llvm/llvm/test/Instrumentation/NumericalStabilitySanitizer/basic.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=nsan -nsan-shadow-type-mapping=dqq -nsan-truncate-fcmp-eq=false -S %s | FileCheck %s --check-prefixes=CHECK,DQQ
; RUN: opt -passes=nsan -nsan-shadow-type-mapping=dlq -nsan-truncate-fcmp-eq=false -S %s | FileCheck %s --check-prefixes=CHECK,DLQ

target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"

declare float @declaration_only(float %a) sanitize_numerical_stability

; Tests with simple control flow.

@float_const = private unnamed_addr constant float 0.5
@x86_fp80_const = private unnamed_addr constant x86_fp80 0xK3FC9E69594BEC44DE000
@double_const = private unnamed_addr constant double 0.5


define float @return_param_float(float %a) sanitize_numerical_stability {
; CHECK-LABEL: @return_param_float(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq i64 [[TMP0]], ptrtoint (ptr @return_param_float to i64)
; CHECK-NEXT:    [[TMP2:%.*]] = load double, ptr @__nsan_shadow_args_ptr, align 1
; CHECK-NEXT:    [[TMP3:%.*]] = fpext float [[A:%.*]] to double
; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP1]], double [[TMP2]], double [[TMP3]]
; CHECK-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @__nsan_internal_check_float_d(float [[A]], double [[TMP4]], i32 1, i64 0)
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[TMP5]], 1
; CHECK-NEXT:    [[TMP7:%.*]] = fpext float [[A]] to double
; CHECK-NEXT:    [[TMP8:%.*]] = select i1 [[TMP6]], double [[TMP7]], double [[TMP4]]
; CHECK-NEXT:    store i64 ptrtoint (ptr @return_param_float to i64), ptr @__nsan_shadow_ret_tag, align 8
; CHECK-NEXT:    store double [[TMP8]], ptr @__nsan_shadow_ret_ptr, align 8
; CHECK-NEXT:    ret float [[A]]
;
entry:
  ret float %a
}

; Note that the shadow fadd should not have a `fast` flag.
define float @param_add_return_float(float %a) sanitize_numerical_stability {
; CHECK-LABEL: @param_add_return_float(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq i64 [[TMP0]], ptrtoint (ptr @param_add_return_float to i64)
; CHECK-NEXT:    [[TMP2:%.*]] = load double, ptr @__nsan_shadow_args_ptr, align 1
; CHECK-NEXT:    [[TMP3:%.*]] = fpext float [[A:%.*]] to double
; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP1]], double [[TMP2]], double [[TMP3]]
; CHECK-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[B:%.*]] = fadd fast float [[A]], 1.000000e+00
; CHECK-NEXT:    [[TMP5:%.*]] = fadd double [[TMP4]], 1.000000e+00
; CHECK-NEXT:    [[TMP6:%.*]] = call i32 @__nsan_internal_check_float_d(float [[B]], double [[TMP5]], i32 1, i64 0)
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[TMP6]], 1
; CHECK-NEXT:    [[TMP8:%.*]] = fpext float [[B]] to double
; CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[TMP7]], double [[TMP8]], double [[TMP5]]
; CHECK-NEXT:    store i64 ptrtoint (ptr @param_add_return_float to i64), ptr @__nsan_shadow_ret_tag, align 8
; CHECK-NEXT:    store double [[TMP9]], ptr @__nsan_shadow_ret_ptr, align 8
; CHECK-NEXT:    ret float [[B]]
;
entry:
  %b = fadd fast float %a, 1.0
  ret float %b
}

define x86_fp80 @param_add_return_x86_fp80(x86_fp80 %a) sanitize_numerical_stability {
; CHECK-LABEL: @param_add_return_x86_fp80(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq i64 [[TMP0]], ptrtoint (ptr @param_add_return_x86_fp80 to i64)
; CHECK-NEXT:    [[TMP2:%.*]] = load fp128, ptr @__nsan_shadow_args_ptr, align 1
; CHECK-NEXT:    [[TMP3:%.*]] = fpext x86_fp80 [[A:%.*]] to fp128
; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP1]], fp128 [[TMP2]], fp128 [[TMP3]]
; CHECK-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[B:%.*]] = fadd x86_fp80 [[A]], 0xK3FC9E69594BEC44DE000
; CHECK-NEXT:    [[TMP5:%.*]] = fadd fp128 [[TMP4]], 0xLC0000000000000003FC9CD2B297D889B
; CHECK-NEXT:    [[TMP6:%.*]] = call i32 @__nsan_internal_check_longdouble_q(x86_fp80 [[B]], fp128 [[TMP5]], i32 1, i64 0)
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[TMP6]], 1
; CHECK-NEXT:    [[TMP8:%.*]] = fpext x86_fp80 [[B]] to fp128
; CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[TMP7]], fp128 [[TMP8]], fp128 [[TMP5]]
; CHECK-NEXT:    store i64 ptrtoint (ptr @param_add_return_x86_fp80 to i64), ptr @__nsan_shadow_ret_tag, align 8
; CHECK-NEXT:    store fp128 [[TMP9]], ptr @__nsan_shadow_ret_ptr, align 16
; CHECK-NEXT:    ret x86_fp80 [[B]]
;
entry:
  %b = fadd x86_fp80 %a, 0xK3FC9E69594BEC44DE000
  ret x86_fp80 %b
}

define double @param_add_return_double(double %a) sanitize_numerical_stability {
; DQQ-LABEL: @param_add_return_double(
; DQQ-NEXT:  entry:
; DQQ-NEXT:    [[TMP0:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; DQQ-NEXT:    [[TMP1:%.*]] = icmp eq i64 [[TMP0]], ptrtoint (ptr @param_add_return_double to i64)
; DQQ-NEXT:    [[TMP2:%.*]] = load fp128, ptr @__nsan_shadow_args_ptr, align 1
; DQQ-NEXT:    [[TMP3:%.*]] = fpext double [[A:%.*]] to fp128
; DQQ-NEXT:    [[TMP4:%.*]] = select i1 [[TMP1]], fp128 [[TMP2]], fp128 [[TMP3]]
; DQQ-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; DQQ-NEXT:    [[B:%.*]] = fadd double [[A]], 1.000000e+00
; DQQ-NEXT:    [[TMP5:%.*]] = fadd fp128 [[TMP4]], 0xL00000000000000003FFF000000000000
; DQQ-NEXT:    [[TMP6:%.*]] = call i32 @__nsan_internal_check_double_q(double [[B]], fp128 [[TMP5]], i32 1, i64 0)
; DQQ-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[TMP6]], 1
; DQQ-NEXT:    [[TMP8:%.*]] = fpext double [[B]] to fp128
; DQQ-NEXT:    [[TMP9:%.*]] = select i1 [[TMP7]], fp128 [[TMP8]], fp128 [[TMP5]]
; DQQ-NEXT:    store i64 ptrtoint (ptr @param_add_return_double to i64), ptr @__nsan_shadow_ret_tag, align 8
; DQQ-NEXT:    store fp128 [[TMP9]], ptr @__nsan_shadow_ret_ptr, align 16
; DQQ-NEXT:    ret double [[B]]
;
; DLQ-LABEL: @param_add_return_double(
; DLQ-NEXT:  entry:
; DLQ-NEXT:    [[TMP0:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; DLQ-NEXT:    [[TMP1:%.*]] = icmp eq i64 [[TMP0]], ptrtoint (ptr @param_add_return_double to i64)
; DLQ-NEXT:    [[TMP2:%.*]] = load x86_fp80, ptr @__nsan_shadow_args_ptr, align 1
; DLQ-NEXT:    [[TMP3:%.*]] = fpext double [[A:%.*]] to x86_fp80
; DLQ-NEXT:    [[TMP4:%.*]] = select i1 [[TMP1]], x86_fp80 [[TMP2]], x86_fp80 [[TMP3]]
; DLQ-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; DLQ-NEXT:    [[B:%.*]] = fadd double [[A]], 1.000000e+00
; DLQ-NEXT:    [[TMP5:%.*]] = fadd x86_fp80 [[TMP4]], 0xK3FFF8000000000000000
; DLQ-NEXT:    [[TMP6:%.*]] = call i32 @__nsan_internal_check_double_l(double [[B]], x86_fp80 [[TMP5]], i32 1, i64 0)
; DLQ-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[TMP6]], 1
; DLQ-NEXT:    [[TMP8:%.*]] = fpext double [[B]] to x86_fp80
; DLQ-NEXT:    [[TMP9:%.*]] = select i1 [[TMP7]], x86_fp80 [[TMP8]], x86_fp80 [[TMP5]]
; DLQ-NEXT:    store i64 ptrtoint (ptr @param_add_return_double to i64), ptr @__nsan_shadow_ret_tag, align 8
; DLQ-NEXT:    store x86_fp80 [[TMP9]], ptr @__nsan_shadow_ret_ptr, align 16
; DLQ-NEXT:    ret double [[B]]
;
entry:
  %b = fadd double %a, 1.0
  ret double %b
}

