[llvm-branch-commits] [llvm] release/23.x: [AArch64] fix invalid GISel lowering of saturating `f16` to integer conversion (#235676) (PR #240155)
via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Sun Nov 8 07:41:33 PST 2026
llvmorg-github-actions[bot] wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-aarch64
Author: Folkert de Vries (folkertdev)
<details>
<summary>Changes</summary>
Backport 617b7da9db855f1c74e9425555ce23f98f4dc6f9
Requested by: @<!-- -->folkertdev
This is a custom PR because the automatic https://github.com/llvm/llvm-project/pull/238543 ran into test failures. I've updated the CHECKs here.
---
Patch is 53.83 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/240155.diff
5 Files Affected:
- (modified) llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp (+2-7)
- (modified) llvm/test/CodeGen/AArch64/fptosi-sat-scalar.ll (+72-8)
- (modified) llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll (+463-117)
- (modified) llvm/test/CodeGen/AArch64/fptoui-sat-scalar.ll (+36-8)
- (modified) llvm/test/CodeGen/AArch64/fptoui-sat-vector.ll (+278-117)
``````````diff
diff --git a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
index 387ed79893d3c6..b076f384d69207 100644
--- a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
+++ b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
@@ -974,13 +974,8 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST)
// Handle types larger than i64 by scalarizing/lowering.
.scalarizeIf(scalarOrEltWiderThan(0, 64), 0)
.scalarizeIf(scalarOrEltWiderThan(1, 64), 1)
- // The range of a fp16 value fits into an i17, so we can lower the width
- // to i64.
- .narrowScalarIf(
- [=](const LegalityQuery &Query) {
- return Query.Types[1] == f16 && Query.Types[0].getSizeInBits() > 64;
- },
- changeTo(0, i64))
+ // NOTE: narrowScalarIf is invalid for the saturating conversions,
+ // infinities need the full width of the target integer type.
.lowerIf(::any(scalarWiderThan(0, 64), scalarWiderThan(1, 64)), 0)
.moreElementsToNextPow2(0)
.widenScalarToNextPow2(0, /*MinSize=*/32)
diff --git a/llvm/test/CodeGen/AArch64/fptosi-sat-scalar.ll b/llvm/test/CodeGen/AArch64/fptosi-sat-scalar.ll
index f95d338198c4d1..921e87f15c2724 100644
--- a/llvm/test/CodeGen/AArch64/fptosi-sat-scalar.ll
+++ b/llvm/test/CodeGen/AArch64/fptosi-sat-scalar.ll
@@ -877,14 +877,46 @@ define i100 @test_signed_i100_f16(half %f) nounwind {
; CHECK-GI-CVT-LABEL: test_signed_i100_f16:
; CHECK-GI-CVT: // %bb.0:
; CHECK-GI-CVT-NEXT: fcvt s0, h0
-; CHECK-GI-CVT-NEXT: mov x1, xzr
-; CHECK-GI-CVT-NEXT: fcvtzs x0, s0
