[llvm] Change `half` to use soft promotion rather than `PromoteFloat` (PR #152727)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Aug 8 07:10:53 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-sparc
Author: Trevor Gross (tgross35)
<details>
<summary>Changes</summary>
`half` currently uses the default legalization of promoting to a `f32`; however, this implementation implements math in a way that results in incorrect rounding. Switch to the soft promote implementation, which does not have this problem.
The SPARC ABI does not specify a `_Float16` type, so there is no concern with keeping interface compatibility.
Fixes the SPARC portion of [1].
[1]: https://github.com/llvm/llvm-project/issues/97975
---
Patch is 50.77 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/152727.diff
4 Files Affected:
- (modified) llvm/lib/Target/Sparc/SparcISelLowering.h (+2)
- (modified) llvm/test/CodeGen/SPARC/fp16-promote.ll (+36-28)
- (added) llvm/test/CodeGen/SPARC/half.ll (+805)
- (modified) llvm/test/CodeGen/SPARC/llvm.sincos.ll (+187-148)
``````````diff
diff --git a/llvm/lib/Target/Sparc/SparcISelLowering.h b/llvm/lib/Target/Sparc/SparcISelLowering.h
index 0d220f8c3d32e..3a6aaf929707d 100644
--- a/llvm/lib/Target/Sparc/SparcISelLowering.h
+++ b/llvm/lib/Target/Sparc/SparcISelLowering.h
@@ -28,6 +28,8 @@ namespace llvm {
bool useSoftFloat() const override;
+ bool softPromoteHalfType() const override { return true; }
+
/// computeKnownBitsForTargetNode - Determine which of the bits specified
/// in Mask are known to be either zero or one and return them in the
/// KnownZero/KnownOne bitsets.
diff --git a/llvm/test/CodeGen/SPARC/fp16-promote.ll b/llvm/test/CodeGen/SPARC/fp16-promote.ll
index efe67b04e8fb3..64873b744de50 100644
--- a/llvm/test/CodeGen/SPARC/fp16-promote.ll
+++ b/llvm/test/CodeGen/SPARC/fp16-promote.ll
@@ -329,13 +329,14 @@ define void @test_fadd(ptr %p, ptr %q) nounwind {
; V8-OPT-LABEL: test_fadd:
; V8-OPT: ! %bb.0:
; V8-OPT-NEXT: save %sp, -104, %sp
+; V8-OPT-NEXT: lduh [%i0], %i2
; V8-OPT-NEXT: call __extendhfsf2
-; V8-OPT-NEXT: lduh [%i0], %o0
+; V8-OPT-NEXT: lduh [%i1], %o0
; V8-OPT-NEXT: st %f0, [%fp+-8] ! 4-byte Folded Spill
; V8-OPT-NEXT: call __extendhfsf2
-; V8-OPT-NEXT: lduh [%i1], %o0
+; V8-OPT-NEXT: mov %i2, %o0
; V8-OPT-NEXT: ld [%fp+-8], %f1 ! 4-byte Folded Reload
-; V8-OPT-NEXT: fadds %f1, %f0, %f0
+; V8-OPT-NEXT: fadds %f0, %f1, %f0
; V8-OPT-NEXT: st %f0, [%fp+-4]
; V8-OPT-NEXT: call __truncsfhf2
; V8-OPT-NEXT: ld [%fp+-4], %o0
@@ -346,13 +347,14 @@ define void @test_fadd(ptr %p, ptr %q) nounwind {
; V8-UNOPT-LABEL: test_fadd:
; V8-UNOPT: ! %bb.0:
; V8-UNOPT-NEXT: save %sp, -104, %sp