define <2 x float> @return_param_add_return_float_vector(<2 x float> %a) sanitize_numerical_stability {
; CHECK-LABEL: @return_param_add_return_float_vector(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq i64 [[TMP0]], ptrtoint (ptr @return_param_add_return_float_vector to i64)
; CHECK-NEXT:    [[TMP2:%.*]] = load <2 x double>, ptr @__nsan_shadow_args_ptr, align 1
; CHECK-NEXT:    [[TMP3:%.*]] = fpext <2 x float> [[A:%.*]] to <2 x double>
; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP1]], <2 x double> [[TMP2]], <2 x double> [[TMP3]]
; CHECK-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[B:%.*]] = fadd <2 x float> [[A]], <float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT:    [[TMP5:%.*]] = fadd <2 x double> [[TMP4]], <double 1.000000e+00, double 1.000000e+00>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x float> [[B]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <2 x double> [[TMP5]], i64 0
; CHECK-NEXT:    [[TMP8:%.*]] = call i32 @__nsan_internal_check_float_d(float [[TMP6]], double [[TMP7]], i32 1, i64 0)
; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <2 x float> [[B]], i64 1
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <2 x double> [[TMP5]], i64 1
; CHECK-NEXT:    [[TMP11:%.*]] = call i32 @__nsan_internal_check_float_d(float [[TMP9]], double [[TMP10]], i32 1, i64 0)
; CHECK-NEXT:    [[TMP12:%.*]] = or i32 [[TMP8]], [[TMP11]]
; CHECK-NEXT:    [[TMP13:%.*]] = icmp eq i32 [[TMP12]], 1
; CHECK-NEXT:    [[TMP14:%.*]] = fpext <2 x float> [[B]] to <2 x double>
; CHECK-NEXT:    [[TMP15:%.*]] = select i1 [[TMP13]], <2 x double> [[TMP14]], <2 x double> [[TMP5]]
; CHECK-NEXT:    store i64 ptrtoint (ptr @return_param_add_return_float_vector to i64), ptr @__nsan_shadow_ret_tag, align 8
; CHECK-NEXT:    store <2 x double> [[TMP15]], ptr @__nsan_shadow_ret_ptr, align 16
; CHECK-NEXT:    ret <2 x float> [[B]]
;
entry:
  %b = fadd <2 x float> %a, <float 1.0, float 1.0>
  ret <2 x float> %b
}

; TODO: This is ignored for now.
define [2 x float] @return_param_float_array([2 x float] %a) sanitize_numerical_stability {
; CHECK-LABEL: @return_param_float_array(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    ret [2 x float] [[A:%.*]]
;
entry:
  ret [2 x float] %a
}

define void @constantload_add_store_float(ptr %dst) sanitize_numerical_stability {
; CHECK-LABEL: @constantload_add_store_float(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[B:%.*]] = load float, ptr @float_const, align 4
; CHECK-NEXT:    [[TMP0:%.*]] = fpext float [[B]] to double
; CHECK-NEXT:    [[C:%.*]] = fadd float [[B]], 1.000000e+00
; CHECK-NEXT:    [[TMP1:%.*]] = fadd double [[TMP0]], 1.000000e+00
; CHECK-NEXT:    [[TMP2:%.*]] = call ptr @__nsan_get_shadow_ptr_for_float_store(ptr [[DST:%.*]], i64 1)
; CHECK-NEXT:    [[TMP3:%.*]] = ptrtoint ptr [[DST]] to i64
; CHECK-NEXT:    [[TMP4:%.*]] = call i32 @__nsan_internal_check_float_d(float [[C]], double [[TMP1]], i32 4, i64 [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 1
; CHECK-NEXT:    [[TMP6:%.*]] = fpext float [[C]] to double
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], double [[TMP6]], double [[TMP1]]
; CHECK-NEXT:    store double [[TMP7]], ptr [[TMP2]], align 1
; CHECK-NEXT:    store float [[C]], ptr [[DST]], align 1
; CHECK-NEXT:    ret void
;
entry:
  %b = load float, ptr @float_const
  %c = fadd float %b, 1.0
  store float %c, ptr %dst, align 1
  ret void
}

define void @constantload_add_store_x86_fp80(ptr %dst) sanitize_numerical_stability {
; CHECK-LABEL: @constantload_add_store_x86_fp80(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[B:%.*]] = load x86_fp80, ptr @x86_fp80_const, align 16
; CHECK-NEXT:    [[TMP0:%.*]] = fpext x86_fp80 [[B]] to fp128
; CHECK-NEXT:    [[C:%.*]] = fadd x86_fp80 [[B]], 0xK3FC9E69594BEC44DE000
; CHECK-NEXT:    [[TMP1:%.*]] = fadd fp128 [[TMP0]], 0xLC0000000000000003FC9CD2B297D889B
; CHECK-NEXT:    [[TMP2:%.*]] = call ptr @__nsan_get_shadow_ptr_for_longdouble_store(ptr [[DST:%.*]], i64 1)
; CHECK-NEXT:    [[TMP3:%.*]] = ptrtoint ptr [[DST]] to i64
; CHECK-NEXT:    [[TMP4:%.*]] = call i32 @__nsan_internal_check_longdouble_q(x86_fp80 [[C]], fp128 [[TMP1]], i32 4, i64 [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 1
; CHECK-NEXT:    [[TMP6:%.*]] = fpext x86_fp80 [[C]] to fp128
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], fp128 [[TMP6]], fp128 [[TMP1]]
; CHECK-NEXT:    store fp128 [[TMP7]], ptr [[TMP2]], align 1
; CHECK-NEXT:    store x86_fp80 [[C]], ptr [[DST]], align 1
; CHECK-NEXT:    ret void
;
entry:
  %b = load x86_fp80, ptr @x86_fp80_const
  %c = fadd x86_fp80 %b, 0xK3FC9E69594BEC44DE000
  store x86_fp80 %c, ptr %dst, align 1
  ret void
}

define void @constantload_add_store_double(ptr %dst) sanitize_numerical_stability {
; DQQ-LABEL: @constantload_add_store_double(
; DQQ-NEXT:  entry:
; DQQ-NEXT:    [[B:%.*]] = load double, ptr @double_const, align 8
; DQQ-NEXT:    [[TMP0:%.*]] = fpext double [[B]] to fp128
; DQQ-NEXT:    [[C:%.*]] = fadd double [[B]], 1.000000e+00
; DQQ-NEXT:    [[TMP1:%.*]] = fadd fp128 [[TMP0]], 0xL00000000000000003FFF000000000000
; DQQ-NEXT:    [[TMP2:%.*]] = call ptr @__nsan_get_shadow_ptr_for_double_store(ptr [[DST:%.*]], i64 1)
; DQQ-NEXT:    [[TMP3:%.*]] = ptrtoint ptr [[DST]] to i64
; DQQ-NEXT:    [[TMP4:%.*]] = call i32 @__nsan_internal_check_double_q(double [[C]], fp128 [[TMP1]], i32 4, i64 [[TMP3]])
; DQQ-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 1
; DQQ-NEXT:    [[TMP6:%.*]] = fpext double [[C]] to fp128
; DQQ-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], fp128 [[TMP6]], fp128 [[TMP1]]
; DQQ-NEXT:    store fp128 [[TMP7]], ptr [[TMP2]], align 1
; DQQ-NEXT:    store double [[C]], ptr [[DST]], align 1
; DQQ-NEXT:    ret void
;
; DLQ-LABEL: @constantload_add_store_double(
; DLQ-NEXT:  entry:
; DLQ-NEXT:    [[B:%.*]] = load double, ptr @double_const, align 8
; DLQ-NEXT:    [[TMP0:%.*]] = fpext double [[B]] to x86_fp80
; DLQ-NEXT:    [[C:%.*]] = fadd double [[B]], 1.000000e+00
; DLQ-NEXT:    [[TMP1:%.*]] = fadd x86_fp80 [[TMP0]], 0xK3FFF8000000000000000
; DLQ-NEXT:    [[TMP2:%.*]] = call ptr @__nsan_get_shadow_ptr_for_double_store(ptr [[DST:%.*]], i64 1)
; DLQ-NEXT:    [[TMP3:%.*]] = ptrtoint ptr [[DST]] to i64
; DLQ-NEXT:    [[TMP4:%.*]] = call i32 @__nsan_internal_check_double_l(double [[C]], x86_fp80 [[TMP1]], i32 4, i64 [[TMP3]])
; DLQ-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 1
; DLQ-NEXT:    [[TMP6:%.*]] = fpext double [[C]] to x86_fp80
; DLQ-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], x86_fp80 [[TMP6]], x86_fp80 [[TMP1]]
; DLQ-NEXT:    store x86_fp80 [[TMP7]], ptr [[TMP2]], align 1
; DLQ-NEXT:    store double [[C]], ptr [[DST]], align 1
; DLQ-NEXT:    ret void
;
entry:
  %b = load double, ptr @double_const
  %c = fadd double %b, 1.0
  store double %c, ptr %dst, align 1
  ret void
}

