summaryrefslogtreecommitdiff
path: root/test/Transforms/ConstProp
diff options
context:
space:
mode:
Diffstat (limited to 'test/Transforms/ConstProp')
-rw-r--r--test/Transforms/ConstProp/calls-math-finite.ll83
-rw-r--r--test/Transforms/ConstProp/calls.ll206
-rw-r--r--test/Transforms/ConstProp/sse.ll208
3 files changed, 291 insertions, 206 deletions
diff --git a/test/Transforms/ConstProp/calls-math-finite.ll b/test/Transforms/ConstProp/calls-math-finite.ll
new file mode 100644
index 0000000000000..00041f3e4a4b0
--- /dev/null
+++ b/test/Transforms/ConstProp/calls-math-finite.ll
@@ -0,0 +1,83 @@
+; RUN: opt < %s -constprop -S | FileCheck %s
+
+; Test to verify constant folding can occur when math
+; routines are mapped to the __<func>_finite versions
+; of functions due to __FINITE_MATH_ONLY__ being
+; enabled on headers. All calls should constant
+; fold away in this test.
+
+declare double @__acos_finite(double) #0
+declare float @__acosf_finite(float) #0
+declare double @__asin_finite(double) #0
+declare float @__asinf_finite(float) #0
+declare double @__atan2_finite(double, double) #0
+declare float @__atan2f_finite(float, float) #0
+declare double @__cosh_finite(double) #0
+declare float @__coshf_finite(float) #0
+declare double @__exp2_finite(double) #0
+declare float @__exp2f_finite(float) #0
+declare double @__exp_finite(double) #0
+declare float @__expf_finite(float) #0
+declare double @__log10_finite(double) #0
+declare float @__log10f_finite(float) #0
+declare double @__log_finite(double) #0
+declare float @__logf_finite(float) #0
+declare double @__pow_finite(double, double) #0
+declare float @__powf_finite(float, float) #0
+declare double @__sinh_finite(double) #0
+declare float @__sinhf_finite(float) #0
+
+attributes #0 = { nounwind readnone }
+
+define void @T() {
+; CHECK-LABEL: @T(
+
+; CHECK-NOT: call
+; CHECK: ret
+
+ %slot = alloca double
+ %slotf = alloca float
+
+ %ACOS = call fast double @__acos_finite(double 1.000000e+00)
+ store double %ACOS, double* %slot
+ %ASIN = call fast double @__asin_finite(double 1.000000e+00)
+ store double %ASIN, double* %slot
+ %ATAN2 = call fast double @__atan2_finite(double 3.000000e+00, double 4.000000e+00)
+ store double %ATAN2, double* %slot
+ %COSH = call fast double @__cosh_finite(double 3.000000e+00)
+ store double %COSH, double* %slot
+ %EXP = call fast double @__exp_finite(double 3.000000e+00)
+ store double %EXP, double* %slot
+ %EXP2 = call fast double @__exp2_finite(double 3.000000e+00)
+ store double %EXP2, double* %slot
+ %LOG = call fast double @__log_finite(double 3.000000e+00)
+ store double %LOG, double* %slot
+ %LOG10 = call fast double @__log10_finite(double 3.000000e+00)