+; CHECK-GI-CVT-NEXT: mov w9, #57344 // =0xe000
+; CHECK-GI-CVT-NEXT: mov w10, #57344 // =0xe000
+; CHECK-GI-CVT-NEXT: movk w9, #51071, lsl #16
+; CHECK-GI-CVT-NEXT: movk w10, #18303, lsl #16
+; CHECK-GI-CVT-NEXT: fmov s1, w9
+; CHECK-GI-CVT-NEXT: fcvtzs x8, s0
+; CHECK-GI-CVT-NEXT: fcmp s0, s1
+; CHECK-GI-CVT-NEXT: fmov s1, w10
+; CHECK-GI-CVT-NEXT: mov x10, #34359738368 // =0x800000000
+; CHECK-GI-CVT-NEXT: asr x9, x8, #63
+; CHECK-GI-CVT-NEXT: csel x8, xzr, x8, lt
+; CHECK-GI-CVT-NEXT: csel x9, x10, x9, lt
+; CHECK-GI-CVT-NEXT: fcmp s0, s1
+; CHECK-GI-CVT-NEXT: mov x10, #34359738367 // =0x7ffffffff
+; CHECK-GI-CVT-NEXT: csinv x8, x8, xzr, le
+; CHECK-GI-CVT-NEXT: csel x9, x10, x9, gt
+; CHECK-GI-CVT-NEXT: fcmp s0, s0
+; CHECK-GI-CVT-NEXT: csel x0, xzr, x8, vs
+; CHECK-GI-CVT-NEXT: csel x1, xzr, x9, vs
; CHECK-GI-CVT-NEXT: ret
;
; CHECK-GI-FP16-LABEL: test_signed_i100_f16:
; CHECK-GI-FP16: // %bb.0:
-; CHECK-GI-FP16-NEXT: fcvtzs x0, h0
-; CHECK-GI-FP16-NEXT: mov x1, xzr
+; CHECK-GI-FP16-NEXT: adrp x8, .LCPI28_1
+; CHECK-GI-FP16-NEXT: fcvtzs x9, h0
+; CHECK-GI-FP16-NEXT: ldr h1, [x8, :lo12:.LCPI28_1]
+; CHECK-GI-FP16-NEXT: adrp x8, .LCPI28_0
+; CHECK-GI-FP16-NEXT: fcmp h0, h1
+; CHECK-GI-FP16-NEXT: ldr h1, [x8, :lo12:.LCPI28_0]
+; CHECK-GI-FP16-NEXT: mov x8, #34359738368 // =0x800000000
+; CHECK-GI-FP16-NEXT: asr x10, x9, #63
+; CHECK-GI-FP16-NEXT: csel x9, xzr, x9, lt
+; CHECK-GI-FP16-NEXT: csel x8, x8, x10, lt
+; CHECK-GI-FP16-NEXT: fcmp h0, h1
+; CHECK-GI-FP16-NEXT: mov x10, #34359738367 // =0x7ffffffff
+; CHECK-GI-FP16-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-FP16-NEXT: csel x8, x10, x8, gt
+; CHECK-GI-FP16-NEXT: fcmp h0, h0
+; CHECK-GI-FP16-NEXT: csel x0, xzr, x9, vs
+; CHECK-GI-FP16-NEXT: csel x1, xzr, x8, vs
; CHECK-GI-FP16-NEXT: ret
%x = call i100 @llvm.fptosi.sat.i100.f16(half %f)
ret i100 %x
@@ -919,14 +951,46 @@ define i128 @test_signed_i128_f16(half %f) nounwind {
; CHECK-GI-CVT-LABEL: test_signed_i128_f16:
; CHECK-GI-CVT: // %bb.0:
; CHECK-GI-CVT-NEXT: fcvt s0, h0
-; CHECK-GI-CVT-NEXT: mov x1, xzr
-; CHECK-GI-CVT-NEXT: fcvtzs x0, s0
+; CHECK-GI-CVT-NEXT: mov w9, #57344 // =0xe000
+; CHECK-GI-CVT-NEXT: mov w10, #57344 // =0xe000
+; CHECK-GI-CVT-NEXT: movk w9, #51071, lsl #16
+; CHECK-GI-CVT-NEXT: movk w10, #18303, lsl #16
+; CHECK-GI-CVT-NEXT: fmov s1, w9
+; CHECK-GI-CVT-NEXT: fcvtzs x8, s0
+; CHECK-GI-CVT-NEXT: fcmp s0, s1
+; CHECK-GI-CVT-NEXT: fmov s1, w10
+; CHECK-GI-CVT-NEXT: mov x10, #-9223372036854775808 // =0x8000000000000000
+; CHECK-GI-CVT-NEXT: asr x9, x8, #63