define void @load_add_store_float(ptr %a) sanitize_numerical_stability {
; CHECK-LABEL: @load_add_store_float(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[B:%.*]] = load float, ptr [[A:%.*]], align 1
; CHECK-NEXT:    [[TMP0:%.*]] = call ptr @__nsan_get_shadow_ptr_for_float_load(ptr [[A]], i64 1)
; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq ptr [[TMP0]], null
; CHECK-NEXT:    br i1 [[TMP1]], label [[TMP4:%.*]], label [[TMP2:%.*]]
; CHECK:       2:
; CHECK-NEXT:    [[TMP3:%.*]] = load double, ptr [[TMP0]], align 1
; CHECK-NEXT:    br label [[TMP6:%.*]]
; CHECK:       4:
; CHECK-NEXT:    [[TMP5:%.*]] = fpext float [[B]] to double
; CHECK-NEXT:    br label [[TMP6]]
; CHECK:       6:
; CHECK-NEXT:    [[TMP7:%.*]] = phi double [ [[TMP3]], [[TMP2]] ], [ [[TMP5]], [[TMP4]] ]
; CHECK-NEXT:    [[C:%.*]] = fadd float [[B]], 1.000000e+00
; CHECK-NEXT:    [[TMP8:%.*]] = fadd double [[TMP7]], 1.000000e+00
; CHECK-NEXT:    [[TMP9:%.*]] = call ptr @__nsan_get_shadow_ptr_for_float_store(ptr [[A]], i64 1)
; CHECK-NEXT:    [[TMP10:%.*]] = ptrtoint ptr [[A]] to i64
; CHECK-NEXT:    [[TMP11:%.*]] = call i32 @__nsan_internal_check_float_d(float [[C]], double [[TMP8]], i32 4, i64 [[TMP10]])
; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[TMP11]], 1
; CHECK-NEXT:    [[TMP13:%.*]] = fpext float [[C]] to double
; CHECK-NEXT:    [[TMP14:%.*]] = select i1 [[TMP12]], double [[TMP13]], double [[TMP8]]
; CHECK-NEXT:    store double [[TMP14]], ptr [[TMP9]], align 1
; CHECK-NEXT:    store float [[C]], ptr [[A]], align 1
; CHECK-NEXT:    ret void
;
entry:
  %b = load float, ptr %a, align 1
  %c = fadd float %b, 1.0
  store float %c, ptr %a, align 1
  ret void
}

define void @load_add_store_x86_fp80(ptr %a) sanitize_numerical_stability {
; CHECK-LABEL: @load_add_store_x86_fp80(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[B:%.*]] = load x86_fp80, ptr [[A:%.*]], align 1
; CHECK-NEXT:    [[TMP0:%.*]] = call ptr @__nsan_get_shadow_ptr_for_longdouble_load(ptr [[A]], i64 1)
; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq ptr [[TMP0]], null
; CHECK-NEXT:    br i1 [[TMP1]], label [[TMP4:%.*]], label [[TMP2:%.*]]
; CHECK:       2:
; CHECK-NEXT:    [[TMP3:%.*]] = load fp128, ptr [[TMP0]], align 1
; CHECK-NEXT:    br label [[TMP6:%.*]]
; CHECK:       4:
; CHECK-NEXT:    [[TMP5:%.*]] = fpext x86_fp80 [[B]] to fp128
; CHECK-NEXT:    br label [[TMP6]]
; CHECK:       6:
; CHECK-NEXT:    [[TMP7:%.*]] = phi fp128 [ [[TMP3]], [[TMP2]] ], [ [[TMP5]], [[TMP4]] ]
; CHECK-NEXT:    [[C:%.*]] = fadd x86_fp80 [[B]], 0xK3FC9E69594BEC44DE000
; CHECK-NEXT:    [[TMP8:%.*]] = fadd fp128 [[TMP7]], 0xLC0000000000000003FC9CD2B297D889B
; CHECK-NEXT:    [[TMP9:%.*]] = call ptr @__nsan_get_shadow_ptr_for_longdouble_store(ptr [[A]], i64 1)
; CHECK-NEXT:    [[TMP10:%.*]] = ptrtoint ptr [[A]] to i64
; CHECK-NEXT:    [[TMP11:%.*]] = call i32 @__nsan_internal_check_longdouble_q(x86_fp80 [[C]], fp128 [[TMP8]], i32 4, i64 [[TMP10]])
; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[TMP11]], 1
; CHECK-NEXT:    [[TMP13:%.*]] = fpext x86_fp80 [[C]] to fp128
; CHECK-NEXT:    [[TMP14:%.*]] = select i1 [[TMP12]], fp128 [[TMP13]], fp128 [[TMP8]]
; CHECK-NEXT:    store fp128 [[TMP14]], ptr [[TMP9]], align 1
; CHECK-NEXT:    store x86_fp80 [[C]], ptr [[A]], align 1
; CHECK-NEXT:    ret void
;
entry:
  %b = load x86_fp80, ptr %a, align 1
  %c = fadd x86_fp80 %b, 0xK3FC9E69594BEC44DE000
  store x86_fp80 %c, ptr %a, align 1
  ret void
}