+ store double %LOG10, double* %slot
+ %POW = call fast double @__pow_finite(double 1.000000e+00, double 4.000000e+00)
+ store double %POW, double* %slot
+ %SINH = call fast double @__sinh_finite(double 3.000000e+00)
+ store double %SINH, double* %slot
+
+ %ACOSF = call fast float @__acosf_finite(float 1.000000e+00)
+ store float %ACOSF, float* %slotf
+ %ASINF = call fast float @__asinf_finite(float 1.000000e+00)
+ store float %ASINF, float* %slotf
+ %ATAN2F = call fast float @__atan2f_finite(float 3.000000e+00, float 4.000000e+00)
+ store float %ATAN2F, float* %slotf
+ %COSHF = call fast float @__coshf_finite(float 3.000000e+00)
+ store float %COSHF, float* %slotf
+ %EXPF = call fast float @__expf_finite(float 3.000000e+00)
+ store float %EXPF, float* %slotf
+ %EXP2F = call fast float @__exp2f_finite(float 3.000000e+00)
+ store float %EXP2F, float* %slotf
+ %LOGF = call fast float @__logf_finite(float 3.000000e+00)
+ store float %LOGF, float* %slotf
+ %LOG10F = call fast float @__log10f_finite(float 3.000000e+00)
+ store float %LOG10F, float* %slotf
+ %POWF = call fast float @__powf_finite(float 3.000000e+00, float 4.000000e+00)
+ store float %POWF, float* %slotf
+ %SINHF = call fast float @__sinhf_finite(float 3.000000e+00)
+ store float %SINHF, float* %slotf
+ ret void
+}
diff --git a/test/Transforms/ConstProp/calls.ll b/test/Transforms/ConstProp/calls.ll
index 1175ea5221758..161637cc92b8f 100644
--- a/test/Transforms/ConstProp/calls.ll
+++ b/test/Transforms/ConstProp/calls.ll
@@ -184,212 +184,6 @@ define double @T() {
ret double %d
}
-define i1 @test_sse_cvts_exact() nounwind readnone {
-; CHECK-LABEL: @test_sse_cvts_exact(
-; CHECK-NOT: call
-; CHECK: ret i1 true
-entry:
- %i0 = tail call i32 @llvm.x86.sse.cvtss2si(<4 x float> <float 3.0, float undef, float undef, float undef>) nounwind
- %i1 = tail call i64 @llvm.x86.sse.cvtss2si64(<4 x float> <float 3.0, float undef, float undef, float undef>) nounwind
- %i2 = call i32 @llvm.x86.sse2.cvtsd2si(<2 x double> <double 7.0, double undef>) nounwind
- %i3 = call i64 @llvm.x86.sse2.cvtsd2si64(<2 x double> <double 7.0, double undef>) nounwind
- %sum02 = add i32 %i0, %i2
- %sum13 = add i64 %i1, %i3
- %cmp02 = icmp eq i32 %sum02, 10
- %cmp13 = icmp eq i64 %sum13, 10
- %b = and i1 %cmp02, %cmp13
- ret i1 %b
-}
-
-; Inexact values should not fold as they are dependent on rounding mode
-define i1 @test_sse_cvts_inexact() nounwind readnone {
-; CHECK-LABEL: @test_sse_cvts_inexact(
-; CHECK: call
-; CHECK: call
-; CHECK: call
-; CHECK: call
-entry:
- %i0 = tail call i32 @llvm.x86.sse.cvtss2si(<4 x float> <float 1.75, float undef, float undef, float undef>) nounwind
