Skip to content

[GISel][AArch64] Libcall support for G_FPEXT 128-bit types #97735

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 1 commit into from
Jul 10, 2024
Merged

[GISel][AArch64] Libcall support for G_FPEXT 128-bit types #97735

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 1 addition & 0 deletions llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -656,6 +656,7 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST)
getActionDefinitionsBuilder(G_FPEXT)
.legalFor(
{{s32, s16}, {s64, s16}, {s64, s32}, {v4s32, v4s16}, {v2s64, v2s32}})
.libcallFor({{s128, s64}, {s128, s32}, {s128, s16}})
.clampNumElements(0, v4s32, v4s32)
.clampNumElements(0, v2s64, v2s64)
.scalarize(0);
Expand Down
235 changes: 235 additions & 0 deletions llvm/test/CodeGen/AArch64/fpext.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,33 @@ entry:
ret float %c
}

define fp128 @fpext_f16_f128(half %a) {
; CHECK-LABEL: fpext_f16_f128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: b __extendhftf2
entry:
%c = fpext half %a to fp128
ret fp128 %c
}

define fp128 @fpext_f32_f128(float %a) {
; CHECK-LABEL: fpext_f32_f128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: b __extendsftf2
entry:
%c = fpext float %a to fp128
ret fp128 %c
}

define fp128 @fpext_f64_f128(double %a) {
; CHECK-LABEL: fpext_f64_f128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: b __extenddftf2
entry:
%c = fpext double %a to fp128
ret fp128 %c
}

define <2 x double> @fpext_v2f32_v2f64(<2 x float> %a) {
; CHECK-LABEL: fpext_v2f32_v2f64:
; CHECK: // %bb.0: // %entry
Expand Down Expand Up @@ -66,6 +93,214 @@ entry:
ret <3 x double> %c
}

define <4 x fp128> @fpext_v4f16_v4f128(<4 x half> %a) {
; CHECK-SD-LABEL: fpext_v4f16_v4f128:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: sub sp, sp, #64
; CHECK-SD-NEXT: str x30, [sp, #48] // 8-byte Folded Spill
; CHECK-SD-NEXT: .cfi_def_cfa_offset 64
; CHECK-SD-NEXT: .cfi_offset w30, -16
; CHECK-SD-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-SD-NEXT: str q0, [sp, #32] // 16-byte Folded Spill
; CHECK-SD-NEXT: // kill: def $h0 killed $h0 killed $q0
; CHECK-SD-NEXT: bl __extendhftf2
; CHECK-SD-NEXT: ldr q1, [sp, #32] // 16-byte Folded Reload
; CHECK-SD-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
; CHECK-SD-NEXT: mov h1, v1.h[1]
; CHECK-SD-NEXT: fmov s0, s1
; CHECK-SD-NEXT: bl __extendhftf2
; CHECK-SD-NEXT: ldr q1, [sp, #32] // 16-byte Folded Reload
; CHECK-SD-NEXT: str q0, [sp] // 16-byte Folded Spill
; CHECK-SD-NEXT: mov h1, v1.h[2]
; CHECK-SD-NEXT: fmov s0, s1
; CHECK-SD-NEXT: bl __extendhftf2
; CHECK-SD-NEXT: ldr q1, [sp, #32] // 16-byte Folded Reload
; CHECK-SD-NEXT: str q0, [sp, #32] // 16-byte Folded Spill
; CHECK-SD-NEXT: mov h1, v1.h[3]
; CHECK-SD-NEXT: fmov s0, s1
; CHECK-SD-NEXT: bl __extendhftf2
; CHECK-SD-NEXT: mov v3.16b, v0.16b
; CHECK-SD-NEXT: ldp q1, q0, [sp] // 32-byte Folded Reload
; CHECK-SD-NEXT: ldr q2, [sp, #32] // 16-byte Folded Reload
; CHECK-SD-NEXT: ldr x30, [sp, #48] // 8-byte Folded Reload
; CHECK-SD-NEXT: add sp, sp, #64
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: fpext_v4f16_v4f128:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: sub sp, sp, #80
; CHECK-GI-NEXT: str d10, [sp, #48] // 8-byte Folded Spill
; CHECK-GI-NEXT: stp d9, d8, [sp, #56] // 16-byte Folded Spill
; CHECK-GI-NEXT: str x30, [sp, #72] // 8-byte Folded Spill
; CHECK-GI-NEXT: .cfi_def_cfa_offset 80
; CHECK-GI-NEXT: .cfi_offset w30, -8
; CHECK-GI-NEXT: .cfi_offset b8, -16
; CHECK-GI-NEXT: .cfi_offset b9, -24
; CHECK-GI-NEXT: .cfi_offset b10, -32
; CHECK-GI-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-GI-NEXT: mov h8, v0.h[1]
; CHECK-GI-NEXT: mov h9, v0.h[2]
; CHECK-GI-NEXT: mov h10, v0.h[3]
; CHECK-GI-NEXT: // kill: def $h0 killed $h0 killed $q0
; CHECK-GI-NEXT: bl __extendhftf2
; CHECK-GI-NEXT: str q0, [sp, #32] // 16-byte Folded Spill
; CHECK-GI-NEXT: fmov s0, s8
; CHECK-GI-NEXT: bl __extendhftf2
; CHECK-GI-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
; CHECK-GI-NEXT: fmov s0, s9
; CHECK-GI-NEXT: bl __extendhftf2
; CHECK-GI-NEXT: str q0, [sp] // 16-byte Folded Spill
; CHECK-GI-NEXT: fmov s0, s10
; CHECK-GI-NEXT: bl __extendhftf2
; CHECK-GI-NEXT: mov v3.16b, v0.16b
; CHECK-GI-NEXT: ldp q1, q0, [sp, #16] // 32-byte Folded Reload
; CHECK-GI-NEXT: ldp d9, d8, [sp, #56] // 16-byte Folded Reload
; CHECK-GI-NEXT: ldr q2, [sp] // 16-byte Folded Reload
; CHECK-GI-NEXT: ldr x30, [sp, #72] // 8-byte Folded Reload
; CHECK-GI-NEXT: ldr d10, [sp, #48] // 8-byte Folded Reload
; CHECK-GI-NEXT: add sp, sp, #80
; CHECK-GI-NEXT: ret
entry:
%c = fpext <4 x half> %a to <4 x fp128>
ret <4 x fp128> %c
}