+; CHECK-GI-CVT-NEXT: csel x8, xzr, x8, lt
+; CHECK-GI-CVT-NEXT: csel x9, x10, x9, lt
+; CHECK-GI-CVT-NEXT: fcmp s0, s1
+; CHECK-GI-CVT-NEXT: mov x10, #9223372036854775807 // =0x7fffffffffffffff
+; CHECK-GI-CVT-NEXT: csinv x8, x8, xzr, le
+; CHECK-GI-CVT-NEXT: csel x9, x10, x9, gt
+; CHECK-GI-CVT-NEXT: fcmp s0, s0
+; CHECK-GI-CVT-NEXT: csel x0, xzr, x8, vs
+; CHECK-GI-CVT-NEXT: csel x1, xzr, x9, vs
; CHECK-GI-CVT-NEXT: ret
;
; CHECK-GI-FP16-LABEL: test_signed_i128_f16:
; CHECK-GI-FP16: // %bb.0:
-; CHECK-GI-FP16-NEXT: fcvtzs x0, h0
-; CHECK-GI-FP16-NEXT: mov x1, xzr
+; CHECK-GI-FP16-NEXT: adrp x8, .LCPI29_1
+; CHECK-GI-FP16-NEXT: fcvtzs x9, h0
+; CHECK-GI-FP16-NEXT: ldr h1, [x8, :lo12:.LCPI29_1]
+; CHECK-GI-FP16-NEXT: adrp x8, .LCPI29_0
+; CHECK-GI-FP16-NEXT: fcmp h0, h1
+; CHECK-GI-FP16-NEXT: ldr h1, [x8, :lo12:.LCPI29_0]
+; CHECK-GI-FP16-NEXT: mov x8, #-9223372036854775808 // =0x8000000000000000
+; CHECK-GI-FP16-NEXT: asr x10, x9, #63
+; CHECK-GI-FP16-NEXT: csel x9, xzr, x9, lt
+; CHECK-GI-FP16-NEXT: csel x8, x8, x10, lt
+; CHECK-GI-FP16-NEXT: fcmp h0, h1
+; CHECK-GI-FP16-NEXT: mov x10, #9223372036854775807 // =0x7fffffffffffffff
+; CHECK-GI-FP16-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-FP16-NEXT: csel x8, x10, x8, gt
+; CHECK-GI-FP16-NEXT: fcmp h0, h0
+; CHECK-GI-FP16-NEXT: csel x0, xzr, x9, vs
+; CHECK-GI-FP16-NEXT: csel x1, xzr, x8, vs
; CHECK-GI-FP16-NEXT: ret
%x = call i128 @llvm.fptosi.sat.i128.f16(half %f)
ret i128 %x
diff --git a/llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll b/llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll
index 145aef9123a4e9..fcceef66470c7b 100644
--- a/llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll
+++ b/llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll
@@ -3237,37 +3237,123 @@ define <4 x i100> @test_signed_v4f16_v4i100(<4 x half> %f) {
; CHECK-GI-CVT-LABEL: test_signed_v4f16_v4i100:
; CHECK-GI-CVT: // %bb.0:
; CHECK-GI-CVT-NEXT: // kill: def $d0 killed $d0 def $q0
-; CHECK-GI-CVT-NEXT: mov h1, v0.h[1]
-; CHECK-GI-CVT-NEXT: mov h2, v0.h[2]
-; CHECK-GI-CVT-NEXT: mov x1, xzr
-; CHECK-GI-CVT-NEXT: mov h3, v0.h[3]
-; CHECK-GI-CVT-NEXT: fcvt s0, h0
-; CHECK-GI-CVT-NEXT: mov x3, xzr
-; CHECK-GI-CVT-NEXT: mov x5, xzr
-; CHECK-GI-CVT-NEXT: mov x7, xzr
-; CHECK-GI-CVT-NEXT: fcvt s1, h1
-; CHECK-GI-CVT-NEXT: fcvt s2, h2
+; CHECK-GI-CVT-NEXT: fcvt s2, h0
+; CHECK-GI-CVT-NEXT: mov w9, #57344 // =0xe000
+; CHECK-GI-CVT-NEXT: mov h3, v0.h[1]
+; CHECK-GI-CVT-NEXT: movk w9, #51071, lsl #16
+; CHECK-GI-CVT-NEXT: mov x11, #34359738368 // =0x800000000
