[x86] inline calls to fmaxf / llvm.maxnum.f32 using maxss (PR24475)

[oota-llvm.git] / test / CodeGen / X86 / fmaxnum.ll

diff --git a/test/CodeGen/X86/fmaxnum.ll b/test/CodeGen/X86/fmaxnum.ll
index 19041c9ff677e2d2be45f8f87395f0bcee4c7be9..ca80eee1360fa30fa375f326654cc1be6c349494 100644 (file)
--- a/test/CodeGen/X86/fmaxnum.ll
+++ b/test/CodeGen/X86/fmaxnum.ll
@@ -16,12 +16,34 @@ declare <8 x double> @llvm.maxnum.v8f64(<8 x double>, <8 x double>)
 
 
 ; CHECK-LABEL: @test_fmaxf
-; CHECK: jmp fmaxf
+; SSE:         movaps %xmm0, %xmm2
+; SSE-NEXT:    cmpunordss %xmm2, %xmm2
+; SSE-NEXT:    movaps %xmm2, %xmm3
+; SSE-NEXT:    andps %xmm1, %xmm3
+; SSE-NEXT:    maxss %xmm0, %xmm1
+; SSE-NEXT:    andnps %xmm1, %xmm2
+; SSE-NEXT:    orps %xmm3, %xmm2
+; SSE-NEXT:    movaps %xmm2, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX:         vmaxss %xmm0, %xmm1, %xmm2
+; AVX-NEXT:    vcmpunordss %xmm0, %xmm0, %xmm0
+; AVX-NEXT:    vblendvps %xmm0, %xmm1, %xmm2, %xmm0
+; AVX-NEXT:    retq
 define float @test_fmaxf(float %x, float %y) {
   %z = call float @fmaxf(float %x, float %y) readnone
   ret float %z
 }
 
+; CHECK-LABEL: @test_fmaxf_minsize
+; CHECK:       jmp fmaxf
+define float @test_fmaxf_minsize(float %x, float %y) minsize {
+  %z = call float @fmaxf(float %x, float %y) readnone
+  ret float %z
+}
+
+; FIXME: Doubles should be inlined similarly to floats.
+
 ; CHECK-LABEL: @test_fmax
 ; CHECK: jmp fmax
 define double @test_fmax(double %x, double %y) {
@@ -37,12 +59,27 @@ define x86_fp80 @test_fmaxl(x86_fp80 %x, x86_fp80 %y) {
 }
 
 ; CHECK-LABEL: @test_intrinsic_fmaxf
-; CHECK: jmp fmaxf
+; SSE:         movaps %xmm0, %xmm2
+; SSE-NEXT:    cmpunordss %xmm2, %xmm2
+; SSE-NEXT:    movaps %xmm2, %xmm3
+; SSE-NEXT:    andps %xmm1, %xmm3
+; SSE-NEXT:    maxss %xmm0, %xmm1
+; SSE-NEXT:    andnps %xmm1, %xmm2
+; SSE-NEXT:    orps %xmm3, %xmm2
+; SSE-NEXT:    movaps %xmm2, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX:         vmaxss %xmm0, %xmm1, %xmm2
+; AVX-NEXT:    vcmpunordss %xmm0, %xmm0, %xmm0
+; AVX-NEXT:    vblendvps %xmm0, %xmm1, %xmm2, %xmm0
+; AVX-NEXT:    retq
 define float @test_intrinsic_fmaxf(float %x, float %y) {
   %z = call float @llvm.maxnum.f32(float %x, float %y) readnone
   ret float %z
 }
 
+; FIXME: Doubles should be inlined similarly to floats.
+
 ; CHECK-LABEL: @test_intrinsic_fmax
 ; CHECK: jmp fmax
 define double @test_intrinsic_fmax(double %x, double %y) {
@@ -57,122 +94,159 @@ define x86_fp80 @test_intrinsic_fmaxl(x86_fp80 %x, x86_fp80 %y) {
   ret x86_fp80 %z
 }
 