define void @load_add_store_double(ptr %a) sanitize_numerical_stability {
; DQQ-LABEL: @load_add_store_double(
; DQQ-NEXT:  entry:
; DQQ-NEXT:    [[B:%.*]] = load double, ptr [[A:%.*]], align 1
; DQQ-NEXT:    [[TMP0:%.*]] = call ptr @__nsan_get_shadow_ptr_for_double_load(ptr [[A]], i64 1)
; DQQ-NEXT:    [[TMP1:%.*]] = icmp eq ptr [[TMP0]], null
; DQQ-NEXT:    br i1 [[TMP1]], label [[TMP4:%.*]], label [[TMP2:%.*]]
; DQQ:       2:
; DQQ-NEXT:    [[TMP3:%.*]] = load fp128, ptr [[TMP0]], align 1
; DQQ-NEXT:    br label [[TMP6:%.*]]
; DQQ:       4:
; DQQ-NEXT:    [[TMP5:%.*]] = fpext double [[B]] to fp128
; DQQ-NEXT:    br label [[TMP6]]
; DQQ:       6:
; DQQ-NEXT:    [[TMP7:%.*]] = phi fp128 [ [[TMP3]], [[TMP2]] ], [ [[TMP5]], [[TMP4]] ]
; DQQ-NEXT:    [[C:%.*]] = fadd double [[B]], 1.000000e+00
; DQQ-NEXT:    [[TMP8:%.*]] = fadd fp128 [[TMP7]], 0xL00000000000000003FFF000000000000
; DQQ-NEXT:    [[TMP9:%.*]] = call ptr @__nsan_get_shadow_ptr_for_double_store(ptr [[A]], i64 1)
; DQQ-NEXT:    [[TMP10:%.*]] = ptrtoint ptr [[A]] to i64
; DQQ-NEXT:    [[TMP11:%.*]] = call i32 @__nsan_internal_check_double_q(double [[C]], fp128 [[TMP8]], i32 4, i64 [[TMP10]])
; DQQ-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[TMP11]], 1
; DQQ-NEXT:    [[TMP13:%.*]] = fpext double [[C]] to fp128
; DQQ-NEXT:    [[TMP14:%.*]] = select i1 [[TMP12]], fp128 [[TMP13]], fp128 [[TMP8]]
; DQQ-NEXT:    store fp128 [[TMP14]], ptr [[TMP9]], align 1
; DQQ-NEXT:    store double [[C]], ptr [[A]], align 1
; DQQ-NEXT:    ret void
;
; DLQ-LABEL: @load_add_store_double(
; DLQ-NEXT:  entry:
; DLQ-NEXT:    [[B:%.*]] = load double, ptr [[A:%.*]], align 1
; DLQ-NEXT:    [[TMP0:%.*]] = call ptr @__nsan_get_shadow_ptr_for_double_load(ptr [[A]], i64 1)
; DLQ-NEXT:    [[TMP1:%.*]] = icmp eq ptr [[TMP0]], null
; DLQ-NEXT:    br i1 [[TMP1]], label [[TMP4:%.*]], label [[TMP2:%.*]]
; DLQ:       2:
; DLQ-NEXT:    [[TMP3:%.*]] = load x86_fp80, ptr [[TMP0]], align 1
; DLQ-NEXT:    br label [[TMP6:%.*]]
; DLQ:       4:
; DLQ-NEXT:    [[TMP5:%.*]] = fpext double [[B]] to x86_fp80
; DLQ-NEXT:    br label [[TMP6]]
; DLQ:       6:
; DLQ-NEXT:    [[TMP7:%.*]] = phi x86_fp80 [ [[TMP3]], [[TMP2]] ], [ [[TMP5]], [[TMP4]] ]
; DLQ-NEXT:    [[C:%.*]] = fadd double [[B]], 1.000000e+00
; DLQ-NEXT:    [[TMP8:%.*]] = fadd x86_fp80 [[TMP7]], 0xK3FFF8000000000000000
; DLQ-NEXT:    [[TMP9:%.*]] = call ptr @__nsan_get_shadow_ptr_for_double_store(ptr [[A]], i64 1)
; DLQ-NEXT:    [[TMP10:%.*]] = ptrtoint ptr [[A]] to i64
; DLQ-NEXT:    [[TMP11:%.*]] = call i32 @__nsan_internal_check_double_l(double [[C]], x86_fp80 [[TMP8]], i32 4, i64 [[TMP10]])
; DLQ-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[TMP11]], 1
; DLQ-NEXT:    [[TMP13:%.*]] = fpext double [[C]] to x86_fp80
; DLQ-NEXT:    [[TMP14:%.*]] = select i1 [[TMP12]], x86_fp80 [[TMP13]], x86_fp80 [[TMP8]]
; DLQ-NEXT:    store x86_fp80 [[TMP14]], ptr [[TMP9]], align 1
; DLQ-NEXT:    store double [[C]], ptr [[A]], align 1
; DLQ-NEXT:    ret void
;
entry:
  %b = load double, ptr %a, align 1
  %c = fadd double %b, 1.0
  store double %c, ptr %a, align 1
  ret void
}

define void @load_add_store_vector(<2 x float>* %a) sanitize_numerical_stability {
; CHECK-LABEL: @load_add_store_vector(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[B:%.*]] = load <2 x float>, ptr [[A:%.*]], align 1
; CHECK-NEXT:    [[TMP0:%.*]] = call ptr @__nsan_get_shadow_ptr_for_float_load(ptr [[A]], i64 2)
; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq ptr [[TMP0]], null
; CHECK-NEXT:    br i1 [[TMP1]], label [[TMP4:%.*]], label [[TMP2:%.*]]
; CHECK:       2:
; CHECK-NEXT:    [[TMP3:%.*]] = load <2 x double>, ptr [[TMP0]], align 1
; CHECK-NEXT:    br label [[TMP6:%.*]]
; CHECK:       4:
; CHECK-NEXT:    [[TMP5:%.*]] = fpext <2 x float> [[B]] to <2 x double>
; CHECK-NEXT:    br label [[TMP6]]
; CHECK:       6:
; CHECK-NEXT:    [[TMP7:%.*]] = phi <2 x double> [ [[TMP3]], [[TMP2]] ], [ [[TMP5]], [[TMP4]] ]
; CHECK-NEXT:    [[C:%.*]] = fadd <2 x float> [[B]], <float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT:    [[TMP8:%.*]] = fadd <2 x double> [[TMP7]], <double 1.000000e+00, double 1.000000e+00>
; CHECK-NEXT:    [[TMP9:%.*]] = call ptr @__nsan_get_shadow_ptr_for_float_store(ptr [[A]], i64 2)
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <2 x float> [[C]], i64 0
; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <2 x double> [[TMP8]], i64 0
; CHECK-NEXT:    [[TMP12:%.*]] = ptrtoint ptr [[A]] to i64
; CHECK-NEXT:    [[TMP13:%.*]] = call i32 @__nsan_internal_check_float_d(float [[TMP10]], double [[TMP11]], i32 4, i64 [[TMP12]])
; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <2 x float> [[C]], i64 1
; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <2 x double> [[TMP8]], i64 1
; CHECK-NEXT:    [[TMP16:%.*]] = ptrtoint ptr [[A]] to i64
; CHECK-NEXT:    [[TMP17:%.*]] = call i32 @__nsan_internal_check_float_d(float [[TMP14]], double [[TMP15]], i32 4, i64 [[TMP16]])
; CHECK-NEXT:    [[TMP18:%.*]] = or i32 [[TMP13]], [[TMP17]]
; CHECK-NEXT:    [[TMP19:%.*]] = icmp eq i32 [[TMP18]], 1
; CHECK-NEXT:    [[TMP20:%.*]] = fpext <2 x float> [[C]] to <2 x double>
; CHECK-NEXT:    [[TMP21:%.*]] = select i1 [[TMP19]], <2 x double> [[TMP20]], <2 x double> [[TMP8]]
; CHECK-NEXT:    store <2 x double> [[TMP21]], ptr [[TMP9]], align 1
; CHECK-NEXT:    store <2 x float> [[C]], ptr [[A]], align 1
; CHECK-NEXT:    ret void
;
entry:
  %b = load <2 x float>, ptr %a, align 1
  %c = fadd <2 x float> %b, <float 1.0, float 1.0>
  store <2 x float> %c, ptr %a, align 1
  ret void
}

declare float @returns_float()

define void @call_fn_returning_float(ptr %dst) sanitize_numerical_stability {
; CHECK-LABEL: @call_fn_returning_float(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[B:%.*]] = call float @returns_float()
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, ptr @__nsan_shadow_ret_tag, align 8
; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq i64 [[TMP0]], ptrtoint (ptr @returns_float to i64)
; CHECK-NEXT:    [[TMP2:%.*]] = load double, ptr @__nsan_shadow_ret_ptr, align 8
; CHECK-NEXT:    [[TMP3:%.*]] = fpext float [[B]] to double
; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP1]], double [[TMP2]], double [[TMP3]]
; CHECK-NEXT:    [[C:%.*]] = fadd float [[B]], 1.000000e+00
; CHECK-NEXT:    [[TMP5:%.*]] = fadd double [[TMP4]], 1.000000e+00
; CHECK-NEXT:    [[TMP6:%.*]] = call ptr @__nsan_get_shadow_ptr_for_float_store(ptr [[DST:%.*]], i64 1)
; CHECK-NEXT:    [[TMP7:%.*]] = ptrtoint ptr [[DST]] to i64
; CHECK-NEXT:    [[TMP8:%.*]] = call i32 @__nsan_internal_check_float_d(float [[C]], double [[TMP5]], i32 4, i64 [[TMP7]])
; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[TMP8]], 1
; CHECK-NEXT:    [[TMP10:%.*]] = fpext float [[C]] to double
; CHECK-NEXT:    [[TMP11:%.*]] = select i1 [[TMP9]], double [[TMP10]], double [[TMP5]]
; CHECK-NEXT:    store double [[TMP11]], ptr [[TMP6]], align 1
; CHECK-NEXT:    store float [[C]], ptr [[DST]], align 1
; CHECK-NEXT:    ret void
;
entry:
  %b = call float @returns_float()
  %c = fadd float %b, 1.0
  store float %c, ptr %dst, align 1
  ret void
}