+; CHECK-GI-CVT-NEXT: mov h5, v0.h[2]
+; CHECK-GI-CVT-NEXT: fmov s1, w9
+; CHECK-GI-CVT-NEXT: mov w9, #57344 // =0xe000
+; CHECK-GI-CVT-NEXT: mov h0, v0.h[3]
+; CHECK-GI-CVT-NEXT: movk w9, #18303, lsl #16
+; CHECK-GI-CVT-NEXT: fcvtzs x8, s2
+; CHECK-GI-CVT-NEXT: fmov s4, w9
; CHECK-GI-CVT-NEXT: fcvt s3, h3
-; CHECK-GI-CVT-NEXT: fcvtzs x0, s0
-; CHECK-GI-CVT-NEXT: fcvtzs x2, s1
-; CHECK-GI-CVT-NEXT: fcvtzs x4, s2
-; CHECK-GI-CVT-NEXT: fcvtzs x6, s3
+; CHECK-GI-CVT-NEXT: fcmp s2, s1
+; CHECK-GI-CVT-NEXT: fcvt s0, h0
+; CHECK-GI-CVT-NEXT: asr x10, x8, #63
+; CHECK-GI-CVT-NEXT: csel x8, xzr, x8, lt
+; CHECK-GI-CVT-NEXT: fcvtzs x12, s3
+; CHECK-GI-CVT-NEXT: csel x9, x11, x10, lt
+; CHECK-GI-CVT-NEXT: fcmp s2, s4
+; CHECK-GI-CVT-NEXT: mov x10, #34359738367 // =0x7ffffffff
+; CHECK-GI-CVT-NEXT: csinv x8, x8, xzr, le
+; CHECK-GI-CVT-NEXT: csel x9, x10, x9, gt
+; CHECK-GI-CVT-NEXT: fcmp s2, s2
+; CHECK-GI-CVT-NEXT: fcvt s2, h5
+; CHECK-GI-CVT-NEXT: csel x0, xzr, x8, vs
+; CHECK-GI-CVT-NEXT: csel x1, xzr, x9, vs
+; CHECK-GI-CVT-NEXT: fcmp s3, s1
+; CHECK-GI-CVT-NEXT: asr x8, x12, #63
+; CHECK-GI-CVT-NEXT: csel x9, xzr, x12, lt
+; CHECK-GI-CVT-NEXT: csel x8, x11, x8, lt
+; CHECK-GI-CVT-NEXT: fcmp s3, s4
+; CHECK-GI-CVT-NEXT: fcvtzs x12, s2
+; CHECK-GI-CVT-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-CVT-NEXT: csel x8, x10, x8, gt
+; CHECK-GI-CVT-NEXT: fcmp s3, s3
+; CHECK-GI-CVT-NEXT: csel x2, xzr, x9, vs
+; CHECK-GI-CVT-NEXT: csel x3, xzr, x8, vs
+; CHECK-GI-CVT-NEXT: fcmp s2, s1
+; CHECK-GI-CVT-NEXT: asr x8, x12, #63
+; CHECK-GI-CVT-NEXT: csel x9, xzr, x12, lt
+; CHECK-GI-CVT-NEXT: csel x8, x11, x8, lt
+; CHECK-GI-CVT-NEXT: fcmp s2, s4
+; CHECK-GI-CVT-NEXT: fcvtzs x12, s0
+; CHECK-GI-CVT-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-CVT-NEXT: csel x8, x10, x8, gt
+; CHECK-GI-CVT-NEXT: fcmp s2, s2
+; CHECK-GI-CVT-NEXT: csel x4, xzr, x9, vs
+; CHECK-GI-CVT-NEXT: csel x5, xzr, x8, vs
+; CHECK-GI-CVT-NEXT: fcmp s0, s1
+; CHECK-GI-CVT-NEXT: asr x8, x12, #63
+; CHECK-GI-CVT-NEXT: csel x9, xzr, x12, lt
+; CHECK-GI-CVT-NEXT: csel x8, x11, x8, lt
+; CHECK-GI-CVT-NEXT: fcmp s0, s4
+; CHECK-GI-CVT-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-CVT-NEXT: csel x8, x10, x8, gt
+; CHECK-GI-CVT-NEXT: fcmp s0, s0
+; CHECK-GI-CVT-NEXT: csel x6, xzr, x9, vs
+; CHECK-GI-CVT-NEXT: csel x7, xzr, x8, vs
; CHECK-GI-CVT-NEXT: ret
;
; CHECK-GI-FP16-LABEL: test_signed_v4f16_v4i100:
; CHECK-GI-FP16: // %bb.0:
; CHECK-GI-FP16-NEXT: // kill: def $d0 killed $d0 def $q0
-; CHECK-GI-FP16-NEXT: mov h1, v0.h[1]
