[X86] Add ldexp test coverage for avx512 targets by RKSimon · Pull Request #165698 · llvm/llvm-project

RKSimon · 2025-10-30T11:33:08Z

Pulled out of the abandoned patch #69710 to act as a baseline for #165694

Pulled out of the abandoned patch llvm#69710 to act as a baseline for llvm#165694

llvmbot · 2025-10-30T11:33:43Z

@llvm/pr-subscribers-backend-x86

Author: Simon Pilgrim (RKSimon)

Changes

Pulled out of the abandoned patch #69710 to act as a baseline for #165694

Patch is 23.98 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/165698.diff

1 Files Affected:

(added) llvm/test/CodeGen/X86/ldexp-avx512.ll (+467)

diff --git a/llvm/test/CodeGen/X86/ldexp-avx512.ll b/llvm/test/CodeGen/X86/ldexp-avx512.ll
new file mode 100644
index 0000000000000..ea93a911a1ad0
--- /dev/null
+++ b/llvm/test/CodeGen/X86/ldexp-avx512.ll
@@ -0,0 +1,467 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
+; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512
+; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX512VL
+
+define half @test_half(half %x, i32 %exp) nounwind {
+; CHECK-LABEL: test_half:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    vcvtph2ps %xmm0, %xmm0
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
+; CHECK-NEXT:    popq %rax
+; CHECK-NEXT:    retq
+entry:
+  %r = tail call fast half @llvm.ldexp.f16.i32(half %x, i32 %exp)
+  ret half %r
+}
+declare half @llvm.ldexp.f16.i32(half, i32) memory(none)
+
+define float @test_float(float %x, i32 %exp) nounwind {
+; CHECK-LABEL: test_float:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    jmp ldexpf@PLT # TAILCALL
+entry:
+  %r = tail call fast float @ldexpf(float %x, i32 %exp)
+  ret float %r
+}
+declare float @ldexpf(float, i32) memory(none)
+
+define double @test_double(double %x, i32 %exp) nounwind {
+; CHECK-LABEL: test_double:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    jmp ldexp@PLT # TAILCALL
+entry:
+  %r = tail call fast double @ldexp(double %x, i32 %exp)
+  ret double %r
+}
+declare double @ldexp(double, i32) memory(none)
+
+define fp128 @testExpl(fp128 %x, i32 %exp) nounwind {
+; CHECK-LABEL: testExpl:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    jmp ldexpl@PLT # TAILCALL
+entry:
+  %r = tail call fast fp128 @ldexpl(fp128 %x, i32 %exp)
+  ret fp128 %r
+}
+declare fp128 @ldexpl(fp128, i32) memory(none)
+
+define <4 x float> @test_ldexp_4xfloat(<4 x float> %x, <4 x i32> %exp) nounwind {
+; CHECK-LABEL: test_ldexp_4xfloat:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    subq $56, %rsp
+; CHECK-NEXT:    vmovdqa %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovd %xmm1, %edi
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $1, %xmm0, %edi
+; CHECK-NEXT:    vmovshdup {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,1,3,3]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
+; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $2, %xmm0, %edi
+; CHECK-NEXT:    vpermilpd $1, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,0]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
+; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $3, %xmm0, %edi
+; CHECK-NEXT:    vpermilps $255, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[3,3,3,3]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1,2],xmm0[0]
+; CHECK-NEXT:    addq $56, %rsp
+; CHECK-NEXT:    retq
+  %r = call <4 x float> @llvm.ldexp.v4f32.v4i32(<4 x float> %x, <4 x i32> %exp)
+  ret <4 x float> %r
+}
+declare <4 x float> @llvm.ldexp.v4f32.v4i32(<4 x float>, <4 x i32>)
+
+define <2 x double> @test_ldexp_2xdouble(<2 x double> %x, <2 x i32> %exp) nounwind {
+; CHECK-LABEL: test_ldexp_2xdouble:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    subq $56, %rsp
+; CHECK-NEXT:    vmovdqa %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovd %xmm1, %edi
+; CHECK-NEXT:    callq ldexp@PLT
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $1, %xmm0, %edi
+; CHECK-NEXT:    vpermilpd $1, (%rsp), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,0]
+; CHECK-NEXT:    callq ldexp@PLT
+; CHECK-NEXT:    vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vunpcklpd {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; CHECK-NEXT:    addq $56, %rsp
+; CHECK-NEXT:    retq
+  %r = call <2 x double> @llvm.ldexp.v2f64.v2i32(<2 x double> %x, <2 x i32> %exp)
+  ret <2 x double> %r
+}
+declare <2 x double> @llvm.ldexp.v2f64.v2i32(<2 x double>, <2 x i32>)
+
+define <8 x float> @test_ldexp_8xfloat(<8 x float> %x, <8 x i32> %exp) nounwind {