define float @return_fn_returning_float(ptr %dst) sanitize_numerical_stability {
; CHECK-LABEL: @return_fn_returning_float(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[B:%.*]] = call float @returns_float()
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, ptr @__nsan_shadow_ret_tag, align 8
; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq i64 [[TMP0]], ptrtoint (ptr @returns_float to i64)
; CHECK-NEXT:    [[TMP2:%.*]] = load double, ptr @__nsan_shadow_ret_ptr, align 8
; CHECK-NEXT:    [[TMP3:%.*]] = fpext float [[B]] to double
; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP1]], double [[TMP2]], double [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @__nsan_internal_check_float_d(float [[B]], double [[TMP4]], i32 1, i64 0)
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[TMP5]], 1
; CHECK-NEXT:    [[TMP7:%.*]] = fpext float [[B]] to double
; CHECK-NEXT:    [[TMP8:%.*]] = select i1 [[TMP6]], double [[TMP7]], double [[TMP4]]
; CHECK-NEXT:    store i64 ptrtoint (ptr @return_fn_returning_float to i64), ptr @__nsan_shadow_ret_tag, align 8
; CHECK-NEXT:    store double [[TMP8]], ptr @__nsan_shadow_ret_ptr, align 8
; CHECK-NEXT:    ret float [[B]]
;
entry:
  %b = call float @returns_float()
  ret float %b
}

declare void @takes_floats(float %a, i8 %b, double %c, x86_fp80 %d)

define void @call_fn_taking_float() sanitize_numerical_stability {
; DQQ-LABEL: @call_fn_taking_float(
; DQQ-NEXT:  entry:
; DQQ-NEXT:    store ptr @takes_floats, ptr @__nsan_shadow_args_tag, align 8
; DQQ-NEXT:    store double 1.000000e+00, ptr @__nsan_shadow_args_ptr, align 1
; DQQ-NEXT:    store fp128 0xL00000000000000004000800000000000, ptr getelementptr ([16384 x i8], ptr @__nsan_shadow_args_ptr, i64 0, i64 8), align 1
; DQQ-NEXT:    store fp128 0xLC0000000000000003FC9CD2B297D889B, ptr getelementptr ([16384 x i8], ptr @__nsan_shadow_args_ptr, i64 0, i64 24), align 1
; DQQ-NEXT:    call void @takes_floats(float 1.000000e+00, i8 2, double 3.000000e+00, x86_fp80 0xK3FC9E69594BEC44DE000)
; DQQ-NEXT:    ret void
;
; DLQ-LABEL: @call_fn_taking_float(
; DLQ-NEXT:  entry:
; DLQ-NEXT:    store ptr @takes_floats, ptr @__nsan_shadow_args_tag, align 8
; DLQ-NEXT:    store double 1.000000e+00, ptr @__nsan_shadow_args_ptr, align 1
; DLQ-NEXT:    store x86_fp80 0xK4000C000000000000000, ptr getelementptr ([16384 x i8], ptr @__nsan_shadow_args_ptr, i64 0, i64 8), align 1
; DLQ-NEXT:    store fp128 0xLC0000000000000003FC9CD2B297D889B, ptr getelementptr ([16384 x i8], ptr @__nsan_shadow_args_ptr, i64 0, i64 18), align 1
; DLQ-NEXT:    call void @takes_floats(float 1.000000e+00, i8 2, double 3.000000e+00, x86_fp80 0xK3FC9E69594BEC44DE000)
; DLQ-NEXT:    ret void
;
entry:
  call void @takes_floats(float 1.0, i8 2, double 3.0, x86_fp80 0xK3FC9E69594BEC44DE000)
  ret void
}

declare float @llvm.sin.f32(float) readnone

define float @call_sin_intrinsic() sanitize_numerical_stability {
; CHECK-LABEL: @call_sin_intrinsic(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[R:%.*]] = call float @llvm.sin.f32(float 1.000000e+00)
; CHECK-NEXT:    [[TMP0:%.*]] = call double @llvm.sin.f64(double 1.000000e+00)
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @__nsan_internal_check_float_d(float [[R]], double [[TMP0]], i32 1, i64 0)
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i32 [[TMP1]], 1
; CHECK-NEXT:    [[TMP3:%.*]] = fpext float [[R]] to double
; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP2]], double [[TMP3]], double [[TMP0]]
; CHECK-NEXT:    store i64 ptrtoint (ptr @call_sin_intrinsic to i64), ptr @__nsan_shadow_ret_tag, align 8
; CHECK-NEXT:    store double [[TMP4]], ptr @__nsan_shadow_ret_ptr, align 8
; CHECK-NEXT:    ret float [[R]]
;
entry:
  %r = call float @llvm.sin.f32(float 1.0)
  ret float %r
}

declare float @sinf(float)

define float @call_sinf_libfunc() sanitize_numerical_stability {
; CHECK-LABEL: @call_sinf_libfunc(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[R:%.*]] = call float @sinf(float 1.000000e+00) #[[ATTR4:[0-9]+]]
; CHECK-NEXT:    [[TMP0:%.*]] = call double @llvm.sin.f64(double 1.000000e+00)
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @__nsan_internal_check_float_d(float [[R]], double [[TMP0]], i32 1, i64 0)
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i32 [[TMP1]], 1
; CHECK-NEXT:    [[TMP3:%.*]] = fpext float [[R]] to double
; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP2]], double [[TMP3]], double [[TMP0]]
; CHECK-NEXT:    store i64 ptrtoint (ptr @call_sinf_libfunc to i64), ptr @__nsan_shadow_ret_tag, align 8
; CHECK-NEXT:    store double [[TMP4]], ptr @__nsan_shadow_ret_ptr, align 8
; CHECK-NEXT:    ret float [[R]]
;
entry:
  %r = call float @sinf(float 1.0)
  ret float %r
}

declare double @sin(double)

; FIXME: nsan uses `sin(double)` for fp128.
define double @call_sin_libfunc() sanitize_numerical_stability {
; DQQ-LABEL: @call_sin_libfunc(
; DQQ-NEXT:  entry:
; DQQ-NEXT:    [[R:%.*]] = call double @sin(double 1.000000e+00) #[[ATTR4]]
; DQQ-NEXT:    [[TMP0:%.*]] = call x86_fp80 @llvm.sin.f80(x86_fp80 0xK3FFF8000000000000000)
; DQQ-NEXT:    [[TMP1:%.*]] = fpext x86_fp80 [[TMP0]] to fp128
; DQQ-NEXT:    [[TMP2:%.*]] = call i32 @__nsan_internal_check_double_q(double [[R]], fp128 [[TMP1]], i32 1, i64 0)
; DQQ-NEXT:    [[TMP3:%.*]] = icmp eq i32 [[TMP2]], 1
; DQQ-NEXT:    [[TMP4:%.*]] = fpext double [[R]] to fp128
; DQQ-NEXT:    [[TMP5:%.*]] = select i1 [[TMP3]], fp128 [[TMP4]], fp128 [[TMP1]]
; DQQ-NEXT:    store i64 ptrtoint (ptr @call_sin_libfunc to i64), ptr @__nsan_shadow_ret_tag, align 8
; DQQ-NEXT:    store fp128 [[TMP5]], ptr @__nsan_shadow_ret_ptr, align 16
; DQQ-NEXT:    ret double [[R]]
;
; DLQ-LABEL: @call_sin_libfunc(
; DLQ-NEXT:  entry:
; DLQ-NEXT:    [[R:%.*]] = call double @sin(double 1.000000e+00) #[[ATTR4]]
; DLQ-NEXT:    [[TMP0:%.*]] = call x86_fp80 @llvm.sin.f80(x86_fp80 0xK3FFF8000000000000000)
; DLQ-NEXT:    [[TMP1:%.*]] = call i32 @__nsan_internal_check_double_l(double [[R]], x86_fp80 [[TMP0]], i32 1, i64 0)
; DLQ-NEXT:    [[TMP2:%.*]] = icmp eq i32 [[TMP1]], 1
; DLQ-NEXT:    [[TMP3:%.*]] = fpext double [[R]] to x86_fp80
; DLQ-NEXT:    [[TMP4:%.*]] = select i1 [[TMP2]], x86_fp80 [[TMP3]], x86_fp80 [[TMP0]]
; DLQ-NEXT:    store i64 ptrtoint (ptr @call_sin_libfunc to i64), ptr @__nsan_shadow_ret_tag, align 8
; DLQ-NEXT:    store x86_fp80 [[TMP4]], ptr @__nsan_shadow_ret_ptr, align 16
; DLQ-NEXT:    ret double [[R]]
;
entry:
  %r = call double @sin(double 1.0)
  ret double %r
}

declare double @frexp(double, i32*)