define <4 x fp128> @fpext_v4f32_v4f128(<4 x float> %a) {
; CHECK-SD-LABEL: fpext_v4f32_v4f128:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: sub sp, sp, #80
; CHECK-SD-NEXT: str x30, [sp, #64] // 8-byte Folded Spill
; CHECK-SD-NEXT: .cfi_def_cfa_offset 80
; CHECK-SD-NEXT: .cfi_offset w30, -16
; CHECK-SD-NEXT: str q0, [sp, #48] // 16-byte Folded Spill
; CHECK-SD-NEXT: ext v0.16b, v0.16b, v0.16b, #8
; CHECK-SD-NEXT: str q0, [sp, #32] // 16-byte Folded Spill
; CHECK-SD-NEXT: // kill: def $s0 killed $s0 killed $q0
; CHECK-SD-NEXT: bl __extendsftf2
; CHECK-SD-NEXT: ldr q1, [sp, #32] // 16-byte Folded Reload
; CHECK-SD-NEXT: str q0, [sp, #32] // 16-byte Folded Spill
; CHECK-SD-NEXT: mov s1, v1.s[1]
; CHECK-SD-NEXT: fmov s0, s1
; CHECK-SD-NEXT: bl __extendsftf2
; CHECK-SD-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
; CHECK-SD-NEXT: ldr q0, [sp, #48] // 16-byte Folded Reload
; CHECK-SD-NEXT: // kill: def $s0 killed $s0 killed $q0
; CHECK-SD-NEXT: bl __extendsftf2
; CHECK-SD-NEXT: str q0, [sp] // 16-byte Folded Spill
; CHECK-SD-NEXT: ldr q0, [sp, #48] // 16-byte Folded Reload
; CHECK-SD-NEXT: mov s0, v0.s[1]
; CHECK-SD-NEXT: bl __extendsftf2
; CHECK-SD-NEXT: mov v1.16b, v0.16b
; CHECK-SD-NEXT: ldp q0, q3, [sp] // 32-byte Folded Reload
; CHECK-SD-NEXT: ldr q2, [sp, #32] // 16-byte Folded Reload
; CHECK-SD-NEXT: ldr x30, [sp, #64] // 8-byte Folded Reload
; CHECK-SD-NEXT: add sp, sp, #80
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: fpext_v4f32_v4f128:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: sub sp, sp, #80
; CHECK-GI-NEXT: str d10, [sp, #48] // 8-byte Folded Spill
; CHECK-GI-NEXT: stp d9, d8, [sp, #56] // 16-byte Folded Spill
; CHECK-GI-NEXT: str x30, [sp, #72] // 8-byte Folded Spill
; CHECK-GI-NEXT: .cfi_def_cfa_offset 80
; CHECK-GI-NEXT: .cfi_offset w30, -8
; CHECK-GI-NEXT: .cfi_offset b8, -16
; CHECK-GI-NEXT: .cfi_offset b9, -24
; CHECK-GI-NEXT: .cfi_offset b10, -32
; CHECK-GI-NEXT: mov s8, v0.s[1]
; CHECK-GI-NEXT: mov s9, v0.s[2]
; CHECK-GI-NEXT: mov s10, v0.s[3]
; CHECK-GI-NEXT: // kill: def $s0 killed $s0 killed $q0
; CHECK-GI-NEXT: bl __extendsftf2
; CHECK-GI-NEXT: str q0, [sp, #32] // 16-byte Folded Spill
; CHECK-GI-NEXT: fmov s0, s8
; CHECK-GI-NEXT: bl __extendsftf2
; CHECK-GI-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
; CHECK-GI-NEXT: fmov s0, s9
; CHECK-GI-NEXT: bl __extendsftf2
; CHECK-GI-NEXT: str q0, [sp] // 16-byte Folded Spill
; CHECK-GI-NEXT: fmov s0, s10
; CHECK-GI-NEXT: bl __extendsftf2
; CHECK-GI-NEXT: mov v3.16b, v0.16b
; CHECK-GI-NEXT: ldp q1, q0, [sp, #16] // 32-byte Folded Reload
; CHECK-GI-NEXT: ldp d9, d8, [sp, #56] // 16-byte Folded Reload
; CHECK-GI-NEXT: ldr q2, [sp] // 16-byte Folded Reload
; CHECK-GI-NEXT: ldr x30, [sp, #72] // 8-byte Folded Reload
; CHECK-GI-NEXT: ldr d10, [sp, #48] // 8-byte Folded Reload
; CHECK-GI-NEXT: add sp, sp, #80
; CHECK-GI-NEXT: ret
entry:
%c = fpext <4 x float> %a to <4 x fp128>
ret <4 x fp128> %c
}