-; V8-UNOPT-NEXT: call __extendhfsf2
-; V8-UNOPT-NEXT: lduh [%i0], %o0
-; V8-UNOPT-NEXT: st %f0, [%fp+-8] ! 4-byte Folded Spill
+; V8-UNOPT-NEXT: lduh [%i0], %i2
+; V8-UNOPT-NEXT: st %i2, [%fp+-12] ! 4-byte Folded Spill
; V8-UNOPT-NEXT: call __extendhfsf2
; V8-UNOPT-NEXT: lduh [%i1], %o0
-; V8-UNOPT-NEXT: fmovs %f0, %f1
-; V8-UNOPT-NEXT: ld [%fp+-8], %f0 ! 4-byte Folded Reload
+; V8-UNOPT-NEXT: ld [%fp+-12], %o0 ! 4-byte Folded Reload
+; V8-UNOPT-NEXT: call __extendhfsf2
+; V8-UNOPT-NEXT: st %f0, [%fp+-8]
+; V8-UNOPT-NEXT: ld [%fp+-8], %f1 ! 4-byte Folded Reload
; V8-UNOPT-NEXT: fadds %f0, %f1, %f0
; V8-UNOPT-NEXT: st %f0, [%fp+-4]
; V8-UNOPT-NEXT: call __truncsfhf2
@@ -364,13 +366,14 @@ define void @test_fadd(ptr %p, ptr %q) nounwind {
; V9-LABEL: test_fadd:
; V9: ! %bb.0:
; V9-NEXT: save %sp, -104, %sp
+; V9-NEXT: lduh [%i0], %i2
; V9-NEXT: call __extendhfsf2
-; V9-NEXT: lduh [%i0], %o0
+; V9-NEXT: lduh [%i1], %o0
; V9-NEXT: st %f0, [%fp+-8] ! 4-byte Folded Spill
; V9-NEXT: call __extendhfsf2
-; V9-NEXT: lduh [%i1], %o0
+; V9-NEXT: mov %i2, %o0
; V9-NEXT: ld [%fp+-8], %f1 ! 4-byte Folded Reload
-; V9-NEXT: fadds %f1, %f0, %f0
+; V9-NEXT: fadds %f0, %f1, %f0
; V9-NEXT: st %f0, [%fp+-4]
; V9-NEXT: call __truncsfhf2
; V9-NEXT: ld [%fp+-4], %o0
@@ -381,14 +384,15 @@ define void @test_fadd(ptr %p, ptr %q) nounwind {
; SPARC64-LABEL: test_fadd:
; SPARC64: ! %bb.0:
; SPARC64-NEXT: save %sp, -192, %sp
+; SPARC64-NEXT: lduh [%i0], %i2
; SPARC64-NEXT: call __extendhfsf2
-; SPARC64-NEXT: lduh [%i0], %o0
+; SPARC64-NEXT: lduh [%i1], %o0
; SPARC64-NEXT: st %f0, [%fp+2043] ! 4-byte Folded Spill
; SPARC64-NEXT: call __extendhfsf2
-; SPARC64-NEXT: lduh [%i1], %o0
+; SPARC64-NEXT: mov %i2, %o0
; SPARC64-NEXT: ld [%fp+2043], %f1 ! 4-byte Folded Reload
; SPARC64-NEXT: call __truncsfhf2
-; SPARC64-NEXT: fadds %f1, %f0, %f1
+; SPARC64-NEXT: fadds %f0, %f1, %f1
; SPARC64-NEXT: sth %o0, [%i0]
; SPARC64-NEXT: ret
; SPARC64-NEXT: restore
@@ -403,13 +407,14 @@ define void @test_fmul(ptr %p, ptr %q) nounwind {
; V8-OPT-LABEL: test_fmul:
; V8-OPT: ! %bb.0:
; V8-OPT-NEXT: save %sp, -104, %sp
+; V8-OPT-NEXT: lduh [%i0], %i2
; V8-OPT-NEXT: call __extendhfsf2
-; V8-OPT-NEXT: lduh [%i0], %o0
+; V8-OPT-NEXT: lduh [%i1], %o0
; V8-OPT-NEXT: st %f0, [%fp+-8] ! 4-byte Folded Spill
; V8-OPT-NEXT: call __extendhfsf2
-; V8-OPT-NEXT: lduh [%i1], %o0
+; V8-OPT-NEXT: mov %i2, %o0
; V8-OPT-NEXT: ld [%fp+-8], %f1 ! 4-byte Folded Reload
-; V8-OPT-NEXT: fmuls %f1, %f0, %f0
+; V8-OPT-NEXT: fmuls %f0, %f1, %f0
; V8-OPT-NEXT: st %f0, [%fp+-4]
; V8-OPT-NEXT: call __truncsfhf2
; V8-OPT-NEXT: ld [%fp+-4], %o0