define double @call_frexp_libfunc_nointrinsic(double %0, i32* nocapture %1) sanitize_numerical_stability {
; DQQ-LABEL: @call_frexp_libfunc_nointrinsic(
; DQQ-NEXT:    [[TMP3:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; DQQ-NEXT:    [[TMP4:%.*]] = icmp eq i64 [[TMP3]], ptrtoint (ptr @call_frexp_libfunc_nointrinsic to i64)
; DQQ-NEXT:    [[TMP5:%.*]] = load fp128, ptr @__nsan_shadow_args_ptr, align 1
; DQQ-NEXT:    [[TMP6:%.*]] = fpext double [[TMP0:%.*]] to fp128
; DQQ-NEXT:    [[TMP7:%.*]] = select i1 [[TMP4]], fp128 [[TMP5]], fp128 [[TMP6]]
; DQQ-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; DQQ-NEXT:    [[TMP8:%.*]] = call i32 @__nsan_internal_check_double_q(double [[TMP0]], fp128 [[TMP7]], i32 2, i64 0)
; DQQ-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[TMP8]], 1
; DQQ-NEXT:    [[TMP10:%.*]] = fpext double [[TMP0]] to fp128
; DQQ-NEXT:    [[TMP11:%.*]] = select i1 [[TMP9]], fp128 [[TMP10]], fp128 [[TMP7]]
; DQQ-NEXT:    [[TMP12:%.*]] = tail call double @frexp(double [[TMP0]], ptr [[TMP1:%.*]])
; DQQ-NEXT:    [[TMP13:%.*]] = load i64, ptr @__nsan_shadow_ret_tag, align 8
; DQQ-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[TMP13]], ptrtoint (ptr @frexp to i64)
; DQQ-NEXT:    [[TMP15:%.*]] = load fp128, ptr @__nsan_shadow_ret_ptr, align 16
; DQQ-NEXT:    [[TMP16:%.*]] = fpext double [[TMP12]] to fp128
; DQQ-NEXT:    [[TMP17:%.*]] = select i1 [[TMP14]], fp128 [[TMP15]], fp128 [[TMP16]]
; DQQ-NEXT:    [[TMP18:%.*]] = call i32 @__nsan_internal_check_double_q(double [[TMP12]], fp128 [[TMP17]], i32 1, i64 0)
; DQQ-NEXT:    [[TMP19:%.*]] = icmp eq i32 [[TMP18]], 1
; DQQ-NEXT:    [[TMP20:%.*]] = fpext double [[TMP12]] to fp128
; DQQ-NEXT:    [[TMP21:%.*]] = select i1 [[TMP19]], fp128 [[TMP20]], fp128 [[TMP17]]
; DQQ-NEXT:    store i64 ptrtoint (ptr @call_frexp_libfunc_nointrinsic to i64), ptr @__nsan_shadow_ret_tag, align 8
; DQQ-NEXT:    store fp128 [[TMP21]], ptr @__nsan_shadow_ret_ptr, align 16
; DQQ-NEXT:    ret double [[TMP12]]
;
; DLQ-LABEL: @call_frexp_libfunc_nointrinsic(
; DLQ-NEXT:    [[TMP3:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; DLQ-NEXT:    [[TMP4:%.*]] = icmp eq i64 [[TMP3]], ptrtoint (ptr @call_frexp_libfunc_nointrinsic to i64)
; DLQ-NEXT:    [[TMP5:%.*]] = load x86_fp80, ptr @__nsan_shadow_args_ptr, align 1
; DLQ-NEXT:    [[TMP6:%.*]] = fpext double [[TMP0:%.*]] to x86_fp80
; DLQ-NEXT:    [[TMP7:%.*]] = select i1 [[TMP4]], x86_fp80 [[TMP5]], x86_fp80 [[TMP6]]
; DLQ-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; DLQ-NEXT:    [[TMP8:%.*]] = call i32 @__nsan_internal_check_double_l(double [[TMP0]], x86_fp80 [[TMP7]], i32 2, i64 0)
; DLQ-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[TMP8]], 1
; DLQ-NEXT:    [[TMP10:%.*]] = fpext double [[TMP0]] to x86_fp80
; DLQ-NEXT:    [[TMP11:%.*]] = select i1 [[TMP9]], x86_fp80 [[TMP10]], x86_fp80 [[TMP7]]
; DLQ-NEXT:    [[TMP12:%.*]] = tail call double @frexp(double [[TMP0]], ptr [[TMP1:%.*]])
; DLQ-NEXT:    [[TMP13:%.*]] = load i64, ptr @__nsan_shadow_ret_tag, align 8
; DLQ-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[TMP13]], ptrtoint (ptr @frexp to i64)
; DLQ-NEXT:    [[TMP15:%.*]] = load x86_fp80, ptr @__nsan_shadow_ret_ptr, align 16
; DLQ-NEXT:    [[TMP16:%.*]] = fpext double [[TMP12]] to x86_fp80
; DLQ-NEXT:    [[TMP17:%.*]] = select i1 [[TMP14]], x86_fp80 [[TMP15]], x86_fp80 [[TMP16]]
; DLQ-NEXT:    [[TMP18:%.*]] = call i32 @__nsan_internal_check_double_l(double [[TMP12]], x86_fp80 [[TMP17]], i32 1, i64 0)
; DLQ-NEXT:    [[TMP19:%.*]] = icmp eq i32 [[TMP18]], 1
; DLQ-NEXT:    [[TMP20:%.*]] = fpext double [[TMP12]] to x86_fp80
; DLQ-NEXT:    [[TMP21:%.*]] = select i1 [[TMP19]], x86_fp80 [[TMP20]], x86_fp80 [[TMP17]]
; DLQ-NEXT:    store i64 ptrtoint (ptr @call_frexp_libfunc_nointrinsic to i64), ptr @__nsan_shadow_ret_tag, align 8
; DLQ-NEXT:    store x86_fp80 [[TMP21]], ptr @__nsan_shadow_ret_ptr, align 16
; DLQ-NEXT:    ret double [[TMP12]]
;
  %3 = tail call double @frexp(double %0, i32* %1)
  ret double %3
}

define float @call_fn_taking_float_by_fn_ptr(float (float)* nocapture %fn_ptr) sanitize_numerical_stability {
; CHECK-LABEL: @call_fn_taking_float_by_fn_ptr(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    store ptr [[FN_PTR:%.*]], ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    store double 1.000000e+00, ptr @__nsan_shadow_args_ptr, align 1
; CHECK-NEXT:    [[R:%.*]] = call float [[FN_PTR]](float 1.000000e+00)
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, ptr @__nsan_shadow_ret_tag, align 8
; CHECK-NEXT:    [[TMP1:%.*]] = ptrtoint ptr [[FN_PTR]] to i64
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[TMP0]], [[TMP1]]
; CHECK-NEXT:    [[TMP3:%.*]] = load double, ptr @__nsan_shadow_ret_ptr, align 8
; CHECK-NEXT:    [[TMP4:%.*]] = fpext float [[R]] to double
; CHECK-NEXT:    [[TMP5:%.*]] = select i1 [[TMP2]], double [[TMP3]], double [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = call i32 @__nsan_internal_check_float_d(float [[R]], double [[TMP5]], i32 1, i64 0)
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[TMP6]], 1
; CHECK-NEXT:    [[TMP8:%.*]] = fpext float [[R]] to double
; CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[TMP7]], double [[TMP8]], double [[TMP5]]
; CHECK-NEXT:    store i64 ptrtoint (ptr @call_fn_taking_float_by_fn_ptr to i64), ptr @__nsan_shadow_ret_tag, align 8
; CHECK-NEXT:    store double [[TMP9]], ptr @__nsan_shadow_ret_ptr, align 8
; CHECK-NEXT:    ret float [[R]]
;
entry:
  %r = call float %fn_ptr(float 1.0)
  ret float %r
}

define void @store_float(ptr %dst) sanitize_numerical_stability {
; CHECK-LABEL: @store_float(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call ptr @__nsan_get_shadow_ptr_for_float_store(ptr [[DST:%.*]], i64 1)
; CHECK-NEXT:    store double 4.200000e+01, ptr [[TMP0]], align 1
; CHECK-NEXT:    store float 4.200000e+01, ptr [[DST]], align 1
; CHECK-NEXT:    ret void
;
entry:
  store float 42.0, ptr %dst, align 1
  ret void
}