+; CHECK-LABEL: test_ldexp_8xfloat:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    subq $120, %rsp
+; CHECK-NEXT:    vmovdqu %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
+; CHECK-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
+; CHECK-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vextracti128 $1, %ymm1, %xmm1
+; CHECK-NEXT:    vmovdqa %xmm1, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovd %xmm1, %edi
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $1, %xmm0, %edi
+; CHECK-NEXT:    vmovshdup {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,1,3,3]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $2, %xmm0, %edi
+; CHECK-NEXT:    vpermilpd $1, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,0]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $3, %xmm0, %edi
+; CHECK-NEXT:    vpermilps $255, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[3,3,3,3]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1,2],xmm0[0]
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
+; CHECK-NEXT:    vmovd %xmm0, %edi
+; CHECK-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
+; CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
+; CHECK-NEXT:    vextractps $1, %xmm0, %edi
+; CHECK-NEXT:    vmovshdup {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,1,3,3]
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
+; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
+; CHECK-NEXT:    vextractps $2, %xmm0, %edi
+; CHECK-NEXT:    vpermilpd $1, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,0]
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
+; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
+; CHECK-NEXT:    vextractps $3, %xmm0, %edi
+; CHECK-NEXT:    vpermilps $255, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[3,3,3,3]
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1,2],xmm0[0]
+; CHECK-NEXT:    vinsertf128 $1, {{[-0-9]+}}(%r{{[sb]}}p), %ymm0, %ymm0 # 16-byte Folded Reload
+; CHECK-NEXT:    addq $120, %rsp
+; CHECK-NEXT:    retq
+  %r = call <8 x float> @llvm.ldexp.v8f32.v8i32(<8 x float> %x, <8 x i32> %exp)
+  ret <8 x float> %r
+}
+declare <8 x float> @llvm.ldexp.v8f32.v8i32(<8 x float>, <8 x i32>)
+
+define <4 x double> @test_ldexp_4xdouble(<4 x double> %x, <4 x i32> %exp) nounwind {
+; CHECK-LABEL: test_ldexp_4xdouble:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    subq $88, %rsp
+; CHECK-NEXT:    vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
+; CHECK-NEXT:    vextractps $2, %xmm1, %edi
+; CHECK-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexp@PLT
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $3, %xmm0, %edi
+; CHECK-NEXT:    vpermilpd $1, (%rsp), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,0]
+; CHECK-NEXT:    callq ldexp@PLT
+; CHECK-NEXT:    vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vunpcklpd {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; CHECK-NEXT:    vmovapd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vmovd %xmm0, %edi
+; CHECK-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
+; CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexp@PLT
+; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $1, %xmm0, %edi
+; CHECK-NEXT:    vpermilpd $1, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,0]
+; CHECK-NEXT:    callq ldexp@PLT
+; CHECK-NEXT:    vmovapd (%rsp), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vunpcklpd {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; CHECK-NEXT:    vinsertf128 $1, {{[-0-9]+}}(%r{{[sb]}}p), %ymm0, %ymm0 # 16-byte Folded Reload
+; CHECK-NEXT:    addq $88, %rsp
+; CHECK-NEXT:    retq
+  %r = call <4 x double> @llvm.ldexp.v4f64.v4i32(<4 x double> %x, <4 x i32> %exp)
+  ret <4 x double> %r
+}
+declare <4 x double> @llvm.ldexp.v4f64.v4i32(<4 x double>, <4 x i32>)
+
+define <16 x float> @test_ldexp_16xfloat(<16 x float> %x, <16 x i32> %exp) nounwind {
+; CHECK-LABEL: test_ldexp_16xfloat:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    subq $216, %rsp
+; CHECK-NEXT:    vmovdqu64 %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
+; CHECK-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
+; CHECK-NEXT:    vextractf32x4 $3, %zmm0, %xmm0
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vextracti32x4 $3, %zmm1, %xmm1
+; CHECK-NEXT:    vmovdqa %xmm1, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovd %xmm1, %edi
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $1, %xmm0, %edi
+; CHECK-NEXT:    vmovshdup {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,1,3,3]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $2, %xmm0, %edi
