32}, {s64, s32}});
getActionDefinitionsBuilder(G_INSERT)
.legalIf(all(typeInSet(0, {s32, s64, p0}),
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/legalizer-info-validation.mir b/llvm/test/CodeGen/AArch64/GlobalISel/legalizer-info-validation.mir
index b38868a530264e9..b0c8be4577e9229 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/legalizer-info-validation.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/legalizer-info-validation.mir
@@ -459,8 +459,8 @@
# DEBUG-NEXT: .. the first uncovered type index: 1, OK
# DEBUG-NEXT: .. the first uncovered imm index: 0, OK
# DEBUG-NEXT: G_FPOWI (opcode {{[0-9]+}}): 2 type indices, 0 imm indices
-# DEBUG-NEXT:.. type index coverage check SKIPPED: no rules defined
-# DEBUG-NEXT:.. imm index coverage check SKIPPED: no rules defined
+# DEBUG-NEXT: .. the first uncovered type index: 2, OK
+# DEBUG-NEXT: .. the first uncovered imm index: 0, OK
# DEBUG-NEXT: G_FEXP (opcode {{[0-9]+}}): 1 type index, 0 imm indices
# DEBUG-NEXT: .. opcode {{[0-9]+}} is aliased to {{[0-9]+}}
# DEBUG-NEXT: .. the first uncovered type index: 1, OK
diff --git a/llvm/test/CodeGen/AArch64/fpowi.ll b/llvm/test/CodeGen/AArch64/fpowi.ll
new file mode 100644
index 000000000000000..e80371784a1b3b3
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/fpowi.ll
@@ -0,0 +1,1422 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
+; RUN: llc -mtriple=aarch64-none-eabi -verify-machineinstrs %s -o - | FileCheck %s --check-prefixes=CHECK,CHECK-SD
+; RUN: llc -mtriple=aarch64-none-eabi -global-isel -verify-machineinstrs %s -o - | FileCheck %s --check-prefixes=CHECK,CHECK-GI
+
+define double @powi_f64(double %a, i32 %b) {
+; CHECK-SD-LABEL: powi_f64:
+; CHECK-SD: // %bb.0: // %entry
+; CHECK-SD-NEXT: b __powidf2
+;
+; CHECK-GI-LABEL: powi_f64:
+; CHECK-GI: // %bb.0: // %entry
+; CHECK-GI-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-GI-NEXT: .cfi_def_cfa_offset 16
+; CHECK-GI-NEXT: .cfi_offset w30, -16
+; CHECK-GI-NEXT: bl __powidf2
+; CHECK-GI-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
+; CHECK-GI-NEXT: ret
+entry:
+ %c = call double @llvm.powi.f64.i32(double %a, i32 %b)
+ ret double %c
+}
+
+define float @powi_f32(float %a, i32 %b) {
+; CHECK-SD-LABEL: powi_f32:
+; CHECK-SD: // %bb.0: // %entry
+; CHECK-SD-NEXT: b __powisf2
+;
+; CHECK-GI-LABEL: powi_f32:
+; CHECK-GI: // %bb.0: // %entry
+; CHECK-GI-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-GI-NEXT: .cfi_def_cfa_offset 16
+; CHECK-GI-NEXT: .cfi_offset w30, -16
+; CHECK-GI-NEXT: bl __powisf2
+; CHECK-GI-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
+; CHECK-GI-NEXT: ret
+entry:
+ %c = call float @llvm.powi.f32.i32(float %a, i32 %b)
+ ret float %c
+}
+
+define half @powi_f16(half %a, i32 %b) {
+; CHECK-LABEL: powi_f16:
+; CHECK: // %bb.0: // %entry
+; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-NEXT: .cfi_def_cfa_offset 16
+; CHECK-NEXT: .cfi_offset w30, -16
+; CHECK-NEXT: fcvt s0, h0
+; CHECK-NEXT: bl __powisf2
+; CHECK-NEXT: fcvt h0, s0
+; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
+; CHECK-NEXT: ret
+entry:
+ %c = call half @llvm.powi.f16.i32(half %a, i32 %b)
+ ret half %c
+}
+
+define <2 x double> @powi_v2f64(<2 x double> %a, i32 %b) {
+; CHECK-SD-LABEL: powi_v2f64:
+; CHECK-SD: // %bb.0: // %entry
+; CHECK-SD-NEXT: sub sp, sp, #48
+; CHECK-SD-NEXT: stp x30, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-SD-NEXT: .cfi_def_cfa_offset 48
+; CHECK-SD-NEXT: .cfi_offset w19, -8
+; CHECK-SD-NEXT: .cfi_offset w30, -16
+; CHECK-SD-NEXT: str q0, [sp] // 16-byte Folded Spill
+; CHECK-SD-NEXT: mov d0, v0.d[1]
+; CHECK-SD-NEXT: mov w19, w0
+; CHECK-SD-NEXT: bl __powidf2
+; CHECK-SD-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
+; CHECK-SD-NEXT: ldr q0, [sp] // 16-byte Folded Reload
+; CHECK-SD-NEXT: mov w0, w19
+; CHECK-SD-NEXT: // kill: def $d0 killed $d0 killed $q0
+; CHECK-SD-NEXT: bl __powidf2
+; CHECK-SD-NEXT: ldr q1, [sp, #16] // 16-byte Folded Reload
+; CHECK-SD-NEXT: ldp x30, x19, [sp, #32] // 16-byte Folded Reload
+; CHECK-SD-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-SD-NEXT: mov v0.d[1], v1.d[0]
+; CHECK-SD-NEXT: add sp, sp, #48
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: powi_v2f64:
+; CHECK-GI: // %bb.0: // %entry
+; CHECK-GI-NEXT: sub sp, sp, #48
+; CHECK-GI-NEXT: str d8, [sp, #16] // 8-byte Folded Spill
+; CHECK-GI-NEXT: stp x30, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-GI-NEXT: .cfi_def_cfa_offset 48
+; CHECK-GI-NEXT: .cfi_offset w19, -8
+; CHECK-GI-NEXT: .cfi_offset w30, -16
+; CHECK-GI-NEXT: .cfi_offset b8, -32
+; CHECK-GI-NEXT: mov d8, v0.d[1]
+; CHECK-GI-NEXT: mov w19, w0
+; CHECK-GI-NEXT: // kill: def $d0 killed $d0 killed $q0
+; CHECK-GI-NEXT: bl __powidf2
+; CHECK-GI-NEXT: str q0, [sp] // 16-byte Folded Spill
+; CHECK-GI-NEXT: fmov d0, d8
+; CHECK-GI-NEXT: mov w0, w19
+; CHECK-GI-NEXT: bl __powidf2
+; CHECK-GI-NEXT: ldr q1, [sp] // 16-byte Folded Reload
+; CHECK-GI-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-GI-NEXT: ldp x30, x19, [sp, #32] // 16-byte Folded Reload
+; CHECK-GI-NEXT: ldr d8, [sp, #16] // 8-byte Folded Reload
+; CHECK-GI-NEXT: mov v1.d[1], v0.d[0]
+; CHECK-GI-NEXT: mov v0.16b, v1.16b
+; CHECK-GI-NEXT: add sp, sp, #48
+; CHECK-GI-NEXT: ret
+entry:
+ %c = call <2 x double> @llvm.powi.v2f64.i32(<2 x double> %a, i32 %b)
+ ret <2 x double> %c
+}
+
+define <3 x double> @powi_v3f64(<3 x double> %a, i32 %b) {
+; CHECK-SD-LABEL: powi_v3f64:
+; CHECK-SD: // %bb.0: // %entry
+; CHECK-SD-NEXT: str d10, [sp, #-48]! // 8-byte Folded Spill
+; CHECK-SD-NEXT: stp d9, d8, [sp, #16] // 16-byte Folded Spill
+; CHECK-SD-NEXT: stp x30, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-SD-NEXT: .cfi_def_cfa_offset 48
