; CHECK: fmul fast <4 x float> %f1, <float 3.000000e+00, float 2.000000e+00, float 1.000000e+00, float 1.000000e+00>
}
+; Make sure fmul with constant expression doesn't assert.
+define <4 x float> @fmul3_vec_constexpr(<4 x float> %f1, <4 x float> %f2) {
+ %constExprMul = bitcast i128 trunc (i160 bitcast (<5 x float> <float 6.0e+3, float 6.0e+3, float 2.0e+3, float 1.0e+3, float undef> to i160) to i128) to <4 x float>
+ %t1 = fdiv <4 x float> %f1, <float 2.0e+3, float 3.0e+3, float 2.0e+3, float 1.0e+3>
+ %t3 = fmul fast <4 x float> %t1, %constExprMul
+ ret <4 x float> %t3
+}
+
; Rule "X/C1 * C2 => X * (C2/C1) is not applicable if C2/C1 is either a special
; value of a denormal. The 0x3810000000000000 here take value FLT_MIN
;
; CHECK: fmul float %f1, %f2
}
+define float @fneg2(float %x) {
+ %sub = fsub nsz float 0.0, %x
+ ret float %sub
+; CHECK-LABEL: @fneg2(
+; CHECK-NEXT: fsub nsz float -0.000000e+00, %x
+; CHECK-NEXT: ret float
+}
+
; =========================================================================
;
; Testing-cases about div
; A squared factor fed into a square root intrinsic should be hoisted out
; as a fabs() value.
-; We have to rely on a function-level attribute to enable this optimization
-; because intrinsics don't currently have access to IR-level fast-math
-; flags. If that changes, we can relax the requirement on all of these
-; tests to just specify 'fast' on the sqrt.
-
-attributes #0 = { "unsafe-fp-math" = "true" }
declare double @llvm.sqrt.f64(double)
-define double @sqrt_intrinsic_arg_squared(double %x) #0 {
+define double @sqrt_intrinsic_arg_squared(double %x) {
%mul = fmul fast double %x, %x
- %sqrt = call double @llvm.sqrt.f64(double %mul)
+ %sqrt = call fast double @llvm.sqrt.f64(double %mul)
ret double %sqrt
; CHECK-LABEL: sqrt_intrinsic_arg_squared(
-; CHECK-NEXT: %fabs = call double @llvm.fabs.f64(double %x)
+; CHECK-NEXT: %fabs = call fast double @llvm.fabs.f64(double %x)
; CHECK-NEXT: ret double %fabs
}
; Check all 6 combinations of a 3-way multiplication tree where
; one factor is repeated.
-define double @sqrt_intrinsic_three_args1(double %x, double %y) #0 {
+define double @sqrt_intrinsic_three_args1(double %x, double %y) {
%mul = fmul fast double %y, %x
%mul2 = fmul fast double %mul, %x
- %sqrt = call double @llvm.sqrt.f64(double %mul2)
+ %sqrt = call fast double @llvm.sqrt.f64(double %mul2)
ret double %sqrt
; CHECK-LABEL: sqrt_intrinsic_three_args1(
-; CHECK-NEXT: %fabs = call double @llvm.fabs.f64(double %x)
-; CHECK-NEXT: %sqrt1 = call double @llvm.sqrt.f64(double %y)
+; CHECK-NEXT: %fabs = call fast double @llvm.fabs.f64(double %x)
+; CHECK-NEXT: %sqrt1 = call fast double @llvm.sqrt.f64(double %y)
; CHECK-NEXT: %1 = fmul fast double %fabs, %sqrt1
; CHECK-NEXT: ret double %1
}
-define double @sqrt_intrinsic_three_args2(double %x, double %y) #0 {
+define double @sqrt_intrinsic_three_args2(double %x, double %y) {
%mul = fmul fast double %x, %y
%mul2 = fmul fast double %mul, %x
- %sqrt = call double @llvm.sqrt.f64(double %mul2)