define <4 x fp128> @fpext_v4f64_v4f128(<4 x double> %a) {
; CHECK-SD-LABEL: fpext_v4f64_v4f128:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: sub sp, sp, #80
; CHECK-SD-NEXT: str x30, [sp, #64] // 8-byte Folded Spill
; CHECK-SD-NEXT: .cfi_def_cfa_offset 80
; CHECK-SD-NEXT: .cfi_offset w30, -16
; CHECK-SD-NEXT: str q1, [sp, #48] // 16-byte Folded Spill
; CHECK-SD-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
; CHECK-SD-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-SD-NEXT: bl __extenddftf2
; CHECK-SD-NEXT: str q0, [sp, #32] // 16-byte Folded Spill
; CHECK-SD-NEXT: ldr q0, [sp, #16] // 16-byte Folded Reload
; CHECK-SD-NEXT: mov d0, v0.d[1]
; CHECK-SD-NEXT: bl __extenddftf2
; CHECK-SD-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
; CHECK-SD-NEXT: ldr q0, [sp, #48] // 16-byte Folded Reload
; CHECK-SD-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-SD-NEXT: bl __extenddftf2
; CHECK-SD-NEXT: str q0, [sp] // 16-byte Folded Spill
; CHECK-SD-NEXT: ldr q0, [sp, #48] // 16-byte Folded Reload
; CHECK-SD-NEXT: mov d0, v0.d[1]
; CHECK-SD-NEXT: bl __extenddftf2
; CHECK-SD-NEXT: mov v3.16b, v0.16b
; CHECK-SD-NEXT: ldp q1, q0, [sp, #16] // 32-byte Folded Reload
; CHECK-SD-NEXT: ldr q2, [sp] // 16-byte Folded Reload
; CHECK-SD-NEXT: ldr x30, [sp, #64] // 8-byte Folded Reload
; CHECK-SD-NEXT: add sp, sp, #80
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: fpext_v4f64_v4f128:
; 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: str x30, [sp, #64] // 8-byte Folded Spill
; CHECK-GI-NEXT: .cfi_def_cfa_offset 80
; 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: // kill: def $d0 killed $d0 killed $q0
; CHECK-GI-NEXT: bl __extenddftf2
; CHECK-GI-NEXT: str q0, [sp, #32] // 16-byte Folded Spill
; CHECK-GI-NEXT: fmov d0, d8
; CHECK-GI-NEXT: bl __extenddftf2
; CHECK-GI-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
; CHECK-GI-NEXT: ldr q0, [sp] // 16-byte Folded Reload
; CHECK-GI-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-GI-NEXT: bl __extenddftf2
; CHECK-GI-NEXT: str q0, [sp] // 16-byte Folded Spill
; CHECK-GI-NEXT: fmov d0, d9
; CHECK-GI-NEXT: bl __extenddftf2
; CHECK-GI-NEXT: mov v3.16b, v0.16b
; CHECK-GI-NEXT: ldp q1, q0, [sp, #16] // 32-byte Folded Reload
; CHECK-GI-NEXT: ldp d9, d8, [sp, #48] // 16-byte Folded Reload
; CHECK-GI-NEXT: ldr q2, [sp] // 16-byte Folded Reload
; CHECK-GI-NEXT: ldr x30, [sp, #64] // 8-byte Folded Reload
; CHECK-GI-NEXT: add sp, sp, #80
; CHECK-GI-NEXT: ret
entry:
%c = fpext <4 x double> %a to <4 x fp128>
ret <4 x fp128> %c
}

define <4 x double> @fpext_v4f32_v4f64(<4 x float> %a) {
; CHECK-SD-LABEL: fpext_v4f32_v4f64:
; CHECK-SD: // %bb.0: // %entry
Expand Down
Loading