+; CHECK-SD-NEXT: .cfi_offset w19, -8
+; CHECK-SD-NEXT: .cfi_offset w30, -16
+; CHECK-SD-NEXT: .cfi_offset b8, -24
+; CHECK-SD-NEXT: .cfi_offset b9, -32
+; CHECK-SD-NEXT: .cfi_offset b10, -48
+; CHECK-SD-NEXT: mov w19, w0
+; CHECK-SD-NEXT: fmov d8, d2
+; CHECK-SD-NEXT: fmov d9, d1
+; CHECK-SD-NEXT: bl __powidf2
+; CHECK-SD-NEXT: fmov d10, d0
+; CHECK-SD-NEXT: fmov d0, d9
+; CHECK-SD-NEXT: mov w0, w19
+; CHECK-SD-NEXT: bl __powidf2
+; CHECK-SD-NEXT: fmov d9, d0
+; CHECK-SD-NEXT: fmov d0, d8
+; CHECK-SD-NEXT: mov w0, w19
+; CHECK-SD-NEXT: bl __powidf2
+; CHECK-SD-NEXT: fmov d1, d9
+; CHECK-SD-NEXT: ldp x30, x19, [sp, #32] // 16-byte Folded Reload
+; CHECK-SD-NEXT: ldp d9, d8, [sp, #16] // 16-byte Folded Reload
+; CHECK-SD-NEXT: fmov d2, d0
+; CHECK-SD-NEXT: fmov d0, d10
+; CHECK-SD-NEXT: ldr d10, [sp], #48 // 8-byte Folded Reload
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: powi_v3f64:
+; CHECK-GI: // %bb.0: // %entry
+; CHECK-GI-NEXT: str d10, [sp, #-48]! // 8-byte Folded Spill
+; CHECK-GI-NEXT: stp d9, d8, [sp, #16] // 16-byte Folded Spill
+; CHECK-GI-NEXT: stp x30, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-GI-NEXT: .cfi_def_cfa_offset 48
+; CHECK-GI-NEXT: .cfi_offset w19, -8
+; CHECK-GI-NEXT: .cfi_offset w30, -16
+; CHECK-GI-NEXT: .cfi_offset b8, -24
+; CHECK-GI-NEXT: .cfi_offset b9, -32
+; CHECK-GI-NEXT: .cfi_offset b10, -48
+; CHECK-GI-NEXT: fmov d8, d1
+; CHECK-GI-NEXT: fmov d9, d2
+; CHECK-GI-NEXT: mov w19, w0
+; CHECK-GI-NEXT: bl __powidf2
+; CHECK-GI-NEXT: fmov d10, d0
+; CHECK-GI-NEXT: fmov d0, d8
+; CHECK-GI-NEXT: mov w0, w19
+; CHECK-GI-NEXT: bl __powidf2
+; CHECK-GI-NEXT: fmov d8, d0
+; CHECK-GI-NEXT: fmov d0, d9
+; CHECK-GI-NEXT: mov w0, w19
+; CHECK-GI-NEXT: bl __powidf2
+; CHECK-GI-NEXT: fmov d1, d8
+; CHECK-GI-NEXT: ldp x30, x19, [sp, #32] // 16-byte Folded Reload
+; CHECK-GI-NEXT: ldp d9, d8, [sp, #16] // 16-byte Folded Reload
+; CHECK-GI-NEXT: fmov d2, d0
+; CHECK-GI-NEXT: fmov d0, d10
+; CHECK-GI-NEXT: ldr d10, [sp], #48 // 8-byte Folded Reload
+; CHECK-GI-NEXT: ret
+entry:
+ %c = call <3 x double> @llvm.powi.v3f64.i32(<3 x double> %a, i32 %b)
+ ret <3 x double> %c
+}
+
+define <4 x double> @powi_v4f64(<4 x double> %a, i32 %b) {
+; CHECK-SD-LABEL: powi_v4f64:
+; CHECK-SD: // %bb.0: // %entry
+; CHECK-SD-NEXT: sub sp, sp, #64
+; CHECK-SD-NEXT: stp x30, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK-SD-NEXT: .cfi_def_cfa_offset 64
+; CHECK-SD-NEXT: .cfi_offset w19, -8
+; CHECK-SD-NEXT: .cfi_offset w30, -16
+; CHECK-SD-NEXT: str q0, [sp] // 16-byte Folded Spill
+; CHECK-SD-NEXT: mov d0, v0.d[1]
+; CHECK-SD-NEXT: mov w19, w0
+; CHECK-SD-NEXT: str q1, [sp, #32] // 16-byte Folded Spill
+; CHECK-SD-NEXT: bl __powidf2
+; CHECK-SD-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