+ %sqrt = call fast double @llvm.sqrt.f64(double %mul2)
ret double %sqrt
; CHECK-LABEL: sqrt_intrinsic_three_args2(
-; CHECK-NEXT: %fabs = call double @llvm.fabs.f64(double %x)
-; CHECK-NEXT: %sqrt1 = call double @llvm.sqrt.f64(double %y)
+; CHECK-NEXT: %fabs = call fast double @llvm.fabs.f64(double %x)
+; CHECK-NEXT: %sqrt1 = call fast double @llvm.sqrt.f64(double %y)
; CHECK-NEXT: %1 = fmul fast double %fabs, %sqrt1
; CHECK-NEXT: ret double %1
}
-define double @sqrt_intrinsic_three_args3(double %x, double %y) #0 {
+define double @sqrt_intrinsic_three_args3(double %x, double %y) {
%mul = fmul fast double %x, %x
%mul2 = fmul fast double %mul, %y
- %sqrt = call double @llvm.sqrt.f64(double %mul2)
+ %sqrt = call fast double @llvm.sqrt.f64(double %mul2)
ret double %sqrt
; CHECK-LABEL: sqrt_intrinsic_three_args3(
-; CHECK-NEXT: %fabs = call double @llvm.fabs.f64(double %x)
-; CHECK-NEXT: %sqrt1 = call double @llvm.sqrt.f64(double %y)
+; CHECK-NEXT: %fabs = call fast double @llvm.fabs.f64(double %x)
+; CHECK-NEXT: %sqrt1 = call fast double @llvm.sqrt.f64(double %y)
; CHECK-NEXT: %1 = fmul fast double %fabs, %sqrt1
; CHECK-NEXT: ret double %1
}
-define double @sqrt_intrinsic_three_args4(double %x, double %y) #0 {
+define double @sqrt_intrinsic_three_args4(double %x, double %y) {
%mul = fmul fast double %y, %x
%mul2 = fmul fast double %x, %mul
- %sqrt = call double @llvm.sqrt.f64(double %mul2)
+ %sqrt = call fast double @llvm.sqrt.f64(double %mul2)
ret double %sqrt
; CHECK-LABEL: sqrt_intrinsic_three_args4(
-; CHECK-NEXT: %fabs = call double @llvm.fabs.f64(double %x)
-; CHECK-NEXT: %sqrt1 = call double @llvm.sqrt.f64(double %y)
+; CHECK-NEXT: %fabs = call fast double @llvm.fabs.f64(double %x)
+; CHECK-NEXT: %sqrt1 = call fast double @llvm.sqrt.f64(double %y)
; CHECK-NEXT: %1 = fmul fast double %fabs, %sqrt1
; CHECK-NEXT: ret double %1
}
-define double @sqrt_intrinsic_three_args5(double %x, double %y) #0 {
+define double @sqrt_intrinsic_three_args5(double %x, double %y) {
%mul = fmul fast double %x, %y
%mul2 = fmul fast double %x, %mul
- %sqrt = call double @llvm.sqrt.f64(double %mul2)
+ %sqrt = call fast double @llvm.sqrt.f64(double %mul2)
ret double %sqrt
; CHECK-LABEL: sqrt_intrinsic_three_args5(
-; CHECK-NEXT: %fabs = call double @llvm.fabs.f64(double %x)
-; CHECK-NEXT: %sqrt1 = call double @llvm.sqrt.f64(double %y)
+; CHECK-NEXT: %fabs = call fast double @llvm.fabs.f64(double %x)
+; CHECK-NEXT: %sqrt1 = call fast double @llvm.sqrt.f64(double %y)
; CHECK-NEXT: %1 = fmul fast double %fabs, %sqrt1
; CHECK-NEXT: ret double %1
}
-define double @sqrt_intrinsic_three_args6(double %x, double %y) #0 {
+define double @sqrt_intrinsic_three_args6(double %x, double %y) {
%mul = fmul fast double %x, %x
%mul2 = fmul fast double %y, %mul
- %sqrt = call double @llvm.sqrt.f64(double %mul2)
+ %sqrt = call fast double @llvm.sqrt.f64(double %mul2)
ret double %sqrt
; CHECK-LABEL: sqrt_intrinsic_three_args6(
-; CHECK-NEXT: %fabs = call double @llvm.fabs.f64(double %x)
-; CHECK-NEXT: %sqrt1 = call double @llvm.sqrt.f64(double %y)