+; FIXME: This should not be doing 4 scalar ops on a 2 element vector.
+; FIXME: This should use vector ops (maxps / cmpps).
+
 ; CHECK-LABEL: @test_intrinsic_fmax_v2f32
-; SSE:         movaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
-; SSE-NEXT:    movaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
-; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[3,1,2,3]
-; SSE-NEXT:    shufps {{.*#+}} xmm1 = xmm1[3,1,2,3]
-; SSE-NEXT:    callq fmaxf
-; SSE-NEXT:    movaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
-; SSE-NEXT:    movaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
-; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[1,1,2,3]
-; SSE-NEXT:    movaps {{[0-9]+}}(%rsp), %xmm1 # 16-byte Reload
-; SSE-NEXT:    shufps {{.*#+}} xmm1 = xmm1[1,1,2,3]
-; SSE-NEXT:    callq fmaxf
-; SSE-NEXT:    unpcklps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
-; SSE:         movaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
-; SSE-NEXT:    movaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
-; SSE-NEXT:    movaps {{[0-9]+}}(%rsp), %xmm1 # 16-byte Reload
-; SSE-NEXT:    callq fmaxf
-; SSE-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
-; SSE-NEXT:    movapd {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
-; SSE-NEXT:    shufpd {{.*#+}} xmm0 = xmm0[1,0]
-; SSE-NEXT:    movapd {{[0-9]+}}(%rsp), %xmm1 # 16-byte Reload
+; SSE:         movaps %xmm1, %xmm2
+; SSE-NEXT:    shufps {{.*#+}} xmm2 = xmm2[3,1,2,3]
+; SSE-NEXT:    movaps %xmm0, %xmm3
+; SSE-NEXT:    shufps {{.*#+}} xmm3 = xmm3[3,1,2,3]
+; SSE-NEXT:    movaps %xmm3, %xmm4
+; SSE-NEXT:    cmpunordss %xmm4, %xmm4
+; SSE-NEXT:    movaps %xmm4, %xmm5
+; SSE-NEXT:    andps %xmm2, %xmm5
+; SSE-NEXT:    maxss %xmm3, %xmm2
+; SSE-NEXT:    andnps %xmm2, %xmm4
+; SSE-NEXT:    orps %xmm5, %xmm4
+; SSE-NEXT:    movaps %xmm1, %xmm2
+; SSE-NEXT:    shufps {{.*#+}} xmm2 = xmm2[1,1,2,3]
+; SSE-NEXT:    movaps %xmm0, %xmm5
+; SSE-NEXT:    shufps {{.*#+}} xmm5 = xmm5[1,1,2,3]
+; SSE-NEXT:    movaps %xmm5, %xmm3
+; SSE-NEXT:    cmpunordss %xmm3, %xmm3
+; SSE-NEXT:    movaps %xmm3, %xmm6
+; SSE-NEXT:    andps %xmm2, %xmm6
+; SSE-NEXT:    maxss %xmm5, %xmm2
+; SSE-NEXT:    andnps %xmm2, %xmm3
+; SSE-NEXT:    orps %xmm6, %xmm3
+; SSE-NEXT:    unpcklps {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
+; SSE-NEXT:    movaps %xmm0, %xmm2
+; SSE-NEXT:    cmpunordss %xmm2, %xmm2
+; SSE-NEXT:    movaps %xmm2, %xmm4
+; SSE-NEXT:    andps %xmm1, %xmm4
+; SSE-NEXT:    movaps %xmm1, %xmm5
+; SSE-NEXT:    maxss %xmm0, %xmm5
+; SSE-NEXT:    andnps %xmm5, %xmm2
+; SSE-NEXT:    orps %xmm4, %xmm2
 ; SSE-NEXT:    shufpd {{.*#+}} xmm1 = xmm1[1,0]
-; SSE-NEXT:    callq fmaxf
-; SSE-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
-; SSE-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
-; SSE-NEXT:    unpcklps {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
-; SSE:         movaps %xmm1, %xmm0
-; SSE-NEXT:    addq $72, %rsp
+; SSE-NEXT:    shufpd {{.*#+}} xmm0 = xmm0[1,0]
+; SSE-NEXT:    movapd %xmm0, %xmm4
+; SSE-NEXT:    cmpunordss %xmm4, %xmm4