+; CHECK-SD-NEXT: ldr q0, [sp] // 16-byte Folded Reload
+; CHECK-SD-NEXT: mov w0, w19
+; CHECK-SD-NEXT: // kill: def $d0 killed $d0 killed $q0
+; CHECK-SD-NEXT: bl __powidf2
+; CHECK-SD-NEXT: ldr q1, [sp, #16] // 16-byte Folded Reload
+; CHECK-SD-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-SD-NEXT: mov w0, w19
+; CHECK-SD-NEXT: mov v0.d[1], v1.d[0]
+; CHECK-SD-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
+; CHECK-SD-NEXT: ldr q0, [sp, #32] // 16-byte Folded Reload
+; CHECK-SD-NEXT: mov d0, v0.d[1]
+; CHECK-SD-NEXT: bl __powidf2
+; CHECK-SD-NEXT: str q0, [sp] // 16-byte Folded Spill
+; CHECK-SD-NEXT: ldr q0, [sp, #32] // 16-byte Folded Reload
+; CHECK-SD-NEXT: mov w0, w19
+; CHECK-SD-NEXT: // kill: def $d0 killed $d0 killed $q0
+; CHECK-SD-NEXT: bl __powidf2
+; CHECK-SD-NEXT: fmov d1, d0
+; CHECK-SD-NEXT: ldp q2, q0, [sp] // 32-byte Folded Reload
+; CHECK-SD-NEXT: ldp x30, x19, [sp, #48] // 16-byte Folded Reload
+; CHECK-SD-NEXT: mov v1.d[1], v2.d[0]
+; CHECK-SD-NEXT: add sp, sp, #64
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: powi_v4f64:
+; CHECK-GI: // %bb.0: // %entry
+; CHECK-GI-NEXT: sub sp, sp, #80
+; CHECK-GI-NEXT: stp d9, d8, [sp, #48] // 16-byte Folded Spill
+; CHECK-GI-NEXT: stp x30, x19, [sp, #64] // 16-byte Folded Spill
+; CHECK-GI-NEXT: .cfi_def_cfa_offset 80
+; CHECK-GI-NEXT: .cfi_offset w19, -8
+; CHECK-GI-NEXT: .cfi_offset w30, -16
+; CHECK-GI-NEXT: .cfi_offset b8, -24
+; CHECK-GI-NEXT: .cfi_offset b9, -32
+; CHECK-GI-NEXT: str q1, [sp] // 16-byte Folded Spill
+; CHECK-GI-NEXT: mov d8, v0.d[1]
+; CHECK-GI-NEXT: mov d9, v1.d[1]
+; CHECK-GI-NEXT: mov w19, w0
+; CHECK-GI-NEXT: // kill: def $d0 killed $d0 killed $q0
+; CHECK-GI-NEXT: bl __powidf2
+; CHECK-GI-NEXT: str q0, [sp, #32] // 16-byte Folded Spill
+; CHECK-GI-NEXT: fmov d0, d8
+; CHECK-GI-NEXT: mov w0, w19
+; CHECK-GI-NEXT: bl __powidf2
+; CHECK-GI-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
+; CHECK-GI-NEXT: ldr q0, [sp] // 16-byte Folded Reload
+; CHECK-GI-NEXT: mov w0, w19
+; CHECK-GI-NEXT: // kill: def $d0 killed $d0 killed $q0
+; CHECK-GI-NEXT: bl __powidf2
+; CHECK-GI-NEXT: str q0, [sp] // 16-byte Folded Spill
+; CHECK-GI-NEXT: fmov d0, d9
+; CHECK-GI-NEXT: mov w0, w19
+; CHECK-GI-NEXT: bl __powidf2
+; CHECK-GI-NEXT: ldp q1, q2, [sp, #16] // 32-byte Folded Reload
+; CHECK-GI-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-GI-NEXT: ldp x30, x19, [sp, #64] // 16-byte Folded Reload
+; CHECK-GI-NEXT: ldp d9, d8, [sp, #48] // 16-byte Folded Reload
+; CHECK-GI-NEXT: mov v2.d[1], v1.d[0]
+; CHECK-GI-NEXT: ldr q1, [sp] // 16-byte Folded Reload
+; CHECK-GI-NEXT: mov v1.d[1], v0.d[0]
+; CHECK-GI-NEXT: mov v0.16b, v2.16b
+; CHECK-GI-NEXT: add sp, sp, #80
+; CHECK-GI-NEXT: ret
+entry:
+ %c = call <4 x double> @llvm.powi.v4f64.i32(<4 x double> %a, i32 %b)
+ ret <4 x double> %c
+}
+