define i1 @inline_asm(double %0) sanitize_numerical_stability {
; DQQ-LABEL: @inline_asm(
; DQQ-NEXT:  entry:
; DQQ-NEXT:    [[TMP1:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; DQQ-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[TMP1]], ptrtoint (ptr @inline_asm to i64)
; DQQ-NEXT:    [[TMP3:%.*]] = load fp128, ptr @__nsan_shadow_args_ptr, align 1
; DQQ-NEXT:    [[TMP4:%.*]] = fpext double [[TMP0:%.*]] to fp128
; DQQ-NEXT:    [[TMP5:%.*]] = select i1 [[TMP2]], fp128 [[TMP3]], fp128 [[TMP4]]
; DQQ-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; DQQ-NEXT:    [[TMP6:%.*]] = call i32 asm "pmovmskb $1, $0", "=r,x,~{dirflag},~{fpsr},~{flags}"(double [[TMP0]])
; DQQ-NEXT:    [[TMP7:%.*]] = trunc i32 [[TMP6]] to i8
; DQQ-NEXT:    [[TMP8:%.*]] = icmp slt i8 [[TMP7]], 0
; DQQ-NEXT:    ret i1 [[TMP8]]
;
; DLQ-LABEL: @inline_asm(
; DLQ-NEXT:  entry:
; DLQ-NEXT:    [[TMP1:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; DLQ-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[TMP1]], ptrtoint (ptr @inline_asm to i64)
; DLQ-NEXT:    [[TMP3:%.*]] = load x86_fp80, ptr @__nsan_shadow_args_ptr, align 1
; DLQ-NEXT:    [[TMP4:%.*]] = fpext double [[TMP0:%.*]] to x86_fp80
; DLQ-NEXT:    [[TMP5:%.*]] = select i1 [[TMP2]], x86_fp80 [[TMP3]], x86_fp80 [[TMP4]]
; DLQ-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; DLQ-NEXT:    [[TMP6:%.*]] = call i32 asm "pmovmskb $1, $0", "=r,x,~{dirflag},~{fpsr},~{flags}"(double [[TMP0]])
; DLQ-NEXT:    [[TMP7:%.*]] = trunc i32 [[TMP6]] to i8
; DLQ-NEXT:    [[TMP8:%.*]] = icmp slt i8 [[TMP7]], 0
; DLQ-NEXT:    ret i1 [[TMP8]]
;
entry:
  %1 = call i32 asm "pmovmskb $1, $0", "=r,x,~{dirflag},~{fpsr},~{flags}"(double %0)
  %2 = trunc i32 %1 to i8
  %3 = icmp slt i8 %2, 0
  ret i1 %3
}

define void @vector_extract(<2 x float> %0) sanitize_numerical_stability {
; CHECK-LABEL: @vector_extract(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP1:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[TMP1]], ptrtoint (ptr @vector_extract to i64)
; CHECK-NEXT:    [[TMP3:%.*]] = load <2 x double>, ptr @__nsan_shadow_args_ptr, align 1
; CHECK-NEXT:    [[TMP4:%.*]] = fpext <2 x float> [[TMP0:%.*]] to <2 x double>
; CHECK-NEXT:    [[TMP5:%.*]] = select i1 [[TMP2]], <2 x double> [[TMP3]], <2 x double> [[TMP4]]
; CHECK-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x float> [[TMP0]], i32 1
; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <2 x double> [[TMP5]], i32 1
; CHECK-NEXT:    ret void
;
entry:
  %1 = extractelement <2 x float> %0, i32 1
  ret void
}

define void @vector_insert(<2 x float> %0) sanitize_numerical_stability {
; CHECK-LABEL: @vector_insert(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP1:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[TMP1]], ptrtoint (ptr @vector_insert to i64)
; CHECK-NEXT:    [[TMP3:%.*]] = load <2 x double>, ptr @__nsan_shadow_args_ptr, align 1
; CHECK-NEXT:    [[TMP4:%.*]] = fpext <2 x float> [[TMP0:%.*]] to <2 x double>
; CHECK-NEXT:    [[TMP5:%.*]] = select i1 [[TMP2]], <2 x double> [[TMP3]], <2 x double> [[TMP4]]
; CHECK-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <2 x float> [[TMP0]], float 1.000000e+00, i32 1
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <2 x double> [[TMP5]], double 1.000000e+00, i32 1
; CHECK-NEXT:    ret void
;
entry:
  %1 = insertelement <2 x float> %0, float 1.0, i32 1
  ret void
}

define void @freeze_vector_insert(<2 x float> %vec, i32 %idx, float %scalar) sanitize_numerical_stability {
; CHECK-LABEL: @freeze_vector_insert(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq i64 [[TMP0]], ptrtoint (ptr @freeze_vector_insert to i64)
; CHECK-NEXT:    [[TMP2:%.*]] = load <2 x double>, ptr @__nsan_shadow_args_ptr, align 1
; CHECK-NEXT:    [[TMP3:%.*]] = fpext <2 x float> [[VEC:%.*]] to <2 x double>
; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP1]], <2 x double> [[TMP2]], <2 x double> [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = load double, ptr getelementptr ([16384 x i8], ptr @__nsan_shadow_args_ptr, i64 0, i64 16), align 1
; CHECK-NEXT:    [[TMP6:%.*]] = fpext float [[SCALAR:%.*]] to double
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP1]], double [[TMP5]], double [[TMP6]]
; CHECK-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <2 x float> [[VEC]], float [[SCALAR]], i32 [[IDX:%.*]]
; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <2 x double> [[TMP4]], double [[TMP7]], i32 [[IDX]]
; CHECK-NEXT:    [[FROZEN:%.*]] = freeze <2 x float> [[TMP8]]
; CHECK-NEXT:    [[TMP10:%.*]] = freeze <2 x double> [[TMP9]]
; CHECK-NEXT:    ret void
;
entry:
  %1 = insertelement <2 x float> %vec, float %scalar, i32 %idx
  %frozen = freeze <2 x float> %1
  ret void
}

define void @vector_shuffle(<2 x float> %0) sanitize_numerical_stability {
; CHECK-LABEL: @vector_shuffle(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP1:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[TMP1]], ptrtoint (ptr @vector_shuffle to i64)
; CHECK-NEXT:    [[TMP3:%.*]] = load <2 x double>, ptr @__nsan_shadow_args_ptr, align 1
; CHECK-NEXT:    [[TMP4:%.*]] = fpext <2 x float> [[TMP0:%.*]] to <2 x double>
; CHECK-NEXT:    [[TMP5:%.*]] = select i1 [[TMP2]], <2 x double> [[TMP3]], <2 x double> [[TMP4]]
; CHECK-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <2 x float> [[TMP0]], <2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x i32> <i32 1, i32 3>
; CHECK-NEXT:    [[TMP7:%.*]] = shufflevector <2 x double> [[TMP5]], <2 x double> <double 1.000000e+00, double 1.000000e+00>, <2 x i32> <i32 1, i32 3>
; CHECK-NEXT:    ret void
;
entry:
  %1 = shufflevector <2 x float> %0, <2 x float> <float 1.0, float 1.0>, <2 x i32> <i32 1, i32 3>
  ret void
}

define void @aggregate_extract({i32, {float, i1}} %0) sanitize_numerical_stability {
; CHECK-LABEL: @aggregate_extract(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP1:%.*]] = extractvalue { i32, { float, i1 } } [[TMP0:%.*]], 1, 0
; CHECK-NEXT:    [[TMP2:%.*]] = fpext float [[TMP1]] to double
; CHECK-NEXT:    ret void
;
entry:
  %1 = extractvalue {i32, {float, i1}} %0, 1, 0
  ret void
}

define void @aggregate_insert({i32, {float, i1}} %0, float %1) sanitize_numerical_stability {
; CHECK-LABEL: @aggregate_insert(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP2:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP3:%.*]] = icmp eq i64 [[TMP2]], ptrtoint (ptr @aggregate_insert to i64)
; CHECK-NEXT:    [[TMP4:%.*]] = load double, ptr @__nsan_shadow_args_ptr, align 1
; CHECK-NEXT:    [[TMP5:%.*]] = fpext float [[TMP1:%.*]] to double
; CHECK-NEXT:    [[TMP6:%.*]] = select i1 [[TMP3]], double [[TMP4]], double [[TMP5]]
; CHECK-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @__nsan_internal_check_float_d(float [[TMP1]], double [[TMP6]], i32 5, i64 0)
; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i32 [[TMP7]], 1
; CHECK-NEXT:    [[TMP9:%.*]] = fpext float [[TMP1]] to double
; CHECK-NEXT:    [[TMP10:%.*]] = select i1 [[TMP8]], double [[TMP9]], double [[TMP6]]
; CHECK-NEXT:    [[TMP11:%.*]] = insertvalue { i32, { float, i1 } } [[TMP0:%.*]], float [[TMP1]], 1, 0
; CHECK-NEXT:    ret void
;
entry:
  %2 = insertvalue {i32, {float, i1}} %0, float %1, 1, 0
  ret void
}