+; SSE-NEXT:    movaps %xmm4, %xmm5
+; SSE-NEXT:    andps %xmm1, %xmm5
+; SSE-NEXT:    maxss %xmm0, %xmm1
+; SSE-NEXT:    andnps %xmm1, %xmm4
+; SSE-NEXT:    orps %xmm5, %xmm4
+; SSE-NEXT:    unpcklps {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
+; SSE-NEXT:    unpcklps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
+; SSE-NEXT:    movaps %xmm2, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX:         vmovaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
-; AVX-NEXT:    vmovaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
-; AVX-NEXT:    callq fmaxf
-; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
-; AVX-NEXT:    vmovshdup {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
-; AVX:         vmovshdup {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
-; AVX:         callq fmaxf
-; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
-; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
-; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
-; AVX-NEXT:    vpermilpd $1, {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
-; AVX:         vpermilpd $1, {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
-; AVX:         callq fmaxf
-; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
-; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
-; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
-; AVX-NEXT:    vpermilps $231, {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
-; AVX:         vpermilps $231, {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
-; AVX:         callq fmaxf
-; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
-; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1,2],xmm0[0]
-; AVX-NEXT:    addq $56, %rsp
+; AVX:         vmaxss %xmm0, %xmm1, %xmm2
+; AVX-NEXT:    vcmpunordss %xmm0, %xmm0, %xmm3
+; AVX-NEXT:    vblendvps %xmm3, %xmm1, %xmm2, %xmm2
+; AVX-NEXT:    vmovshdup {{.*#+}} xmm3 = xmm0[1,1,3,3]
+; AVX-NEXT:    vmovshdup {{.*#+}} xmm4 = xmm1[1,1,3,3]
+; AVX-NEXT:    vmaxss %xmm3, %xmm4, %xmm5
+; AVX-NEXT:    vcmpunordss %xmm3, %xmm3, %xmm3
+; AVX-NEXT:    vblendvps %xmm3, %xmm4, %xmm5, %xmm3
+; AVX-NEXT:    vinsertps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[2,3]
+; AVX-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm0[1,0]
+; AVX-NEXT:    vpermilpd {{.*#+}} xmm4 = xmm1[1,0]
+; AVX-NEXT:    vmaxss %xmm3, %xmm4, %xmm5
+; AVX-NEXT:    vcmpunordss %xmm3, %xmm3, %xmm3
+; AVX-NEXT:    vblendvps %xmm3, %xmm4, %xmm5, %xmm3
+; AVX-NEXT:    vinsertps {{.*#+}} xmm2 = xmm2[0,1],xmm3[0],xmm2[3]
+; AVX-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
+; AVX-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[3,1,2,3]
+; AVX-NEXT:    vmaxss %xmm0, %xmm1, %xmm3
+; AVX-NEXT:    vcmpunordss %xmm0, %xmm0, %xmm0
+; AVX-NEXT:    vblendvps %xmm0, %xmm1, %xmm3, %xmm0
+; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm2[0,1,2],xmm0[0]
 ; AVX-NEXT:    retq
 define <2 x float> @test_intrinsic_fmax_v2f32(<2 x float> %x, <2 x float> %y) {
   %z = call <2 x float> @llvm.maxnum.v2f32(<2 x float> %x, <2 x float> %y) readnone
   ret <2 x float> %z
 }
 