@@ -420,13 +425,14 @@ define void @test_fmul(ptr %p, ptr %q) nounwind {
; V8-UNOPT-LABEL: test_fmul:
; V8-UNOPT: ! %bb.0:
; V8-UNOPT-NEXT: save %sp, -104, %sp
-; V8-UNOPT-NEXT: call __extendhfsf2
-; V8-UNOPT-NEXT: lduh [%i0], %o0
-; V8-UNOPT-NEXT: st %f0, [%fp+-8] ! 4-byte Folded Spill
+; V8-UNOPT-NEXT: lduh [%i0], %i2
+; V8-UNOPT-NEXT: st %i2, [%fp+-12] ! 4-byte Folded Spill
; V8-UNOPT-NEXT: call __extendhfsf2
; V8-UNOPT-NEXT: lduh [%i1], %o0
-; V8-UNOPT-NEXT: fmovs %f0, %f1
-; V8-UNOPT-NEXT: ld [%fp+-8], %f0 ! 4-byte Folded Reload
+; V8-UNOPT-NEXT: ld [%fp+-12], %o0 ! 4-byte Folded Reload
+; V8-UNOPT-NEXT: call __extendhfsf2
+; V8-UNOPT-NEXT: st %f0, [%fp+-8]
+; V8-UNOPT-NEXT: ld [%fp+-8], %f1 ! 4-byte Folded Reload
; V8-UNOPT-NEXT: fmuls %f0, %f1, %f0
; V8-UNOPT-NEXT: st %f0, [%fp+-4]
; V8-UNOPT-NEXT: call __truncsfhf2
@@ -438,13 +444,14 @@ define void @test_fmul(ptr %p, ptr %q) nounwind {
; V9-LABEL: test_fmul:
; V9: ! %bb.0:
; V9-NEXT: save %sp, -104, %sp
+; V9-NEXT: lduh [%i0], %i2
; V9-NEXT: call __extendhfsf2
-; V9-NEXT: lduh [%i0], %o0
+; V9-NEXT: lduh [%i1], %o0
; V9-NEXT: st %f0, [%fp+-8] ! 4-byte Folded Spill
; V9-NEXT: call __extendhfsf2
-; V9-NEXT: lduh [%i1], %o0
+; V9-NEXT: mov %i2, %o0
; V9-NEXT: ld [%fp+-8], %f1 ! 4-byte Folded Reload
-; V9-NEXT: fmuls %f1, %f0, %f0
+; V9-NEXT: fmuls %f0, %f1, %f0
; V9-NEXT: st %f0, [%fp+-4]
; V9-NEXT: call __truncsfhf2
; V9-NEXT: ld [%fp+-4], %o0
@@ -455,14 +462,15 @@ define void @test_fmul(ptr %p, ptr %q) nounwind {
; SPARC64-LABEL: test_fmul:
; SPARC64: ! %bb.0:
; SPARC64-NEXT: save %sp, -192, %sp
+; SPARC64-NEXT: lduh [%i0], %i2
; SPARC64-NEXT: call __extendhfsf2
-; SPARC64-NEXT: lduh [%i0], %o0
+; SPARC64-NEXT: lduh [%i1], %o0
; SPARC64-NEXT: st %f0, [%fp+2043] ! 4-byte Folded Spill
; SPARC64-NEXT: call __extendhfsf2
-; SPARC64-NEXT: lduh [%i1], %o0
+; SPARC64-NEXT: mov %i2, %o0
; SPARC64-NEXT: ld [%fp+2043], %f1 ! 4-byte Folded Reload
; SPARC64-NEXT: call __truncsfhf2
-; SPARC64-NEXT: fmuls %f1, %f0, %f1
+; SPARC64-NEXT: fmuls %f0, %f1, %f1
; SPARC64-NEXT: sth %o0, [%i0]
; SPARC64-NEXT: ret
; SPARC64-NEXT: restore
diff --git a/llvm/test/CodeGen/SPARC/half.ll b/llvm/test/CodeGen/SPARC/half.ll
new file mode 100644
index 0000000000000..5db5176fe39cd
--- /dev/null
+++ b/llvm/test/CodeGen/SPARC/half.ll
@@ -0,0 +1,805 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+
+; RUN: llc %s -o - -mtriple=sparc-unknown-linux-gnu | FileCheck %s --check-prefixes=SPARC32
+; RUN: llc %s -o - -mtriple=sparc64-unknown-linux-gnu | FileCheck %s --check-prefixes=SPARC64
+
+; Tests for various operations on half precison float. Much of the test is
+; copied from test/CodeGen/X86/half.ll.