-; CHECK-GI-FP16-NEXT: mov h2, v0.h[2]
-; CHECK-GI-FP16-NEXT: mov x1, xzr
-; CHECK-GI-FP16-NEXT: mov h3, v0.h[3]
-; CHECK-GI-FP16-NEXT: fcvtzs x0, h0
-; CHECK-GI-FP16-NEXT: mov x3, xzr
-; CHECK-GI-FP16-NEXT: mov x5, xzr
-; CHECK-GI-FP16-NEXT: mov x7, xzr
-; CHECK-GI-FP16-NEXT: fcvtzs x2, h1
-; CHECK-GI-FP16-NEXT: fcvtzs x4, h2
-; CHECK-GI-FP16-NEXT: fcvtzs x6, h3
+; CHECK-GI-FP16-NEXT: adrp x8, .LCPI64_1
+; CHECK-GI-FP16-NEXT: fcvtzs x9, h0
+; CHECK-GI-FP16-NEXT: mov h2, v0.h[1]
+; CHECK-GI-FP16-NEXT: ldr h1, [x8, :lo12:.LCPI64_1]
+; CHECK-GI-FP16-NEXT: adrp x8, .LCPI64_0
+; CHECK-GI-FP16-NEXT: mov x10, #34359738368 // =0x800000000
+; CHECK-GI-FP16-NEXT: ldr h3, [x8, :lo12:.LCPI64_0]
+; CHECK-GI-FP16-NEXT: mov x11, #34359738367 // =0x7ffffffff
+; CHECK-GI-FP16-NEXT: mov h4, v0.h[2]
+; CHECK-GI-FP16-NEXT: fcmp h0, h1
+; CHECK-GI-FP16-NEXT: asr x8, x9, #63
+; CHECK-GI-FP16-NEXT: fcvtzs x12, h2
+; CHECK-GI-FP16-NEXT: csel x9, xzr, x9, lt
+; CHECK-GI-FP16-NEXT: csel x8, x10, x8, lt
+; CHECK-GI-FP16-NEXT: fcmp h0, h3
+; CHECK-GI-FP16-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-FP16-NEXT: csel x8, x11, x8, gt
+; CHECK-GI-FP16-NEXT: fcmp h0, h0
+; CHECK-GI-FP16-NEXT: mov h0, v0.h[3]
+; CHECK-GI-FP16-NEXT: csel x0, xzr, x9, vs
+; CHECK-GI-FP16-NEXT: csel x1, xzr, x8, vs
+; CHECK-GI-FP16-NEXT: fcmp h2, h1
+; CHECK-GI-FP16-NEXT: asr x8, x12, #63
+; CHECK-GI-FP16-NEXT: csel x9, xzr, x12, lt
+; CHECK-GI-FP16-NEXT: csel x8, x10, x8, lt
+; CHECK-GI-FP16-NEXT: fcmp h2, h3
+; CHECK-GI-FP16-NEXT: fcvtzs x12, h4
+; CHECK-GI-FP16-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-FP16-NEXT: csel x8, x11, x8, gt
+; CHECK-GI-FP16-NEXT: fcmp h2, h2
+; CHECK-GI-FP16-NEXT: csel x2, xzr, x9, vs
+; CHECK-GI-FP16-NEXT: csel x3, xzr, x8, vs
+; CHECK-GI-FP16-NEXT: fcmp h4, h1
+; CHECK-GI-FP16-NEXT: asr x8, x12, #63
+; CHECK-GI-FP16-NEXT: csel x9, xzr, x12, lt
+; CHECK-GI-FP16-NEXT: csel x8, x10, x8, lt
+; CHECK-GI-FP16-NEXT: fcmp h4, h3
+; CHECK-GI-FP16-NEXT: fcvtzs x12, h0
+; CHECK-GI-FP16-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-FP16-NEXT: csel x8, x11, x8, gt
+; CHECK-GI-FP16-NEXT: fcmp h4, h4
+; CHECK-GI-FP16-NEXT: csel x4, xzr, x9, vs
+; CHECK-GI-FP16-NEXT: csel x5, xzr, x8, vs
+; CHECK-GI-FP16-NEXT: fcmp h0, h1
+; CHECK-GI-FP16-NEXT: asr x8, x12, #63
+; CHECK-GI-FP16-NEXT: csel x9, xzr, x12, lt
+; CHECK-GI-FP16-NEXT: csel x8, x10, x8, lt
+; CHECK-GI-FP16-NEXT: fcmp h0, h3
+; CHECK-GI-FP16-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-FP16-NEXT: csel x8, x11, x8, gt
+; CHECK-GI-FP16-NEXT: fcmp h0, h0