+; CHECK-NEXT: %fabs = call fast double @llvm.fabs.f64(double %x)
+; CHECK-NEXT: %sqrt1 = call fast double @llvm.sqrt.f64(double %y)
; CHECK-NEXT: %1 = fmul fast double %fabs, %sqrt1
; CHECK-NEXT: ret double %1
}
-define double @sqrt_intrinsic_arg_4th(double %x) #0 {
+define double @sqrt_intrinsic_arg_4th(double %x) {
%mul = fmul fast double %x, %x
%mul2 = fmul fast double %mul, %mul
- %sqrt = call double @llvm.sqrt.f64(double %mul2)
+ %sqrt = call fast double @llvm.sqrt.f64(double %mul2)
ret double %sqrt
; CHECK-LABEL: sqrt_intrinsic_arg_4th(
; CHECK-NEXT: ret double %mul
}
-define double @sqrt_intrinsic_arg_5th(double %x) #0 {
+define double @sqrt_intrinsic_arg_5th(double %x) {
%mul = fmul fast double %x, %x
%mul2 = fmul fast double %mul, %x
%mul3 = fmul fast double %mul2, %mul
- %sqrt = call double @llvm.sqrt.f64(double %mul3)
+ %sqrt = call fast double @llvm.sqrt.f64(double %mul3)
ret double %sqrt
; CHECK-LABEL: sqrt_intrinsic_arg_5th(
; CHECK-NEXT: %mul = fmul fast double %x, %x
-; CHECK-NEXT: %sqrt1 = call double @llvm.sqrt.f64(double %x)
+; CHECK-NEXT: %sqrt1 = call fast double @llvm.sqrt.f64(double %x)
; CHECK-NEXT: %1 = fmul fast double %mul, %sqrt1
; CHECK-NEXT: ret double %1
}
declare double @sqrt(double)
declare fp128 @sqrtl(fp128)
-define float @sqrt_call_squared_f32(float %x) #0 {
+define float @sqrt_call_squared_f32(float %x) {
%mul = fmul fast float %x, %x
- %sqrt = call float @sqrtf(float %mul)
+ %sqrt = call fast float @sqrtf(float %mul)
ret float %sqrt
; CHECK-LABEL: sqrt_call_squared_f32(
-; CHECK-NEXT: %fabs = call float @llvm.fabs.f32(float %x)
+; CHECK-NEXT: %fabs = call fast float @llvm.fabs.f32(float %x)
; CHECK-NEXT: ret float %fabs
}
-define double @sqrt_call_squared_f64(double %x) #0 {
+define double @sqrt_call_squared_f64(double %x) {
%mul = fmul fast double %x, %x
- %sqrt = call double @sqrt(double %mul)
+ %sqrt = call fast double @sqrt(double %mul)
ret double %sqrt
; CHECK-LABEL: sqrt_call_squared_f64(
-; CHECK-NEXT: %fabs = call double @llvm.fabs.f64(double %x)
+; CHECK-NEXT: %fabs = call fast double @llvm.fabs.f64(double %x)
; CHECK-NEXT: ret double %fabs
}
-define fp128 @sqrt_call_squared_f128(fp128 %x) #0 {
+define fp128 @sqrt_call_squared_f128(fp128 %x) {
%mul = fmul fast fp128 %x, %x
- %sqrt = call fp128 @sqrtl(fp128 %mul)
+ %sqrt = call fast fp128 @sqrtl(fp128 %mul)
ret fp128 %sqrt
; CHECK-LABEL: sqrt_call_squared_f128(
-; CHECK-NEXT: %fabs = call fp128 @llvm.fabs.f128(fp128 %x)
+; CHECK-NEXT: %fabs = call fast fp128 @llvm.fabs.f128(fp128 %x)
; CHECK-NEXT: ret fp128 %fabs
}
+; =========================================================================
+;
+; Test-cases for fmin / fmax
+;
+; =========================================================================
+
+declare double @fmax(double, double)
+declare double @fmin(double, double)
+declare float @fmaxf(float, float)
+declare float @fminf(float, float)
+declare fp128 @fmaxl(fp128, fp128)
+declare fp128 @fminl(fp128, fp128)
+
+; No NaNs is the minimum requirement to replace these calls.