+
+define void @store(half %x, ptr %p) nounwind {
+; SPARC32-LABEL: store:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: retl
+; SPARC32-NEXT: sth %o0, [%o1]
+;
+; SPARC64-LABEL: store:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: retl
+; SPARC64-NEXT: sth %o0, [%o1]
+ store half %x, ptr %p
+ ret void
+}
+
+define half @return(ptr %p) nounwind {
+; SPARC32-LABEL: return:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: retl
+; SPARC32-NEXT: lduh [%o0], %o0
+;
+; SPARC64-LABEL: return:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: retl
+; SPARC64-NEXT: lduh [%o0], %o0
+ %r = load half, ptr %p
+ ret half %r
+}
+
+define dso_local double @loadd(ptr nocapture readonly %a) local_unnamed_addr nounwind {
+; SPARC32-LABEL: loadd:
+; SPARC32: ! %bb.0: ! %entry
+; SPARC32-NEXT: save %sp, -96, %sp
+; SPARC32-NEXT: call __extendhfsf2
+; SPARC32-NEXT: lduh [%i0+2], %o0
+; SPARC32-NEXT: fstod %f0, %f0
+; SPARC32-NEXT: ret
+; SPARC32-NEXT: restore
+;
+; SPARC64-LABEL: loadd:
+; SPARC64: ! %bb.0: ! %entry
+; SPARC64-NEXT: save %sp, -176, %sp
+; SPARC64-NEXT: call __extendhfsf2
+; SPARC64-NEXT: lduh [%i0+2], %o0
+; SPARC64-NEXT: fstod %f0, %f0
+; SPARC64-NEXT: ret
+; SPARC64-NEXT: restore
+entry:
+ %arrayidx = getelementptr inbounds i16, ptr %a, i64 1
+ %0 = load i16, ptr %arrayidx, align 2
+ %1 = tail call double @llvm.convert.from.fp16.f64(i16 %0)
+ ret double %1
+}
+
+define dso_local float @loadf(ptr nocapture readonly %a) local_unnamed_addr nounwind {
+; SPARC32-LABEL: loadf:
+; SPARC32: ! %bb.0: ! %entry
+; SPARC32-NEXT: save %sp, -96, %sp
+; SPARC32-NEXT: call __extendhfsf2
+; SPARC32-NEXT: lduh [%i0+2], %o0
+; SPARC32-NEXT: ret
+; SPARC32-NEXT: restore
+;
+; SPARC64-LABEL: loadf:
+; SPARC64: ! %bb.0: ! %entry
+; SPARC64-NEXT: save %sp, -176, %sp
+; SPARC64-NEXT: call __extendhfsf2
+; SPARC64-NEXT: lduh [%i0+2], %o0
+; SPARC64-NEXT: ret
+; SPARC64-NEXT: restore
+entry:
+ %arrayidx = getelementptr inbounds i16, ptr %a, i64 1
+ %0 = load i16, ptr %arrayidx, align 2
+ %1 = tail call float @llvm.convert.from.fp16.f32(i16 %0)
+ ret float %1
+}
+
+define dso_local void @stored(ptr nocapture %a, double %b) local_unnamed_addr nounwind {
+; SPARC32-LABEL: stored:
+; SPARC32: ! %bb.0: ! %entry
+; SPARC32-NEXT: save %sp, -112, %sp
+; SPARC32-NEXT: mov %i2, %i3
+; SPARC32-NEXT: mov %i1, %i2
+; SPARC32-NEXT: std %i2, [%fp+-8]
+; SPARC32-NEXT: ldd [%fp+-8], %f0
+; SPARC32-NEXT: std %f0, [%fp+-16]
+; SPARC32-NEXT: call __truncdfhf2
+; SPARC32-NEXT: ldd [%fp+-16], %o0