+; CHECK-GI-FP16-NEXT: csel x6, xzr, x9, vs
+; CHECK-GI-FP16-NEXT: csel x7, xzr, x8, vs
; CHECK-GI-FP16-NEXT: ret
%x = call <4 x i100> @llvm.fptosi.sat.v4f16.v4i100(<4 x half> %f)
ret <4 x i100> %x
@@ -3377,37 +3463,123 @@ define <4 x i128> @test_signed_v4f16_v4i128(<4 x half> %f) {
; CHECK-GI-CVT-LABEL: test_signed_v4f16_v4i128:
; CHECK-GI-CVT: // %bb.0:
; CHECK-GI-CVT-NEXT: // kill: def $d0 killed $d0 def $q0
-; CHECK-GI-CVT-NEXT: mov h1, v0.h[1]
-; CHECK-GI-CVT-NEXT: mov h2, v0.h[2]
-; CHECK-GI-CVT-NEXT: mov x1, xzr
-; CHECK-GI-CVT-NEXT: mov h3, v0.h[3]
-; CHECK-GI-CVT-NEXT: fcvt s0, h0
-; CHECK-GI-CVT-NEXT: mov x3, xzr
-; CHECK-GI-CVT-NEXT: mov x5, xzr
-; CHECK-GI-CVT-NEXT: mov x7, xzr
-; CHECK-GI-CVT-NEXT: fcvt s1, h1
-; CHECK-GI-CVT-NEXT: fcvt s2, h2
+; CHECK-GI-CVT-NEXT: fcvt s2, h0
+; CHECK-GI-CVT-NEXT: mov w9, #57344 // =0xe000
+; CHECK-GI-CVT-NEXT: mov h3, v0.h[1]
+; CHECK-GI-CVT-NEXT: movk w9, #51071, lsl #16
+; CHECK-GI-CVT-NEXT: mov x11, #-9223372036854775808 // =0x8000000000000000
+; CHECK-GI-CVT-NEXT: mov h5, v0.h[2]
+; CHECK-GI-CVT-NEXT: fmov s1, w9
+; CHECK-GI-CVT-NEXT: mov w9, #57344 // =0xe000
+; CHECK-GI-CVT-NEXT: mov h0, v0.h[3]
+; CHECK-GI-CVT-NEXT: movk w9, #18303, lsl #16
+; CHECK-GI-CVT-NEXT: fcvtzs x8, s2
+; CHECK-GI-CVT-NEXT: fmov s4, w9
; CHECK-GI-CVT-NEXT: fcvt s3, h3
-; CHECK-GI-CVT-NEXT: fcvtzs x0, s0
-; CHECK-GI-CVT-NEXT: fcvtzs x2, s1
-; CHECK-GI-CVT-NEXT: fcvtzs x4, s2
-; CHECK-GI-CVT-NEXT: fcvtzs x6, s3
+; CHECK-GI-CVT-NEXT: fcmp s2, s1
+; CHECK-GI-CVT-NEXT: fcvt s0, h0
+; CHECK-GI-CVT-NEXT: asr x10, x8, #63
+; CHECK-GI-CVT-NEXT: csel x8, xzr, x8, lt
+; CHECK-GI-CVT-NEXT: fcvtzs x12, s3
+; CHECK-GI-CVT-NEXT: csel x9, x11, x10, lt
+; CHECK-GI-CVT-NEXT: fcmp s2, s4
+; CHECK-GI-CVT-NEXT: mov x10, #9223372036854775807 // =0x7fffffffffffffff
+; CHECK-GI-CVT-NEXT: csinv x8, x8, xzr, le
+; CHECK-GI-CVT-NEXT: csel x9, x10, x9, gt
+; CHECK-GI-CVT-NEXT: fcmp s2, s2
+; CHECK-GI-CVT-NEXT: fcvt s2, h5
+; CHECK-GI-CVT-NEXT: csel x0, xzr, x8, vs
+; CHECK-GI-CVT-NEXT: csel x1, xzr, x9, vs
+; CHECK-GI-CVT-NEXT: fcmp s3, s1
+; CHECK-GI-CVT-NEXT: asr x8, x12, #63
+; CHECK-GI-CVT-NEXT: csel x9, xzr, x12, lt
+; CHECK-GI-CVT-NEXT: csel x8, x11, x8, lt
+; CHECK-GI-CVT-NEXT: fcmp s3, s4
+; CHECK-GI-CVT-NEXT: fcvtzs x12, s2
+; CHECK-GI-CVT-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-CVT-NEXT: csel x8, x10, x8, gt
+; CHECK-GI-CVT-NEXT: fcmp s3, s3
+; CHECK-GI-CVT-NEXT: csel x2, xzr, x9, vs
+; CHECK-GI-CVT-NEXT: csel x3, xzr, x8, vs
+; CHECK-GI-CVT-NEXT: fcmp s2, s1
+; CHECK-GI-CVT-NEXT: asr x8, x12, #63