define void @aggregate_insert_avoid_const_check({i32, {float, i1}} %0) sanitize_numerical_stability {
; CHECK-LABEL: @aggregate_insert_avoid_const_check(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP1:%.*]] = insertvalue { i32, { float, i1 } } [[TMP0:%.*]], float 1.000000e+00, 1, 0
; CHECK-NEXT:    ret void
;
entry:
  %1 = insertvalue {i32, {float, i1}} %0, float 1.0, 1, 0
  ret void
}


declare float @fabsf(float)

define float @sub_fabs(float %a, float %b) sanitize_numerical_stability {
; CHECK-LABEL: @sub_fabs(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq i64 [[TMP0]], ptrtoint (ptr @sub_fabs to i64)
; CHECK-NEXT:    [[TMP2:%.*]] = load double, ptr @__nsan_shadow_args_ptr, align 1
; CHECK-NEXT:    [[TMP3:%.*]] = fpext float [[A:%.*]] to double
; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP1]], double [[TMP2]], double [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = load double, ptr getelementptr ([16384 x i8], ptr @__nsan_shadow_args_ptr, i64 0, i64 8), align 1
; CHECK-NEXT:    [[TMP6:%.*]] = fpext float [[B:%.*]] to double
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP1]], double [[TMP5]], double [[TMP6]]
; CHECK-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[S:%.*]] = fsub float [[A]], [[B]]
; CHECK-NEXT:    [[TMP8:%.*]] = fsub double [[TMP4]], [[TMP7]]
; CHECK-NEXT:    [[TMP9:%.*]] = call i32 @__nsan_internal_check_float_d(float [[S]], double [[TMP8]], i32 2, i64 0)
; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i32 [[TMP9]], 1
; CHECK-NEXT:    [[TMP11:%.*]] = fpext float [[S]] to double
; CHECK-NEXT:    [[TMP12:%.*]] = select i1 [[TMP10]], double [[TMP11]], double [[TMP8]]
; CHECK-NEXT:    [[R:%.*]] = call float @fabsf(float [[S]]) #[[ATTR4]]
; CHECK-NEXT:    [[TMP13:%.*]] = call double @llvm.fabs.f64(double [[TMP8]])
; CHECK-NEXT:    [[TMP14:%.*]] = call i32 @__nsan_internal_check_float_d(float [[R]], double [[TMP13]], i32 1, i64 0)
; CHECK-NEXT:    [[TMP15:%.*]] = icmp eq i32 [[TMP14]], 1
; CHECK-NEXT:    [[TMP16:%.*]] = fpext float [[R]] to double
; CHECK-NEXT:    [[TMP17:%.*]] = select i1 [[TMP15]], double [[TMP16]], double [[TMP13]]
; CHECK-NEXT:    store i64 ptrtoint (ptr @sub_fabs to i64), ptr @__nsan_shadow_ret_tag, align 8
; CHECK-NEXT:    store double [[TMP17]], ptr @__nsan_shadow_ret_ptr, align 8
; CHECK-NEXT:    ret float [[R]]
;
entry:
  %s = fsub float %a, %b
  %r = call float @fabsf(float %s)
  ret float %r
}

; Note that the `unsafe-fp-math` from the function attributes should be moved to
; individual instructions, with the shadow instructions NOT getting the attribute.
define float @param_add_return_float_unsafe_fp_math(float %a) #0 {
; CHECK-LABEL: @param_add_return_float_unsafe_fp_math(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq i64 [[TMP0]], ptrtoint (ptr @param_add_return_float_unsafe_fp_math to i64)
; CHECK-NEXT:    [[TMP2:%.*]] = load double, ptr @__nsan_shadow_args_ptr, align 1
; CHECK-NEXT:    [[TMP3:%.*]] = fpext float [[A:%.*]] to double
; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP1]], double [[TMP2]], double [[TMP3]]
; CHECK-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[B:%.*]] = fadd fast float [[A]], 1.000000e+00
; CHECK-NEXT:    [[TMP5:%.*]] = fadd double [[TMP4]], 1.000000e+00
; CHECK-NEXT:    [[TMP6:%.*]] = call i32 @__nsan_internal_check_float_d(float [[B]], double [[TMP5]], i32 1, i64 0)
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[TMP6]], 1
; CHECK-NEXT:    [[TMP8:%.*]] = fpext float [[B]] to double
; CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[TMP7]], double [[TMP8]], double [[TMP5]]
; CHECK-NEXT:    store i64 ptrtoint (ptr @param_add_return_float_unsafe_fp_math to i64), ptr @__nsan_shadow_ret_tag, align 8
; CHECK-NEXT:    store double [[TMP9]], ptr @__nsan_shadow_ret_ptr, align 8
; CHECK-NEXT:    ret float [[B]]
;
entry:
  %b = fadd float %a, 1.0
  ret float %b
}


define void @truncate(<2 x double> %0) sanitize_numerical_stability {
; DQQ-LABEL: @truncate(
; DQQ-NEXT:  entry:
; DQQ-NEXT:    [[TMP1:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; DQQ-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[TMP1]], ptrtoint (ptr @truncate to i64)
; DQQ-NEXT:    [[TMP3:%.*]] = load <2 x fp128>, ptr @__nsan_shadow_args_ptr, align 1
; DQQ-NEXT:    [[TMP4:%.*]] = fpext <2 x double> [[TMP0:%.*]] to <2 x fp128>
; DQQ-NEXT:    [[TMP5:%.*]] = select i1 [[TMP2]], <2 x fp128> [[TMP3]], <2 x fp128> [[TMP4]]
; DQQ-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; DQQ-NEXT:    [[TMP6:%.*]] = fptrunc <2 x double> [[TMP0]] to <2 x float>
; DQQ-NEXT:    [[TMP7:%.*]] = fptrunc <2 x fp128> [[TMP5]] to <2 x double>
; DQQ-NEXT:    ret void
;
; DLQ-LABEL: @truncate(
; DLQ-NEXT:  entry:
; DLQ-NEXT:    [[TMP1:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; DLQ-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[TMP1]], ptrtoint (ptr @truncate to i64)
; DLQ-NEXT:    [[TMP3:%.*]] = load <2 x x86_fp80>, ptr @__nsan_shadow_args_ptr, align 1
; DLQ-NEXT:    [[TMP4:%.*]] = fpext <2 x double> [[TMP0:%.*]] to <2 x x86_fp80>
; DLQ-NEXT:    [[TMP5:%.*]] = select i1 [[TMP2]], <2 x x86_fp80> [[TMP3]], <2 x x86_fp80> [[TMP4]]
; DLQ-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; DLQ-NEXT:    [[TMP6:%.*]] = fptrunc <2 x double> [[TMP0]] to <2 x float>
; DLQ-NEXT:    [[TMP7:%.*]] = fptrunc <2 x x86_fp80> [[TMP5]] to <2 x double>
; DLQ-NEXT:    ret void
;
entry:
  %1 = fptrunc <2 x double> %0 to  <2 x float>
  ret void
}

define void @unaryop(float %a) sanitize_numerical_stability {
; CHECK-LABEL: @unaryop(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq i64 [[TMP0]], ptrtoint (ptr @unaryop to i64)
; CHECK-NEXT:    [[TMP2:%.*]] = load double, ptr @__nsan_shadow_args_ptr, align 1
; CHECK-NEXT:    [[TMP3:%.*]] = fpext float [[A:%.*]] to double
; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP1]], double [[TMP2]], double [[TMP3]]
; CHECK-NEXT:    store i64 0, ptr @__nsan_shadow_args_tag, align 8
; CHECK-NEXT:    [[C:%.*]] = fneg float [[A]]
; CHECK-NEXT:    [[TMP5:%.*]] = fneg double [[TMP4]]
; CHECK-NEXT:    ret void
;
entry:
  %c = fneg float %a
  ret void
}


attributes #0 = { nounwind readonly uwtable sanitize_numerical_stability "correctly-rounded-divide-sqrt-fp-math"="false" "denormal-fp-math"="preserve-sign,preserve-sign" "denormal-fp-math-f32"="ieee,ieee" "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-infs-fp-math"="true" "no-jump-tables"="false" "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="true" "use-soft-float"="false" }