+; FIXME: This should use vector ops (maxps / cmpps).
+
 ; CHECK-LABEL: @test_intrinsic_fmax_v4f32
-; SSE:         movaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
-; SSE-NEXT:    movaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
-; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[3,1,2,3]
-; SSE-NEXT:    shufps {{.*#+}} xmm1 = xmm1[3,1,2,3]
-; SSE-NEXT:    callq fmaxf
-; SSE-NEXT:    movaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
-; SSE-NEXT:    movaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
-; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[1,1,2,3]
-; SSE-NEXT:    movaps {{[0-9]+}}(%rsp), %xmm1 # 16-byte Reload
-; SSE-NEXT:    shufps {{.*#+}} xmm1 = xmm1[1,1,2,3]
-; SSE-NEXT:    callq fmaxf
-; SSE-NEXT:    unpcklps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
-; SSE:         movaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
-; SSE-NEXT:    movaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
-; SSE-NEXT:    movaps {{[0-9]+}}(%rsp), %xmm1 # 16-byte Reload
-; SSE-NEXT:    callq fmaxf
-; SSE-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
-; SSE-NEXT:    movapd {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
-; SSE-NEXT:    shufpd {{.*#+}} xmm0 = xmm0[1,0]
-; SSE-NEXT:    movapd {{[0-9]+}}(%rsp), %xmm1 # 16-byte Reload
+; SSE:         movaps %xmm1, %xmm2
+; SSE-NEXT:    shufps {{.*#+}} xmm2 = xmm2[3,1,2,3]
+; SSE-NEXT:    movaps %xmm0, %xmm3
+; SSE-NEXT:    shufps {{.*#+}} xmm3 = xmm3[3,1,2,3]
+; SSE-NEXT:    movaps %xmm3, %xmm4
+; SSE-NEXT:    cmpunordss %xmm4, %xmm4
+; SSE-NEXT:    movaps %xmm4, %xmm5
+; SSE-NEXT:    andps %xmm2, %xmm5
+; SSE-NEXT:    maxss %xmm3, %xmm2
+; SSE-NEXT:    andnps %xmm2, %xmm4
+; SSE-NEXT:    orps %xmm5, %xmm4
+; SSE-NEXT:    movaps %xmm1, %xmm2
+; SSE-NEXT:    shufps {{.*#+}} xmm2 = xmm2[1,1,2,3]
+; SSE-NEXT:    movaps %xmm0, %xmm5
+; SSE-NEXT:    shufps {{.*#+}} xmm5 = xmm5[1,1,2,3]
+; SSE-NEXT:    movaps %xmm5, %xmm3
+; SSE-NEXT:    cmpunordss %xmm3, %xmm3
+; SSE-NEXT:    movaps %xmm3, %xmm6
+; SSE-NEXT:    andps %xmm2, %xmm6
+; SSE-NEXT:    maxss %xmm5, %xmm2
+; SSE-NEXT:    andnps %xmm2, %xmm3
+; SSE-NEXT:    orps %xmm6, %xmm3
+; SSE-NEXT:    unpcklps {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
+; SSE-NEXT:    movaps %xmm0, %xmm2
+; SSE-NEXT:    cmpunordss %xmm2, %xmm2
+; SSE-NEXT:    movaps %xmm2, %xmm4
+; SSE-NEXT:    andps %xmm1, %xmm4
+; SSE-NEXT:    movaps %xmm1, %xmm5
+; SSE-NEXT:    maxss %xmm0, %xmm5
+; SSE-NEXT:    andnps %xmm5, %xmm2
+; SSE-NEXT:    orps %xmm4, %xmm2
 ; SSE-NEXT:    shufpd {{.*#+}} xmm1 = xmm1[1,0]
-; SSE-NEXT:    callq fmaxf
-; SSE-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
-; SSE-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
-; SSE-NEXT:    unpcklps {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
-; SSE:         movaps %xmm1, %xmm0
-; SSE-NEXT:    addq $72, %rsp
+; SSE-NEXT:    shufpd {{.*#+}} xmm0 = xmm0[1,0]
+; SSE-NEXT:    movapd %xmm0, %xmm4
+; SSE-NEXT:    cmpunordss %xmm4, %xmm4
+; SSE-NEXT:    movaps %xmm4, %xmm5
+; SSE-NEXT:    andps %xmm1, %xmm5
+; SSE-NEXT:    maxss %xmm0, %xmm1
+; SSE-NEXT:    andnps %xmm1, %xmm4
+; SSE-NEXT:    orps %xmm5, %xmm4
+; SSE-NEXT:    unpcklps {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
+; SSE-NEXT:    unpcklps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
+; SSE-NEXT:    movaps %xmm2, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX:         vmovaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