+; SPARC32-NEXT: sth %o0, [%i0]
+; SPARC32-NEXT: ret
+; SPARC32-NEXT: restore
+;
+; SPARC64-LABEL: stored:
+; SPARC64: ! %bb.0: ! %entry
+; SPARC64-NEXT: save %sp, -176, %sp
+; SPARC64-NEXT: fmovd %f2, %f0
+; SPARC64-NEXT: call __truncdfhf2
+; SPARC64-NEXT: nop
+; SPARC64-NEXT: sth %o0, [%i0]
+; SPARC64-NEXT: ret
+; SPARC64-NEXT: restore
+entry:
+ %0 = tail call i16 @llvm.convert.to.fp16.f64(double %b)
+ store i16 %0, ptr %a, align 2
+ ret void
+}
+
+define dso_local void @storef(ptr nocapture %a, float %b) local_unnamed_addr nounwind {
+; SPARC32-LABEL: storef:
+; SPARC32: ! %bb.0: ! %entry
+; SPARC32-NEXT: save %sp, -96, %sp
+; SPARC32-NEXT: call __truncsfhf2
+; SPARC32-NEXT: mov %i1, %o0
+; SPARC32-NEXT: sth %o0, [%i0]
+; SPARC32-NEXT: ret
+; SPARC32-NEXT: restore
+;
+; SPARC64-LABEL: storef:
+; SPARC64: ! %bb.0: ! %entry
+; SPARC64-NEXT: save %sp, -176, %sp
+; SPARC64-NEXT: fmovs %f3, %f1
+; SPARC64-NEXT: call __truncsfhf2
+; SPARC64-NEXT: nop
+; SPARC64-NEXT: sth %o0, [%i0]
+; SPARC64-NEXT: ret
+; SPARC64-NEXT: restore
+entry:
+ %0 = tail call i16 @llvm.convert.to.fp16.f32(float %b)
+ store i16 %0, ptr %a, align 2
+ ret void
+}
+
+define void @test_load_store(ptr %in, ptr %out) nounwind {
+; SPARC32-LABEL: test_load_store:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: lduh [%o0], %o0
+; SPARC32-NEXT: retl
+; SPARC32-NEXT: sth %o0, [%o1]
+;
+; SPARC64-LABEL: test_load_store:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: lduh [%o0], %o0
+; SPARC64-NEXT: retl
+; SPARC64-NEXT: sth %o0, [%o1]
+ %val = load half, ptr %in
+ store half %val, ptr %out
+ ret void
+}
+
+define i16 @test_bitcast_from_half(ptr %addr) nounwind {
+; SPARC32-LABEL: test_bitcast_from_half:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: retl
+; SPARC32-NEXT: lduh [%o0], %o0
+;
+; SPARC64-LABEL: test_bitcast_from_half:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: retl
+; SPARC64-NEXT: lduh [%o0], %o0
+ %val = load half, ptr %addr
+ %val_int = bitcast half %val to i16
+ ret i16 %val_int
+}
+
+define void @test_bitcast_to_half(ptr %addr, i16 %in) nounwind {
+; SPARC32-LABEL: test_bitcast_to_half:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: retl
+; SPARC32-NEXT: sth %o1, [%o0]
+;
+; SPARC64-LABEL: test_bitcast_to_half:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: retl
+; SPARC64-NEXT: sth %o1, [%o0]
+ %val_fp = bitcast i16 %in to half
+ store half %val_fp, ptr %addr
+ ret void
+}
+
+define half @from_bits(i16 %x) nounwind {
+; SPARC32-LABEL: from_bits:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: retl