+; CHECK-NEXT:    vpermilpd $1, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,0]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $3, %xmm0, %edi
+; CHECK-NEXT:    vpermilps $255, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[3,3,3,3]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1,2],xmm0[0]
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
+; CHECK-NEXT:    vextractf32x4 $2, %zmm0, %xmm1
+; CHECK-NEXT:    vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovdqu64 {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
+; CHECK-NEXT:    vextracti32x4 $2, %zmm0, %xmm0
+; CHECK-NEXT:    vmovdqa %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovd %xmm0, %edi
+; CHECK-NEXT:    vmovaps %xmm1, %xmm0
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $1, %xmm0, %edi
+; CHECK-NEXT:    vmovshdup {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,1,3,3]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $2, %xmm0, %edi
+; CHECK-NEXT:    vpermilpd $1, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,0]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $3, %xmm0, %edi
+; CHECK-NEXT:    vpermilps $255, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[3,3,3,3]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1,2],xmm0[0]
+; CHECK-NEXT:    vinsertf128 $1, {{[-0-9]+}}(%r{{[sb]}}p), %ymm0, %ymm0 # 16-byte Folded Reload
+; CHECK-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
+; CHECK-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
+; CHECK-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; CHECK-NEXT:    vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovdqu64 {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
+; CHECK-NEXT:    vextracti128 $1, %ymm0, %xmm0
+; CHECK-NEXT:    vmovdqa %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovd %xmm0, %edi
+; CHECK-NEXT:    vmovaps %xmm1, %xmm0
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $1, %xmm0, %edi
+; CHECK-NEXT:    vmovshdup {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,1,3,3]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $2, %xmm0, %edi
+; CHECK-NEXT:    vpermilpd $1, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,0]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vextractps $3, %xmm0, %edi
+; CHECK-NEXT:    vpermilps $255, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[3,3,3,3]
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1,2],xmm0[0]
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovdqu64 {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
+; CHECK-NEXT:    vmovd %xmm0, %edi
+; CHECK-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
+; CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 killed $zmm0
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
+; CHECK-NEXT:    vextractps $1, %xmm0, %edi
+; CHECK-NEXT:    vmovshdup {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,1,3,3]
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
+; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
+; CHECK-NEXT:    vextractps $2, %xmm0, %edi
+; CHECK-NEXT:    vpermilpd $1, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,0]
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
+; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
+; CHECK-NEXT:    vextractps $3, %xmm0, %edi
+; CHECK-NEXT:    vpermilps $255, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[3,3,3,3]
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq ldexpf@PLT
+; CHECK-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1,2],xmm0[0]
+; CHECK-NEXT:    vinsertf128 $1, {{[-0-9]+}}(%r{{[sb]}}p), %ymm0, %ymm0 # 16-byte Folded Reload
+; CHECK-NEXT:    vinsertf64x4 $1, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 32-byte Folded Reload
+; CHECK-NEXT:    addq $216, %rsp
+; CHECK-NEXT:    retq
+  %r = call <16 x float> @llvm.ldexp.v16f32.v16i32(<16 x float> %x, <16 x i32> %exp)
+  ret <16 x float> %r
+}
+declare <16 x float> @llvm.ldexp.v16f32.v16i32(<16 x float>, <16 x i32>)
+
+define <8 x double> @test_ldexp_8xdouble(<8 x double> %x, <8 x i32> %exp) nounwind {
+; CHECK-LABEL: test_ldexp_8xdouble:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    subq $184, %rsp
+; CHECK-NEXT:    vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
+; CHECK-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
+; CHECK-NEXT:    vextractf32x4 $3, %zmm0, %xmm0
+; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    vextractf128 $1...
[truncated]