+define <2 x float> @powi_v2f32(<2 x float> %a, i32 %b) {
+; CHECK-SD-LABEL: powi_v2f32:
+; CHECK-SD: // %bb.0: // %entry
+; CHECK-SD-NEXT: sub sp, sp, #48
+; CHECK-SD-NEXT: stp x30, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-SD-NEXT: .cfi_def_cfa_offset 48
+; CHECK-SD-NEXT: .cfi_offset w19, -8
+; CHECK-SD-NEXT: .cfi_offset w30, -16
+; CHECK-SD-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-SD-NEXT: str q0, [sp] // 16-byte Folded Spill
+; CHECK-SD-NEXT: mov w19, w0
+; CHECK-SD-NEXT: mov s0, v0.s[1]
+; CHECK-SD-NEXT: bl __powisf2
+; CHECK-SD-NEXT: str d0, [sp, #16] // 16-byte Folded Spill
+; CHECK-SD-NEXT: ldr q0, [sp] // 16-byte Folded Reload
+; CHECK-SD-NEXT: mov w0, w19
+; CHECK-SD-NEXT: // kill: def $s0 killed $s0 killed $q0
+; CHECK-SD-NEXT: bl __powisf2
+; CHECK-SD-NEXT: ldr q1, [sp, #16] // 16-byte Folded Reload
+; CHECK-SD-NEXT: // kill: def $s0 killed $s0 def $q0
+; CHECK-SD-NEXT: ldp x30, x19, [sp, #32] // 16-byte Folded Reload
+; CHECK-SD-NEXT: mov v0.s[1], v1.s[0]
+; CHECK-SD-NEXT: // kill: def $d0 killed $d0 killed $q0
+; CHECK-SD-NEXT: add sp, sp, #48
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: powi_v2f32:
+; CHECK-GI: // %bb.0: // %entry
+; CHECK-GI-NEXT: sub sp, sp, #48
+; CHECK-GI-NEXT: str d8, [sp, #16] // 8-byte Folded Spill
+; CHECK-GI-NEXT: stp x30, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-GI-NEXT: .cfi_def_cfa_offset 48
+; CHECK-GI-NEXT: .cfi_offset w19, -8
+; CHECK-GI-NEXT: .cfi_offset w30, -16
+; CHECK-GI-NEXT: .cfi_offset b8, -32
+; CHECK-GI-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-GI-NEXT: mov s8, v0.s[1]
+; CHECK-GI-NEXT: mov w19, w0
+; CHECK-GI-NEXT: // kill: def $s0 killed $s0 killed $q0
+; CHECK-GI-NEXT: bl __powisf2
+; CHECK-GI-NEXT: str d0, [sp] // 16-byte Folded Spill
+; CHECK-GI-NEXT: fmov s0, s8
+; CHECK-GI-NEXT: mov w0, w19
+; CHECK-GI-NEXT: bl __powisf2
+; CHECK-GI-NEXT: ldr q1, [sp] // 16-byte Folded Reload
+; CHECK-GI-NEXT: // kill: def $s0 killed $s0 def $q0
+; CHECK-GI-NEXT: ldp x30, x19, [sp, #32] // 16-byte Folded Reload
+; CHECK-GI-NEXT: ldr d8, [sp, #16] // 8-byte Folded Reload
+; CHECK-GI-NEXT: mov v1.s[1], v0.s[0]
+; CHECK-GI-NEXT: fmov d0, d1
+; CHECK-GI-NEXT: add sp, sp, #48
+; CHECK-GI-NEXT: ret
+entry:
+ %c = call <2 x float> @llvm.powi.v2f32.i32(<2 x float> %a, i32 %b)
+ ret <2 x float> %c
+}
+
+define <3 x float> @powi_v3f32(<3 x float> %a, i32 %b) {
+; CHECK-SD-LABEL: powi_v3f32:
+; CHECK-SD: // %bb.0: // %entry
+; CHECK-SD-NEXT: sub sp, sp, #48
+; CHECK-SD-NEXT: stp x30, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-SD-NEXT: .cfi_def_cfa_offset 48
+; CHECK-SD-NEXT: .cfi_offset w19, -8
+; CHECK-SD-NEXT: .cfi_offset w30, -16
+; CHECK-SD-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
+; CHECK-SD-NEXT: mov s0, v0.s[1]
+; CHECK-SD-NEXT: mov w19, w0
+; CHECK-SD-NEXT: bl __powisf2