+; SPARC32-NEXT: nop
+;
+; SPARC64-LABEL: from_bits:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: retl
+; SPARC64-NEXT: nop
+ %res = bitcast i16 %x to half
+ ret half %res
+}
+
+define i16 @to_bits(half %x) nounwind {
+; SPARC32-LABEL: to_bits:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: retl
+; SPARC32-NEXT: nop
+;
+; SPARC64-LABEL: to_bits:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: retl
+; SPARC64-NEXT: nop
+ %res = bitcast half %x to i16
+ ret i16 %res
+}
+
+define float @test_extend32(ptr %addr) nounwind {
+; SPARC32-LABEL: test_extend32:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: save %sp, -96, %sp
+; SPARC32-NEXT: call __extendhfsf2
+; SPARC32-NEXT: lduh [%i0], %o0
+; SPARC32-NEXT: ret
+; SPARC32-NEXT: restore
+;
+; SPARC64-LABEL: test_extend32:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: save %sp, -176, %sp
+; SPARC64-NEXT: call __extendhfsf2
+; SPARC64-NEXT: lduh [%i0], %o0
+; SPARC64-NEXT: ret
+; SPARC64-NEXT: restore
+ %val16 = load half, ptr %addr
+ %val32 = fpext half %val16 to float
+ ret float %val32
+}
+
+define double @test_extend64(ptr %addr) nounwind {
+; SPARC32-LABEL: test_extend64:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: save %sp, -96, %sp
+; SPARC32-NEXT: call __extendhfsf2
+; SPARC32-NEXT: lduh [%i0], %o0
+; SPARC32-NEXT: fstod %f0, %f0
+; SPARC32-NEXT: ret
+; SPARC32-NEXT: restore
+;
+; SPARC64-LABEL: test_extend64:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: save %sp, -176, %sp
+; SPARC64-NEXT: call __extendhfsf2
+; SPARC64-NEXT: lduh [%i0], %o0
+; SPARC64-NEXT: fstod %f0, %f0
+; SPARC64-NEXT: ret
+; SPARC64-NEXT: restore
+ %val16 = load half, ptr %addr
+ %val32 = fpext half %val16 to double
+ ret double %val32
+}
+
+define void @test_trunc32(float %in, ptr %addr) nounwind {
+; SPARC32-LABEL: test_trunc32:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: save %sp, -96, %sp
+; SPARC32-NEXT: call __truncsfhf2
+; SPARC32-NEXT: mov %i0, %o0
+; SPARC32-NEXT: sth %o0, [%i1]
+; SPARC32-NEXT: ret
+; SPARC32-NEXT: restore
+;
+; SPARC64-LABEL: test_trunc32:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: save %sp, -176, %sp
+; SPARC64-NEXT: call __truncsfhf2
+; SPARC64-NEXT: nop
+; SPARC64-NEXT: sth %o0, [%i1]
+; SPARC64-NEXT: ret
+; SPARC64-NEXT: restore
+ %val16 = fptrunc float %in to half
+ store half %val16, ptr %addr
+ ret void
+}
+
+define void @test_trunc64(double %in, ptr %addr) nounwind {
+; SPARC32-LABEL: test_trunc64:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: save %sp, -112, %sp