+; CHECK-GI-CVT-NEXT: csel x9, xzr, x12, lt
+; CHECK-GI-CVT-NEXT: csel x8, x11, x8, lt
+; CHECK-GI-CVT-NEXT: fcmp s2, s4
+; CHECK-GI-CVT-NEXT: fcvtzs x12, s0
+; CHECK-GI-CVT-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-CVT-NEXT: csel x8, x10, x8, gt
+; CHECK-GI-CVT-NEXT: fcmp s2, s2
+; CHECK-GI-CVT-NEXT: csel x4, xzr, x9, vs
+; CHECK-GI-CVT-NEXT: csel x5, xzr, x8, vs
+; CHECK-GI-CVT-NEXT: fcmp s0, s1
+; CHECK-GI-CVT-NEXT: asr x8, x12, #63
+; CHECK-GI-CVT-NEXT: csel x9, xzr, x12, lt
+; CHECK-GI-CVT-NEXT: csel x8, x11, x8, lt
+; CHECK-GI-CVT-NEXT: fcmp s0, s4
+; CHECK-GI-CVT-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-CVT-NEXT: csel x8, x10, x8, gt
+; CHECK-GI-CVT-NEXT: fcmp s0, s0
+; CHECK-GI-CVT-NEXT: csel x6, xzr, x9, vs
+; CHECK-GI-CVT-NEXT: csel x7, xzr, x8, vs
; CHECK-GI-CVT-NEXT: ret
;
; CHECK-GI-FP16-LABEL: test_signed_v4f16_v4i128:
; CHECK-GI-FP16: // %bb.0:
; CHECK-GI-FP16-NEXT: // kill: def $d0 killed $d0 def $q0
-; CHECK-GI-FP16-NEXT: mov h1, v0.h[1]
-; CHECK-GI-FP16-NEXT: mov h2, v0.h[2]
-; CHECK-GI-FP16-NEXT: mov x1, xzr
-; CHECK-GI-FP16-NEXT: mov h3, v0.h[3]
-; CHECK-GI-FP16-NEXT: fcvtzs x0, h0
-; CHECK-GI-FP16-NEXT: mov x3, xzr
-; CHECK-GI-FP16-NEXT: mov x5, xzr
-; CHECK-GI-FP16-NEXT: mov x7, xzr
-; CHECK-GI-FP16-NEXT: fcvtzs x2, h1
-; CHECK-GI-FP16-NEXT: fcvtzs x4, h2
-; CHECK-GI-FP16-NEXT: fcvtzs x6, h3
+; CHECK-GI-FP16-NEXT: adrp x8, .LCPI65_1
+; CHECK-GI-FP16-NEXT: fcvtzs x9, h0
+; CHECK-GI-FP16-NEXT: mov h2, v0.h[1]
+; CHECK-GI-FP16-NEXT: ldr h1, [x8, :lo12:.LCPI65_1]
+; CHECK-GI-FP16-NEXT: adrp x8, .LCPI65_0
+; CHECK-GI-FP16-NEXT: mov x10, #-9223372036854775808 // =0x8000000000000000
+; CHECK-GI-FP16-NEXT: ldr h3, [x8, :lo12:.LCPI65_0]
+; CHECK-GI-FP16-NEXT: mov x11, #9223372036854775807 // =0x7fffffffffffffff
+; CHECK-GI-FP16-NEXT: mov h4, v0.h[2]
+; CHECK-GI-FP16-NEXT: fcmp h0, h1
+; CHECK-GI-FP16-NEXT: asr x8, x9, #63
+; CHECK-GI-FP16-NEXT: fcvtzs x12, h2
+; CHECK-GI-FP16-NEXT: csel x9, xzr, x9, lt
+; CHECK-GI-FP16-NEXT: csel x8, x10, x8, lt
+; CHECK-GI-FP16-NEXT: fcmp h0, h3
+; CHECK-GI-FP16-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-FP16-NEXT: csel x8, x11, x8, gt
+; CHECK-GI-FP16-NEXT: fcmp h0, h0
+; CHECK-GI-FP16-NEXT: mov h0, v0.h[3]
+; CHECK-GI-FP16-NEXT: csel x0, xzr, x9, vs
+; CHECK-GI-FP16-NEXT: csel x1, xzr, x8, vs
+; CHECK-GI-FP16-NEXT: fcmp h2, h1
+; CHECK-GI-FP16-NEXT: asr x8, x12, #63
+; CHECK-GI-FP16-NEXT: csel x9, xzr, x12, lt
+; CHECK-GI-FP16-NEXT: csel x8, x10, x8, lt
+; CHECK-GI-FP16-NEXT: fcmp h2, h3
+; CHECK-GI-FP16-NEXT: fcvtzs x12, h4