+; CHECK-SD-NEXT: str d0, [sp] // 16-byte Folded Spill
+; CHECK-SD-NEXT: ldr q0, [sp, #16] // 16-byte Folded Reload
+; CHECK-SD-NEXT: mov w0, w19
+; CHECK-SD-NEXT: // kill: def $s0 killed $s0 killed $q0
+; CHECK-SD-NEXT: bl __powisf2
+; CHECK-SD-NEXT: ldr q1, [sp] // 16-byte Folded Reload
+; CHECK-SD-NEXT: // kill: def $s0 killed $s0 def $q0
+; CHECK-SD-NEXT: mov w0, w19
+; CHECK-SD-NEXT: mov v0.s[1], v1.s[0]
+; CHECK-SD-NEXT: str q0, [sp] // 16-byte Folded Spill
+; CHECK-SD-NEXT: ldr q0, [sp, #16] // 16-byte Folded Reload
+; CHECK-SD-NEXT: mov s0, v0.s[2]
+; CHECK-SD-NEXT: bl __powisf2
+; CHECK-SD-NEXT: ldr q1, [sp] // 16-byte Folded Reload
+; CHECK-SD-NEXT: // kill: def $s0 killed $s0 def $q0
+; CHECK-SD-NEXT: ldp x30, x19, [sp, #32] // 16-byte Folded Reload
+; CHECK-SD-NEXT: mov v1.s[2], v0.s[0]
+; CHECK-SD-NEXT: mov v0.16b, v1.16b
+; CHECK-SD-NEXT: add sp, sp, #48
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: powi_v3f32:
+; CHECK-GI: // %bb.0: // %entry
+; CHECK-GI-NEXT: sub sp, sp, #64
+; CHECK-GI-NEXT: stp d9, d8, [sp, #32] // 16-byte Folded Spill
+; CHECK-GI-NEXT: stp x30, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK-GI-NEXT: .cfi_def_cfa_offset 64
+; CHECK-GI-NEXT: .cfi_offset w19, -8
+; CHECK-GI-NEXT: .cfi_offset w30, -16
+; CHECK-GI-NEXT: .cfi_offset b8, -24
+; CHECK-GI-NEXT: .cfi_offset b9, -32
+; CHECK-GI-NEXT: mov s8, v0.s[1]
+; CHECK-GI-NEXT: mov s9, v0.s[2]
+; CHECK-GI-NEXT: mov w19, w0
+; CHECK-GI-NEXT: // kill: def $s0 killed $s0 killed $q0
+; CHECK-GI-NEXT: bl __powisf2
+; CHECK-GI-NEXT: str d0, [sp, #16] // 16-byte Folded Spill
+; CHECK-GI-NEXT: fmov s0, s8
+; CHECK-GI-NEXT: mov w0, w19
+; CHECK-GI-NEXT: bl __powisf2
+; CHECK-GI-NEXT: str d0, [sp] // 16-byte Folded Spill
+; CHECK-GI-NEXT: fmov s0, s9
+; CHECK-GI-NEXT: mov w0, w19
+; CHECK-GI-NEXT: bl __powisf2
+; CHECK-GI-NEXT: ldp q2, q1, [sp] // 32-byte Folded Reload
+; CHECK-GI-NEXT: // kill: def $s0 killed $s0 def $q0
+; CHECK-GI-NEXT: ldp x30, x19, [sp, #48] // 16-byte Folded Reload
+; CHECK-GI-NEXT: ldp d9, d8, [sp, #32] // 16-byte Folded Reload
+; CHECK-GI-NEXT: mov v1.s[1], v2.s[0]
+; CHECK-GI-NEXT: mov v1.s[2], v0.s[0]
+; CHECK-GI-NEXT: mov v1.s[3], v0.s[0]
+; CHECK-GI-NEXT: mov v0.16b, v1.16b
+; CHECK-GI-NEXT: add sp, sp, #64
+; CHECK-GI-NEXT: ret
+entry:
+ %c = call <3 x float> @llvm.powi.v3f32.i32(<3 x float> %a, i32 %b)
+ ret <3 x float> %c
+}
+
+define <4 x float> @powi_v4f32(<4 x float> %a, i32 %b) {
+; CHECK-SD-LABEL: powi_v4f32:
+; CHECK-SD: // %bb.0: // %entry
+; CHECK-SD-NEXT: sub sp, sp, #48
+; CHECK-SD-NEXT: stp x30, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-SD-NEXT: .cfi_def_cfa_offset 48
+; CHECK-SD-NEXT: .cfi_offset w19, -8
+; CHECK-SD-NEXT: .cfi_offset ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/67114
More information about the llvm-commits
mailing list