+; SPARC32-NEXT: ! kill: def $i1 killed $i1 killed $i0_i1 def $i0_i1
+; SPARC32-NEXT: ! kill: def $i0 killed $i0 killed $i0_i1 def $i0_i1
+; SPARC32-NEXT: std %i0, [%fp+-8]
+; SPARC32-NEXT: ldd [%fp+-8], %f0
+; SPARC32-NEXT: std %f0, [%fp+-16]
+; SPARC32-NEXT: call __truncdfhf2
+; SPARC32-NEXT: ldd [%fp+-16], %o0
+; SPARC32-NEXT: sth %o0, [%i2]
+; SPARC32-NEXT: ret
+; SPARC32-NEXT: restore
+;
+; SPARC64-LABEL: test_trunc64:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: save %sp, -176, %sp
+; SPARC64-NEXT: call __truncdfhf2
+; SPARC64-NEXT: nop
+; SPARC64-NEXT: sth %o0, [%i1]
+; SPARC64-NEXT: ret
+; SPARC64-NEXT: restore
+ %val16 = fptrunc double %in to half
+ store half %val16, ptr %addr
+ ret void
+}
+
+define i64 @test_fptosi_i64(ptr %p) nounwind {
+; SPARC32-LABEL: test_fptosi_i64:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: save %sp, -96, %sp
+; SPARC32-NEXT: call __extendhfsf2
+; SPARC32-NEXT: lduh [%i0], %o0
+; SPARC32-NEXT: st %f0, [%fp+-4]
+; SPARC32-NEXT: call __fixsfdi
+; SPARC32-NEXT: ld [%fp+-4], %o0
+; SPARC32-NEXT: mov %o0, %i0
+; SPARC32-NEXT: ret
+; SPARC32-NEXT: restore %g0, %o1, %o1
+;
+; SPARC64-LABEL: test_fptosi_i64:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: save %sp, -192, %sp
+; SPARC64-NEXT: call __extendhfsf2
+; SPARC64-NEXT: lduh [%i0], %o0
+; SPARC64-NEXT: fstox %f0, %f0
+; SPARC64-NEXT: std %f0, [%fp+2039]
+; SPARC64-NEXT: ldx [%fp+2039], %i0
+; SPARC64-NEXT: ret
+; SPARC64-NEXT: restore
+ %a = load half, ptr %p, align 2
+ %r = fptosi half %a to i64
+ ret i64 %r
+}
+
+define void @test_sitofp_i64(i64 %a, ptr %p) nounwind {
+; SPARC32-LABEL: test_sitofp_i64:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: save %sp, -96, %sp
+; SPARC32-NEXT: mov %i1, %o1
+; SPARC32-NEXT: call __floatdisf
+; SPARC32-NEXT: mov %i0, %o0
+; SPARC32-NEXT: st %f0, [%fp+-4]
+; SPARC32-NEXT: call __truncsfhf2
+; SPARC32-NEXT: ld [%fp+-4], %o0
+; SPARC32-NEXT: sth %o0, [%i2]
+; SPARC32-NEXT: ret
+; SPARC32-NEXT: restore
+;
+; SPARC64-LABEL: test_sitofp_i64:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: save %sp, -192, %sp
+; SPARC64-NEXT: stx %i0, [%fp+2039]
+; SPARC64-NEXT: ldd [%fp+2039], %f0
+; SPARC64-NEXT: call __truncsfhf2
+; SPARC64-NEXT: fxtos %f0, %f1
+; SPARC64-NEXT: sth %o0, [%i1]
+; SPARC64-NEXT: ret
+; SPARC64-NEXT: restore
+ %r = sitofp i64 %a to half
+ store half %r, ptr %p
+ ret void
+}
+
+define i64 @test_fptoui_i64(ptr %p) nounwind {