+; CHECK-GI-FP16-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-FP16-NEXT: csel x8, x11, x8, gt
+; CHECK-GI-FP16-NEXT: fcmp h2, h2
+; CHECK-GI-FP16-NEXT: csel x2, xzr, x9, vs
+; CHECK-GI-FP16-NEXT: csel x3, xzr, x8, vs
+; CHECK-GI-FP16-NEXT: fcmp h4, h1
+; CHECK-GI-FP16-NEXT: asr x8, x12, #63
+; CHECK-GI-FP16-NEXT: csel x9, xzr, x12, lt
+; CHECK-GI-FP16-NEXT: csel x8, x10, x8, lt
+; CHECK-GI-FP16-NEXT: fcmp h4, h3
+; CHECK-GI-FP16-NEXT: fcvtzs x12, h0
+; CHECK-GI-FP16-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-FP16-NEXT: csel x8, x11, x8, gt
+; CHECK-GI-FP16-NEXT: fcmp h4, h4
+; CHECK-GI-FP16-NEXT: csel x4, xzr, x9, vs
+; CHECK-GI-FP16-NEXT: csel x5, xzr, x8, vs
+; CHECK-GI-FP16-NEXT: fcmp h0, h1
+; CHECK-GI-FP16-NEXT: asr x8, x12, #63
+; CHECK-GI-FP16-NEXT: csel x9, xzr, x12, lt
+; CHECK-GI-FP16-NEXT: csel x8, x10, x8, lt
+; CHECK-GI-FP16-NEXT: fcmp h0, h3
+; CHECK-GI-FP16-NEXT: csinv x9, x9, xzr, le
+; CHECK-GI-FP16-NEXT: csel x8, x11, x8, gt
+; CHECK-GI-FP16-NEXT: fcmp h0, h0
+; CHECK-GI-FP16-NEXT: csel x6, xzr, x9, vs
+; CHECK-GI-FP16-NEXT: csel x7, xzr, x8, vs
; CHECK-GI-FP16-NEXT: ret
%x = call <4 x i128> @llvm.fptosi.sat.v4f16.v4i128(<4 x half> %f)
ret <4 x i128> %x
@@ -4209,86 +4381,260 @@ define <8 x i128> @test_signed_v8f16_v8i128(<8 x half> %f) {
;
; CHECK-GI-CVT-LABEL: test_signed_v8f16_v8i128:
; CHECK-GI-CVT: // %bb.0:
-; CHECK-GI-CVT-NEXT: mov h1, v0.h[1]
-; CHECK-GI-CVT-NEXT: mov h2, v0.h[2]
-; CHECK-GI-CVT-NEXT: mov h3, v0.h[3]
-; CHECK-GI-CVT-NEXT: mov h4, v0.h[4]
-; CHECK-GI-CVT-NEXT: fcvt s5, h0
-; CHECK-GI-CVT-NEXT: mov h6, v0.h[5]
-; CHECK-GI-CVT-NEXT: mov h7, v0.h[6]
+; CHECK-GI-CVT-NEXT: fcvt s3, h0
+; CHECK-GI-CVT-NEXT: mov w10, #57344 // =0xe000
+; CHECK-GI-CVT-NEXT: mov h2, v0.h[1]
+; CHECK-GI-CVT-NEXT: movk w10, #51071, lsl #16
+; CHECK-GI-CVT-NEXT: mov w11, #57344 // =0xe000
+; CHECK-GI-CVT-NEXT: mov h5, v0.h[2]
+; CHECK-GI-CVT-NEXT: fmov s1, w10
+; CHECK-GI-CVT-NEXT: movk w11, #18303, lsl #16
+; CHECK-GI-CVT-NEXT: mov x10, #-9223372036854775808 // =0x8000000000000000
+; CHECK-GI-CVT-NEXT: fcvtzs x9, s3
+; CHECK-GI-CVT-NEXT: fcvt s4, h2
+; CHECK-GI-CVT-NEXT: fmov s2, w11
+; CHECK-GI-CVT-NEXT: fcmp s3, s1
+; CHECK-GI-CVT-NEXT: asr x12, x9, #63
+; CHECK-GI-CVT-NEXT: csel x11, xzr, x9, lt
+; CHECK-GI-CVT-NEXT: mov x9, #9223372036854775807 // =0x7fffffffffffffff
+; CHECK-GI-CVT-NEXT: fcvtzs x13, s4
+; CHECK-GI-CVT-NEXT: csel x12, x10, x12, lt
+; CHECK-GI-CVT-NEXT: ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/240155
More information about the llvm-branch-commits
mailing list