- %i1 = tail call i64 @llvm.x86.sse.cvtss2si64(<4 x float> <float 1.75, float undef, float undef, float undef>) nounwind
- %i2 = call i32 @llvm.x86.sse2.cvtsd2si(<2 x double> <double 1.75, double undef>) nounwind
- %i3 = call i64 @llvm.x86.sse2.cvtsd2si64(<2 x double> <double 1.75, double undef>) nounwind
- %sum02 = add i32 %i0, %i2
- %sum13 = add i64 %i1, %i3
- %cmp02 = icmp eq i32 %sum02, 4
- %cmp13 = icmp eq i64 %sum13, 4
- %b = and i1 %cmp02, %cmp13
- ret i1 %b
-}
-
-; FLT_MAX/DBL_MAX should not fold
-define i1 @test_sse_cvts_max() nounwind readnone {
-; CHECK-LABEL: @test_sse_cvts_max(
-; CHECK: call
-; CHECK: call
-; CHECK: call
-; CHECK: call
-entry:
- %fm = bitcast <4 x i32> <i32 2139095039, i32 undef, i32 undef, i32 undef> to <4 x float>
- %dm = bitcast <2 x i64> <i64 9218868437227405311, i64 undef> to <2 x double>
- %i0 = tail call i32 @llvm.x86.sse.cvtss2si(<4 x float> %fm) nounwind
- %i1 = tail call i64 @llvm.x86.sse.cvtss2si64(<4 x float> %fm) nounwind
- %i2 = call i32 @llvm.x86.sse2.cvtsd2si(<2 x double> %dm) nounwind
- %i3 = call i64 @llvm.x86.sse2.cvtsd2si64(<2 x double> %dm) nounwind
- %sum02 = add i32 %i0, %i2
- %sum13 = add i64 %i1, %i3
- %sum02.sext = sext i32 %sum02 to i64
- %b = icmp eq i64 %sum02.sext, %sum13
- ret i1 %b
-}
-
-; INF should not fold
-define i1 @test_sse_cvts_inf() nounwind readnone {
-; CHECK-LABEL: @test_sse_cvts_inf(
-; CHECK: call
-; CHECK: call
-; CHECK: call
-; CHECK: call
-entry:
- %fm = bitcast <4 x i32> <i32 2139095040, i32 undef, i32 undef, i32 undef> to <4 x float>
- %dm = bitcast <2 x i64> <i64 9218868437227405312, i64 undef> to <2 x double>
- %i0 = tail call i32 @llvm.x86.sse.cvtss2si(<4 x float> %fm) nounwind
- %i1 = tail call i64 @llvm.x86.sse.cvtss2si64(<4 x float> %fm) nounwind
- %i2 = call i32 @llvm.x86.sse2.cvtsd2si(<2 x double> %dm) nounwind
- %i3 = call i64 @llvm.x86.sse2.cvtsd2si64(<2 x double> %dm) nounwind
- %sum02 = add i32 %i0, %i2
- %sum13 = add i64 %i1, %i3
- %sum02.sext = sext i32 %sum02 to i64
- %b = icmp eq i64 %sum02.sext, %sum13
- ret i1 %b
-}
-
-; NAN should not fold
-define i1 @test_sse_cvts_nan() nounwind readnone {
-; CHECK-LABEL: @test_sse_cvts_nan(
-; CHECK: call
-; CHECK: call
-; CHECK: call
-; CHECK: call
-entry:
- %fm = bitcast <4 x i32> <i32 2143289344, i32 undef, i32 undef, i32 undef> to <4 x float>
- %dm = bitcast <2 x i64> <i64 9221120237041090560, i64 undef> to <2 x double>
- %i0 = tail call i32 @llvm.x86.sse.cvtss2si(<4 x float> %fm) nounwind
- %i1 = tail call i64 @llvm.x86.sse.cvtss2si64(<4 x float> %fm) nounwind
- %i2 = call i32 @llvm.x86.sse2.cvtsd2si(<2 x double> %dm) nounwind
- %i3 = call i64 @llvm.x86.sse2.cvtsd2si64(<2 x double> %dm) nounwind