+; This should always be set when unsafe-fp-math is true, but
+; alternate the attributes for additional test coverage.
+; 'nsz' is implied by the definition of fmax or fmin itself.
+
+; Shrink and remove the call.
+define float @max1(float %a, float %b) {
+ %c = fpext float %a to double
+ %d = fpext float %b to double
+ %e = call fast double @fmax(double %c, double %d)
+ %f = fptrunc double %e to float
+ ret float %f
+
+; CHECK-LABEL: max1(
+; CHECK-NEXT: fcmp fast ogt float %a, %b
+; CHECK-NEXT: select {{.*}} float %a, float %b
+; CHECK-NEXT: ret
+}
+
+define float @max2(float %a, float %b) {
+ %c = call nnan float @fmaxf(float %a, float %b)
+ ret float %c
+
+; CHECK-LABEL: max2(
+; CHECK-NEXT: fcmp nnan nsz ogt float %a, %b
+; CHECK-NEXT: select {{.*}} float %a, float %b
+; CHECK-NEXT: ret
+}
+
+
+define double @max3(double %a, double %b) {
+ %c = call fast double @fmax(double %a, double %b)
+ ret double %c
+
+; CHECK-LABEL: max3(
+; CHECK-NEXT: fcmp fast ogt double %a, %b
+; CHECK-NEXT: select {{.*}} double %a, double %b
+; CHECK-NEXT: ret
+}
+
+define fp128 @max4(fp128 %a, fp128 %b) {
+ %c = call nnan fp128 @fmaxl(fp128 %a, fp128 %b)
+ ret fp128 %c
+
+; CHECK-LABEL: max4(
+; CHECK-NEXT: fcmp nnan nsz ogt fp128 %a, %b
+; CHECK-NEXT: select {{.*}} fp128 %a, fp128 %b
+; CHECK-NEXT: ret
+}
+
+; Shrink and remove the call.
+define float @min1(float %a, float %b) {
+ %c = fpext float %a to double
+ %d = fpext float %b to double
+ %e = call nnan double @fmin(double %c, double %d)
+ %f = fptrunc double %e to float
+ ret float %f
+
+; CHECK-LABEL: min1(
+; CHECK-NEXT: fcmp nnan nsz olt float %a, %b
+; CHECK-NEXT: select {{.*}} float %a, float %b
+; CHECK-NEXT: ret
+}
+
+define float @min2(float %a, float %b) {
+ %c = call fast float @fminf(float %a, float %b)
+ ret float %c
+
+; CHECK-LABEL: min2(
+; CHECK-NEXT: fcmp fast olt float %a, %b
+; CHECK-NEXT: select {{.*}} float %a, float %b
+; CHECK-NEXT: ret
+}
+
+define double @min3(double %a, double %b) {
+ %c = call nnan double @fmin(double %a, double %b)
+ ret double %c
+
+; CHECK-LABEL: min3(
+; CHECK-NEXT: fcmp nnan nsz olt double %a, %b
+; CHECK-NEXT: select {{.*}} double %a, double %b
+; CHECK-NEXT: ret
+}
+
+define fp128 @min4(fp128 %a, fp128 %b) {
+ %c = call fast fp128 @fminl(fp128 %a, fp128 %b)
+ ret fp128 %c
+
+; CHECK-LABEL: min4(
+; CHECK-NEXT: fcmp fast olt fp128 %a, %b
+; CHECK-NEXT: select {{.*}} fp128 %a, fp128 %b
+; CHECK-NEXT: ret
+}
projects / oota-llvm.git / blobdiff