+; SPARC32-LABEL: test_fptoui_i64:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: save %sp, -96, %sp
+; SPARC32-NEXT: call __extendhfsf2
+; SPARC32-NEXT: lduh [%i0], %o0
+; SPARC32-NEXT: st %f0, [%fp+-4]
+; SPARC32-NEXT: call __fixunssfdi
+; SPARC32-NEXT: ld [%fp+-4], %o0
+; SPARC32-NEXT: mov %o0, %i0
+; SPARC32-NEXT: ret
+; SPARC32-NEXT: restore %g0, %o1, %o1
+;
+; SPARC64-LABEL: test_fptoui_i64:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: save %sp, -192, %sp
+; SPARC64-NEXT: call __extendhfsf2
+; SPARC64-NEXT: lduh [%i0], %o0
+; SPARC64-NEXT: sethi %h44(.LCPI17_0), %i0
+; SPARC64-NEXT: add %i0, %m44(.LCPI17_0), %i0
+; SPARC64-NEXT: sllx %i0, 12, %i0
+; SPARC64-NEXT: ld [%i0+%l44(.LCPI17_0)], %f1
+; SPARC64-NEXT: fsubs %f0, %f1, %f2
+; SPARC64-NEXT: fstox %f2, %f2
+; SPARC64-NEXT: std %f2, [%fp+2031]
+; SPARC64-NEXT: fstox %f0, %f2
+; SPARC64-NEXT: std %f2, [%fp+2039]
+; SPARC64-NEXT: ldx [%fp+2031], %i0
+; SPARC64-NEXT: sethi 0, %i1
+; SPARC64-NEXT: or %i1, 0, %i1
+; SPARC64-NEXT: sethi 2097152, %i2
+; SPARC64-NEXT: or %i2, 0, %i2
+; SPARC64-NEXT: sllx %i2, 32, %i2
+; SPARC64-NEXT: ldx [%fp+2039], %i3
+; SPARC64-NEXT: or %i2, %i1, %i1
+; SPARC64-NEXT: xor %i0, %i1, %i0
+; SPARC64-NEXT: fcmps %fcc0, %f0, %f1
+; SPARC64-NEXT: movl %fcc0, %i3, %i0
+; SPARC64-NEXT: ret
+; SPARC64-NEXT: restore
+ %a = load half, ptr %p, align 2
+ %r = fptoui half %a to i64
+ ret i64 %r
+}
+
+define void @test_uitofp_i64(i64 %a, ptr %p) nounwind {
+; SPARC32-LABEL: test_uitofp_i64:
+; SPARC32: ! %bb.0:
+; SPARC32-NEXT: save %sp, -96, %sp
+; SPARC32-NEXT: mov %i1, %o1
+; SPARC32-NEXT: call __floatundisf
+; SPARC32-NEXT: mov %i0, %o0
+; SPARC32-NEXT: st %f0, [%fp+-4]
+; SPARC32-NEXT: call __truncsfhf2
+; SPARC32-NEXT: ld [%fp+-4], %o0
+; SPARC32-NEXT: sth %o0, [%i2]
+; SPARC32-NEXT: ret
+; SPARC32-NEXT: restore
+;
+; SPARC64-LABEL: test_uitofp_i64:
+; SPARC64: ! %bb.0:
+; SPARC64-NEXT: save %sp, -192, %sp
+; SPARC64-NEXT: stx %i0, [%fp+2031]
+; SPARC64-NEXT: srlx %i0, 1, %i2
+; SPARC64-NEXT: and %i0, 1, %i3
+; SPARC64-NEXT: or %i3, %i2, %i2
+; SPARC64-NEXT: stx %i2, [%fp+2039]
+; SPARC64-NEXT: ldd [%fp+2031], %f0
+; SPARC64-NEXT: ldd [%fp+2039], %f2
+; SPARC64-NEXT: fxtos %f0, %f1
+; SPARC64-NEXT: fxtos %f2, %f0
+; SPARC64-NEXT: fadds %f0, %f0, %f0
+; SPARC64-NEXT: call __truncsfhf2
+; SPARC64-NEXT: fmovrslz %i0, %f0, %f1
+; SPARC64-NEXT: sth %o0, [%i1]
+; SPARC64-NEXT: ret
+; SPARC64-NEXT: restore
+ %r = uitofp i...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/152727
More information about the llvm-commits
mailing list