llvm-ci · 2025-10-30T12:42:04Z

LLVM Buildbot has detected a new failure on builder lldb-remote-linux-ubuntu running on as-builder-9 while building llvm at step 16 "test-check-lldb-api".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/195/builds/16674

Here is the relevant piece of the build log for the reference

Step 16 (test-check-lldb-api) failure: Test just built components: check-lldb-api completed (failure)
...
PASS: lldb-api :: types/TestIntegerType.py (1309 of 1318)
PASS: lldb-api :: types/TestRecursiveTypes.py (1310 of 1318)
UNSUPPORTED: lldb-api :: windows/launch/missing-dll/TestMissingDll.py (1311 of 1318)
PASS: lldb-api :: types/TestIntegerTypeExpr.py (1312 of 1318)
UNSUPPORTED: lldb-api :: windows/launch/replace-dll/TestReplaceDLL.py (1313 of 1318)
PASS: lldb-api :: types/TestShortType.py (1314 of 1318)
PASS: lldb-api :: types/TestShortTypeExpr.py (1315 of 1318)
PASS: lldb-api :: types/TestLongTypes.py (1316 of 1318)
PASS: lldb-api :: types/TestLongTypesExpr.py (1317 of 1318)
TIMEOUT: lldb-api :: python_api/process/cancel_attach/TestCancelAttach.py (1318 of 1318)
******************** TEST 'lldb-api :: python_api/process/cancel_attach/TestCancelAttach.py' FAILED ********************
Script:
--
/usr/bin/python3.12 /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/llvm-project/lldb/test/API/dotest.py -u CXXFLAGS -u CFLAGS --env LLVM_LIBS_DIR=/home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/./lib --env LLVM_INCLUDE_DIR=/home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/include --env LLVM_TOOLS_DIR=/home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/./bin --libcxx-include-dir /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/include/c++/v1 --libcxx-include-target-dir /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/include/aarch64-unknown-linux-gnu/c++/v1 --libcxx-library-dir /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/./lib/aarch64-unknown-linux-gnu --arch aarch64 --build-dir /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/lldb-test-build.noindex --lldb-module-cache-dir /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/lldb-test-build.noindex/module-cache-lldb/lldb-api --clang-module-cache-dir /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/lldb-test-build.noindex/module-cache-clang/lldb-api --executable /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/./bin/lldb --compiler /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/bin/clang --dsymutil /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/./bin/dsymutil --make /usr/bin/gmake --llvm-tools-dir /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/./bin --lldb-obj-root /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/tools/lldb --lldb-libs-dir /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/./lib --cmake-build-type Release --platform-url connect://jetson-agx-2198.lab.llvm.org:1234 --platform-working-dir /home/ubuntu/lldb-tests --sysroot /mnt/fs/jetson-agx-ubuntu --env ARCH_CFLAGS=-mcpu=cortex-a78 --platform-name remote-linux --skip-category=lldb-server /home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/llvm-project/lldb/test/API/python_api/process/cancel_attach -p TestCancelAttach.py
--
Exit Code: -9
Timeout: Reached timeout of 600 seconds

Command Output (stdout):
--
lldb version 22.0.0git (https://github.com/llvm/llvm-project.git revision 3b30010303909efa01ac4d4fc018ad166e3b772d)
  clang revision 3b30010303909efa01ac4d4fc018ad166e3b772d
  llvm revision 3b30010303909efa01ac4d4fc018ad166e3b772d