-; AVX-NEXT:    vmovaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
-; AVX-NEXT:    callq fmaxf
-; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
-; AVX-NEXT:    vmovshdup {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
-; AVX:         vmovshdup {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
-; AVX:         callq fmaxf
-; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
-; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
-; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
-; AVX-NEXT:    vpermilpd $1, {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
-; AVX:         vpermilpd $1, {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
-; AVX:         callq fmaxf
-; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
-; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
-; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
-; AVX-NEXT:    vpermilps $231, {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
-; AVX:         vpermilps $231, {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
-; AVX:         callq fmaxf
-; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
-; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1,2],xmm0[0]
-; AVX-NEXT:    addq $56, %rsp
+; AVX:         vmaxss %xmm0, %xmm1, %xmm2
+; AVX-NEXT:    vcmpunordss %xmm0, %xmm0, %xmm3
+; AVX-NEXT:    vblendvps %xmm3, %xmm1, %xmm2, %xmm2
+; AVX-NEXT:    vmovshdup {{.*#+}} xmm3 = xmm0[1,1,3,3]
+; AVX-NEXT:    vmovshdup {{.*#+}} xmm4 = xmm1[1,1,3,3]
+; AVX-NEXT:    vmaxss %xmm3, %xmm4, %xmm5
+; AVX-NEXT:    vcmpunordss %xmm3, %xmm3, %xmm3
+; AVX-NEXT:    vblendvps %xmm3, %xmm4, %xmm5, %xmm3
+; AVX-NEXT:    vinsertps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[2,3]
+; AVX-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm0[1,0]
+; AVX-NEXT:    vpermilpd {{.*#+}} xmm4 = xmm1[1,0]
+; AVX-NEXT:    vmaxss %xmm3, %xmm4, %xmm5
+; AVX-NEXT:    vcmpunordss %xmm3, %xmm3, %xmm3
+; AVX-NEXT:    vblendvps %xmm3, %xmm4, %xmm5, %xmm3
+; AVX-NEXT:    vinsertps {{.*#+}} xmm2 = xmm2[0,1],xmm3[0],xmm2[3]
+; AVX-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
+; AVX-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[3,1,2,3]
+; AVX-NEXT:    vmaxss %xmm0, %xmm1, %xmm3
+; AVX-NEXT:    vcmpunordss %xmm0, %xmm0, %xmm0
+; AVX-NEXT:    vblendvps %xmm0, %xmm1, %xmm3, %xmm0
+; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm2[0,1,2],xmm0[0]
 ; AVX-NEXT:    retq
 define <4 x float> @test_intrinsic_fmax_v4f32(<4 x float> %x, <4 x float> %y) {
   %z = call <4 x float> @llvm.maxnum.v4f32(<4 x float> %x, <4 x float> %y) readnone
   ret <4 x float> %z
 }
 
+; FIXME: Vector of doubles should be inlined similarly to vector of floats.
+
 ; CHECK-LABEL: @test_intrinsic_fmax_v2f64
 ; CHECK: callq fmax
 ; CHECK: callq fmax
@@ -181,6 +255,8 @@ define <2 x double> @test_intrinsic_fmax_v2f64(<2 x double> %x, <2 x double> %y)
   ret <2 x double> %z
 }
 
+; FIXME: Vector of doubles should be inlined similarly to vector of floats.
+
 ; CHECK-LABEL: @test_intrinsic_fmax_v4f64
 ; CHECK: callq fmax
 ; CHECK: callq fmax
@@ -191,6 +267,8 @@ define <4 x double> @test_intrinsic_fmax_v4f64(<4 x double> %x, <4 x double> %y)
   ret <4 x double> %z
 }
 
+; FIXME: Vector of doubles should be inlined similarly to vector of floats.
+
 ; CHECK-LABEL: @test_intrinsic_fmax_v8f64
 ; CHECK: callq fmax
 ; CHECK: callq fmax