- %sum02 = add i32 %i0, %i2
- %sum13 = add i64 %i1, %i3
- %sum02.sext = sext i32 %sum02 to i64
- %b = icmp eq i64 %sum02.sext, %sum13
- ret i1 %b
-}
-
-define i1 @test_sse_cvtts_exact() nounwind readnone {
-; CHECK-LABEL: @test_sse_cvtts_exact(
-; CHECK-NOT: call
-; CHECK: ret i1 true
-entry:
- %i0 = tail call i32 @llvm.x86.sse.cvttss2si(<4 x float> <float 3.0, float undef, float undef, float undef>) nounwind
- %i1 = tail call i64 @llvm.x86.sse.cvttss2si64(<4 x float> <float 3.0, float undef, float undef, float undef>) nounwind
- %i2 = call i32 @llvm.x86.sse2.cvttsd2si(<2 x double> <double 7.0, double undef>) nounwind
- %i3 = call i64 @llvm.x86.sse2.cvttsd2si64(<2 x double> <double 7.0, double undef>) nounwind
- %sum02 = add i32 %i0, %i2
- %sum13 = add i64 %i1, %i3
- %cmp02 = icmp eq i32 %sum02, 10
- %cmp13 = icmp eq i64 %sum13, 10
- %b = and i1 %cmp02, %cmp13
- ret i1 %b
-}
-
-define i1 @test_sse_cvtts_inexact() nounwind readnone {
-; CHECK-LABEL: @test_sse_cvtts_inexact(
-; CHECK-NOT: call
-; CHECK: ret i1 true
-entry:
- %i0 = tail call i32 @llvm.x86.sse.cvttss2si(<4 x float> <float 1.75, float undef, float undef, float undef>) nounwind
- %i1 = tail call i64 @llvm.x86.sse.cvttss2si64(<4 x float> <float 1.75, float undef, float undef, float undef>) nounwind
- %i2 = call i32 @llvm.x86.sse2.cvttsd2si(<2 x double> <double 1.75, double undef>) nounwind
- %i3 = call i64 @llvm.x86.sse2.cvttsd2si64(<2 x double> <double 1.75, double undef>) nounwind
- %sum02 = add i32 %i0, %i2
- %sum13 = add i64 %i1, %i3
- %cmp02 = icmp eq i32 %sum02, 2
- %cmp13 = icmp eq i64 %sum13, 2
- %b = and i1 %cmp02, %cmp13
- ret i1 %b
-}
-
-; FLT_MAX/DBL_MAX should not fold
-define i1 @test_sse_cvtts_max() nounwind readnone {
-; CHECK-LABEL: @test_sse_cvtts_max(
-; CHECK: call
-; CHECK: call
-; CHECK: call
-; CHECK: call
-entry:
- %fm = bitcast <4 x i32> <i32 2139095039, i32 undef, i32 undef, i32 undef> to <4 x float>
- %dm = bitcast <2 x i64> <i64 9218868437227405311, i64 undef> to <2 x double>
- %i0 = tail call i32 @llvm.x86.sse.cvttss2si(<4 x float> %fm) nounwind
- %i1 = tail call i64 @llvm.x86.sse.cvttss2si64(<4 x float> %fm) nounwind
- %i2 = call i32 @llvm.x86.sse2.cvttsd2si(<2 x double> %dm) nounwind
- %i3 = call i64 @llvm.x86.sse2.cvttsd2si64(<2 x double> %dm) nounwind
- %sum02 = add i32 %i0, %i2
- %sum13 = add i64 %i1, %i3
- %sum02.sext = sext i32 %sum02 to i64
- %b = icmp eq i64 %sum02.sext, %sum13
- ret i1 %b
-}
-
-; INF should not fold
-define i1 @test_sse_cvtts_inf() nounwind readnone {
-; CHECK-LABEL: @test_sse_cvtts_inf(
-; CHECK: call
-; CHECK: call
-; CHECK: call
-; CHECK: call
-entry:
- %fm = bitcast <4 x i32> <i32 2139095040, i32 undef, i32 undef, i32 undef> to <4 x float>
- %dm = bitcast <2 x i64> <i64 9218868437227405312, i64 undef> to <2 x double>
- %i0 = tail call i32 @llvm.x86.sse.cvttss2si(<4 x float> %fm) nounwind
- %i1 = tail call i64 @llvm.x86.sse.cvttss2si64(<4 x float> %fm) nounwind
- %i2 = call i32 @llvm.x86.sse2.cvttsd2si(<2 x double> %dm) nounwind
- %i3 = call i64 @llvm.x86.sse2.cvttsd2si64(<2 x double> %dm) nounwind
- %sum02 = add i32 %i0, %i2
- %sum13 = add i64 %i1, %i3
- %sum02.sext = sext i32 %sum02 to i64
- %b = icmp eq i64 %sum02.sext, %sum13
- ret i1 %b
-}
-
-; NAN should not fold
-define i1 @test_sse_cvtts_nan() nounwind readnone {
-; CHECK-LABEL: @test_sse_cvtts_nan(
-; CHECK: call
-; CHECK: call
-; CHECK: call
-; CHECK: call
-entry:
- %fm = bitcast <4 x i32> <i32 2143289344, i32 undef, i32 undef, i32 undef> to <4 x float>
- %dm = bitcast <2 x i64> <i64 9221120237041090560, i64 undef> to <2 x double>
- %i0 = tail call i32 @llvm.x86.sse.cvttss2si(<4 x float> %fm) nounwind
- %i1 = tail call i64 @llvm.x86.sse.cvttss2si64(<4 x float> %fm) nounwind
- %i2 = call i32 @llvm.x86.sse2.cvttsd2si(<2 x double> %dm) nounwind
- %i3 = call i64 @llvm.x86.sse2.cvttsd2si64(<2 x double> %dm) nounwind
- %sum02 = add i32 %i0, %i2
- %sum13 = add i64 %i1, %i3
- %sum02.sext = sext i32 %sum02 to i64
- %b = icmp eq i64 %sum02.sext, %sum13
- ret i1 %b
-}
-
-declare i32 @llvm.x86.sse.cvtss2si(<4 x float>) nounwind readnone
-declare i32 @llvm.x86.sse.cvttss2si(<4 x float>) nounwind readnone
-declare i64 @llvm.x86.sse.cvtss2si64(<4 x float>) nounwind readnone
-declare i64 @llvm.x86.sse.cvttss2si64(<4 x float>) nounwind readnone
-declare i32 @llvm.x86.sse2.cvtsd2si(<2 x double>) nounwind readnone
-declare i32 @llvm.x86.sse2.cvttsd2si(<2 x double>) nounwind readnone
-declare i64 @llvm.x86.sse2.cvtsd2si64(<2 x double>) nounwind readnone
-declare i64 @llvm.x86.sse2.cvttsd2si64(<2 x double>) nounwind readnone
-
define double @test_intrinsic_pow() nounwind uwtable ssp {
entry:
; CHECK-LABEL: @test_intrinsic_pow(
diff --git a/test/Transforms/ConstProp/sse.ll b/test/Transforms/ConstProp/sse.ll
new file mode 100644
index 0000000000000..cc37c96c1ff1d
--- /dev/null
+++ b/test/Transforms/ConstProp/sse.ll
@@ -0,0 +1,208 @@
+; RUN: opt < %s -constprop -S | FileCheck %s
+; REQUIRES: x86
+
+define i1 @test_sse_cvts_exact() nounwind readnone {
+; CHECK-LABEL: @test_sse_cvts_exact(
+; CHECK-NOT: call
+; CHECK: ret i1 true
+entry:
+ %i0 = tail call i32 @llvm.x86.sse.cvtss2si(<4 x float> <float 3.0, float undef, float undef, float undef>) nounwind
+ %i1 = tail call i64 @llvm.x86.sse.cvtss2si64(<4 x float> <float 3.0, float undef, float undef, float undef>) nounwind
+ %i2 = call i32 @llvm.x86.sse2.cvtsd2si(<2 x double> <double 7.0, double undef>) nounwind
+ %i3 = call i64 @llvm.x86.sse2.cvtsd2si64(<2 x double> <double 7.0, double undef>) nounwind
+ %sum02 = add i32 %i0, %i2
+ %sum13 = add i64 %i1, %i3
+ %cmp02 = icmp eq i32 %sum02, 10
+ %cmp13 = icmp eq i64 %sum13, 10
+ %b = and i1 %cmp02, %cmp13
+ ret i1 %b
+}
+
+; Inexact values should not fold as they are dependent on rounding mode
+define i1 @test_sse_cvts_inexact() nounwind readnone {
+; CHECK-LABEL: @test_sse_cvts_inexact(
+; CHECK: call
+; CHECK: call
+; CHECK: call
+; CHECK: call
+entry:
+ %i0 = tail call i32 @llvm.x86.sse.cvtss2si(<4 x float> <float 1.75, float undef, float undef, float undef>) nounwind
+ %i1 = tail call i64 @llvm.x86.sse.cvtss2si64(<4 x float> <float 1.75, float undef, float undef, float undef>) nounwind
+ %i2 = call i32 @llvm.x86.sse2.cvtsd2si(<2 x double> <double 1.75, double undef>) nounwind
+ %i3 = call i64 @llvm.x86.sse2.cvtsd2si64(<2 x double> <double 1.75, double undef>) nounwind
+ %sum02 = add i32 %i0, %i2
+ %sum13 = add i64 %i1, %i3
+ %cmp02 = icmp eq i32 %sum02, 4
+ %cmp13 = icmp eq i64 %sum13, 4
+ %b = and i1 %cmp02, %cmp13
+ ret i1 %b
+}
+
+; FLT_MAX/DBL_MAX should not fold
+define i1 @test_sse_cvts_max() nounwind readnone {
+; CHECK-LABEL: @test_sse_cvts_max(
+; CHECK: call
+; CHECK: call
+; CHECK: call
+; CHECK: call
+entry:
+ %fm = bitcast <4 x i32> <i32 2139095039, i32 undef, i32 undef, i32 undef> to <4 x float>
+ %dm = bitcast <2 x i64> <i64 9218868437227405311, i64 undef> to <2 x double>
+ %i0 = tail call i32 @llvm.x86.sse.cvtss2si(<4 x float> %fm) nounwind
+ %i1 = tail call i64 @llvm.x86.sse.cvtss2si64(<4 x float> %fm) nounwind
+ %i2 = call i32 @llvm.x86.sse2.cvtsd2si(<2 x double> %dm) nounwind
+ %i3 = call i64 @llvm.x86.sse2.cvtsd2si64(<2 x double> %dm) nounwind
+ %sum02 = add i32 %i0, %i2
+ %sum13 = add i64 %i1, %i3
+ %sum02.sext = sext i32 %sum02 to i64
+ %b = icmp eq i64 %sum02.sext, %sum13
+ ret i1 %b
+}
+
+; INF should not fold
+define i1 @test_sse_cvts_inf() nounwind readnone {
+; CHECK-LABEL: @test_sse_cvts_inf(
+; CHECK: call
+; CHECK: call
+; CHECK: call
+; CHECK: call
+entry:
+ %fm = bitcast <4 x i32> <i32 2139095040, i32 undef, i32 undef, i32 undef> to <4 x float>
+ %dm = bitcast <2 x i64> <i64 9218868437227405312, i64 undef> to <2 x double>
+ %i0 = tail call i32 @llvm.x86.sse.cvtss2si(<4 x float> %fm) nounwind
+ %i1 = tail call i64 @llvm.x86.sse.cvtss2si64(<4 x float> %fm) nounwind
+ %i2 = call i32 @llvm.x86.sse2.cvtsd2si(<2 x double> %dm) nounwind
+ %i3 = call i64 @llvm.x86.sse2.cvtsd2si64(<2 x double> %dm) nounwind
+ %sum02 = add i32 %i0, %i2
+ %sum13 = add i64 %i1, %i3
+ %sum02.sext = sext i32 %sum02 to i64
+ %b = icmp eq i64 %sum02.sext, %sum13
+ ret i1 %b
+}
+
+; NAN should not fold
+define i1 @test_sse_cvts_nan() nounwind readnone {
+; CHECK-LABEL: @test_sse_cvts_nan(
+; CHECK: call
+; CHECK: call
+; CHECK: call
+; CHECK: call
+entry:
+ %fm = bitcast <4 x i32> <i32 2143289344, i32 undef, i32 undef, i32 undef> to <4 x float>
+ %dm = bitcast <2 x i64> <i64 9221120237041090560, i64 undef> to <2 x double>
+ %i0 = tail call i32 @llvm.x86.sse.cvtss2si(<4 x float> %fm) nounwind
+ %i1 = tail call i64 @llvm.x86.sse.cvtss2si64(<4 x float> %fm) nounwind
+ %i2 = call i32 @llvm.x86.sse2.cvtsd2si(<2 x double> %dm) nounwind
+ %i3 = call i64 @llvm.x86.sse2.cvtsd2si64(<2 x double> %dm) nounwind
+ %sum02 = add i32 %i0, %i2
+ %sum13 = add i64 %i1, %i3
+ %sum02.sext = sext i32 %sum02 to i64
+ %b = icmp eq i64 %sum02.sext, %sum13
+ ret i1 %b
+}
+
+define i1 @test_sse_cvtts_exact() nounwind readnone {
+; CHECK-LABEL: @test_sse_cvtts_exact(
+; CHECK-NOT: call
+; CHECK: ret i1 true
+entry:
+ %i0 = tail call i32 @llvm.x86.sse.cvttss2si(<4 x float> <float 3.0, float undef, float undef, float undef>) nounwind
+ %i1 = tail call i64 @llvm.x86.sse.cvttss2si64(<4 x float> <float 3.0, float undef, float undef, float undef>) nounwind
+ %i2 = call i32 @llvm.x86.sse2.cvttsd2si(<2 x double> <double 7.0, double undef>) nounwind
+ %i3 = call i64 @llvm.x86.sse2.cvttsd2si64(<2 x double> <double 7.0, double undef>) nounwind
+ %sum02 = add i32 %i0, %i2
+ %sum13 = add i64 %i1, %i3
+ %cmp02 = icmp eq i32 %sum02, 10
+ %cmp13 = icmp eq i64 %sum13, 10
+ %b = and i1 %cmp02, %cmp13
+ ret i1 %b
+}
+
+define i1 @test_sse_cvtts_inexact() nounwind readnone {
+; CHECK-LABEL: @test_sse_cvtts_inexact(
+; CHECK-NOT: call
+; CHECK: ret i1 true
+entry:
+ %i0 = tail call i32 @llvm.x86.sse.cvttss2si(<4 x float> <float 1.75, float undef, float undef, float undef>) nounwind
+ %i1 = tail call i64 @llvm.x86.sse.cvttss2si64(<4 x float> <float 1.75, float undef, float undef, float undef>) nounwind
+ %i2 = call i32 @llvm.x86.sse2.cvttsd2si(<2 x double> <double 1.75, double undef>) nounwind
+ %i3 = call i64 @llvm.x86.sse2.cvttsd2si64(<2 x double> <double 1.75, double undef>) nounwind
+ %sum02 = add i32 %i0, %i2
+ %sum13 = add i64 %i1, %i3
+ %cmp02 = icmp eq i32 %sum02, 2
+ %cmp13 = icmp eq i64 %sum13, 2
+ %b = and i1 %cmp02, %cmp13
+ ret i1 %b
+}
+
+; FLT_MAX/DBL_MAX should not fold
+define i1 @test_sse_cvtts_max() nounwind readnone {
+; CHECK-LABEL: @test_sse_cvtts_max(
+; CHECK: call
+; CHECK: call
+; CHECK: call
+; CHECK: call
+entry:
+ %fm = bitcast <4 x i32> <i32 2139095039, i32 undef, i32 undef, i32 undef> to <4 x float>
+ %dm = bitcast <2 x i64> <i64 9218868437227405311, i64 undef> to <2 x double>
+ %i0 = tail call i32 @llvm.x86.sse.cvttss2si(<4 x float> %fm) nounwind
+ %i1 = tail call i64 @llvm.x86.sse.cvttss2si64(<4 x float> %fm) nounwind
+ %i2 = call i32 @llvm.x86.sse2.cvttsd2si(<2 x double> %dm) nounwind
+ %i3 = call i64 @llvm.x86.sse2.cvttsd2si64(<2 x double> %dm) nounwind
+ %sum02 = add i32 %i0, %i2
+ %sum13 = add i64 %i1, %i3
+ %sum02.sext = sext i32 %sum02 to i64
+ %b = icmp eq i64 %sum02.sext, %sum13
+ ret i1 %b
+}
+
+; INF should not fold
+define i1 @test_sse_cvtts_inf() nounwind readnone {
+; CHECK-LABEL: @test_sse_cvtts_inf(
+; CHECK: call
+; CHECK: call
+; CHECK: call
+; CHECK: call
+entry:
+ %fm = bitcast <4 x i32> <i32 2139095040, i32 undef, i32 undef, i32 undef> to <4 x float>
+ %dm = bitcast <2 x i64> <i64 9218868437227405312, i64 undef> to <2 x double>
+ %i0 = tail call i32 @llvm.x86.sse.cvttss2si(<4 x float> %fm) nounwind
+ %i1 = tail call i64 @llvm.x86.sse.cvttss2si64(<4 x float> %fm) nounwind
+ %i2 = call i32 @llvm.x86.sse2.cvttsd2si(<2 x double> %dm) nounwind
+ %i3 = call i64 @llvm.x86.sse2.cvttsd2si64(<2 x double> %dm) nounwind
+ %sum02 = add i32 %i0, %i2
+ %sum13 = add i64 %i1, %i3
+ %sum02.sext = sext i32 %sum02 to i64
+ %b = icmp eq i64 %sum02.sext, %sum13
+ ret i1 %b
+}
+
+; NAN should not fold
+define i1 @test_sse_cvtts_nan() nounwind readnone {
+; CHECK-LABEL: @test_sse_cvtts_nan(
+; CHECK: call
+; CHECK: call
+; CHECK: call
+; CHECK: call
+entry:
+ %fm = bitcast <4 x i32> <i32 2143289344, i32 undef, i32 undef, i32 undef> to <4 x float>
+ %dm = bitcast <2 x i64> <i64 9221120237041090560, i64 undef> to <2 x double>
+ %i0 = tail call i32 @llvm.x86.sse.cvttss2si(<4 x float> %fm) nounwind
+ %i1 = tail call i64 @llvm.x86.sse.cvttss2si64(<4 x float> %fm) nounwind
+ %i2 = call i32 @llvm.x86.sse2.cvttsd2si(<2 x double> %dm) nounwind
+ %i3 = call i64 @llvm.x86.sse2.cvttsd2si64(<2 x double> %dm) nounwind
+ %sum02 = add i32 %i0, %i2
+ %sum13 = add i64 %i1, %i3
+ %sum02.sext = sext i32 %sum02 to i64
+ %b = icmp eq i64 %sum02.sext, %sum13
+ ret i1 %b
+}
+
+declare i32 @llvm.x86.sse.cvtss2si(<4 x float>) nounwind readnone
+declare i32 @llvm.x86.sse.cvttss2si(<4 x float>) nounwind readnone
+declare i64 @llvm.x86.sse.cvtss2si64(<4 x float>) nounwind readnone
+declare i64 @llvm.x86.sse.cvttss2si64(<4 x float>) nounwind readnone
+declare i32 @llvm.x86.sse2.cvtsd2si(<2 x double>) nounwind readnone
+declare i32 @llvm.x86.sse2.cvttsd2si(<2 x double>) nounwind readnone
+declare i64 @llvm.x86.sse2.cvtsd2si64(<2 x double>) nounwind readnone
+declare i64 @llvm.x86.sse2.cvttsd2si64(<2 x double>) nounwind readnone
generated by cgit v1.3 (git 2.53.0) at 2026-09-07 00:56:42 +0000