--
Command Output (stderr):
--
WARNING:root:Custom libc++ is not supported for remote runs: ignoring --libcxx arguments
FAIL: LLDB (/home/buildbot/worker/as-builder-9/lldb-remote-linux-ubuntu/build/bin/clang-aarch64) :: test_scripted_implementation (TestCancelAttach.AttachCancelTestCase.test_scripted_implementation)

--

********************
Slowest Tests:
--------------------------------------------------------------------------
600.04s: lldb-api :: python_api/process/cancel_attach/TestCancelAttach.py
123.27s: lldb-api :: functionalities/progress_reporting/TestProgressReporting.py
70.23s: lldb-api :: commands/process/attach/TestProcessAttach.py
64.56s: lldb-api :: functionalities/data-formatter/data-formatter-stl/libcxx-simulators/string/TestDataFormatterLibcxxStringSimulator.py
60.73s: lldb-api :: commands/command/script_alias/TestCommandScriptAlias.py
35.37s: lldb-api :: functionalities/single-thread-step/TestSingleThreadStepTimeout.py
34.70s: lldb-api :: functionalities/completion/TestCompletion.py
24.56s: lldb-api :: commands/statistics/basic/TestStats.py
23.10s: lldb-api :: python_api/watchpoint/watchlocation/TestTargetWatchAddress.py
21.29s: lldb-api :: functionalities/gdb_remote_client/TestGDBRemoteClient.py
20.60s: lldb-api :: functionalities/gdb_remote_client/TestPlatformClient.py
18.52s: lldb-api :: functionalities/thread/state/TestThreadStates.py
18.44s: lldb-api :: commands/dwim-print/TestDWIMPrint.py
14.29s: lldb-api :: commands/expression/expr-in-syscall/TestExpressionInSyscall.py

Pulled out of the abandoned patch llvm#69710 to act as a baseline for llvm#165694

[X86] Add ldexp test coverage for avx512 targets

634b0f4

Pulled out of the abandoned patch llvm#69710 to act as a baseline for llvm#165694

RKSimon enabled auto-merge (squash) October 30, 2025 11:33

llvmbot added the backend:X86 label Oct 30, 2025

RKSimon merged commit 3b30010 into llvm:main Oct 30, 2025
11 of 12 checks passed

RKSimon deleted the x86-ldexp-avx512-tests branch October 30, 2025 12:11

aokblast pushed a commit to aokblast/llvm-project that referenced this pull request Oct 30, 2025

[X86] Add ldexp test coverage for avx512 targets (llvm#165698)

5df3f68

Pulled out of the abandoned patch llvm#69710 to act as a baseline for llvm#165694

luciechoi pushed a commit to luciechoi/llvm-project that referenced this pull request Nov 1, 2025

[X86] Add ldexp test coverage for avx512 targets (llvm#165698)

23666da

Pulled out of the abandoned patch llvm#69710 to act as a baseline for llvm#165694

DEBADRIBASAK pushed a commit to DEBADRIBASAK/llvm-project that referenced this pull request Nov 3, 2025

[X86] Add ldexp test coverage for avx512 targets (llvm#165698)

23af488

Pulled out of the abandoned patch llvm#69710 to act as a baseline for llvm#165694

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[X86] Add ldexp test coverage for avx512 targets#165698

[X86] Add ldexp test coverage for avx512 targets#165698
RKSimon merged 1 commit intollvm:mainfrom
RKSimon:x86-ldexp-avx512-tests

RKSimon commented Oct 30, 2025

Uh oh!

llvmbot commented Oct 30, 2025

Uh oh!

Uh oh!

llvm-ci commented Oct 30, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

RKSimon commented Oct 30, 2025

Uh oh!

llvmbot commented Oct 30, 2025

Uh oh!

Uh oh!

llvm-ci commented Oct 30, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants