shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/amdgpu-codegenprepare-fdiv.f64.ll
Matt Arsenault 2502e3b7ba
IR: Promote "denormal-fp-math" to a first class attribute (#174293) 
Convert "denormal-fp-math" and "denormal-fp-math-f32" into a first
class denormal_fpenv attribute. Previously the query for the effective
denormal mode involved two string attribute queries with parsing. I'm
introducing more uses of this, so it makes sense to convert this
to a more efficient encoding. The old representation was also awkward
since it was split across two separate attributes. The new encoding
just stores the default and float modes as bitfields, largely avoiding
the need to consider if the other mode is set.

The syntax in the common cases looks like this:
  `denormal_fpenv(preservesign,preservesign)`
  `denormal_fpenv(float: preservesign,preservesign)`
  `denormal_fpenv(dynamic,dynamic float: preservesign,preservesign)`

I wasn't sure about reusing the float type name instead of adding a
new keyword. It's parsed as a type but only accepts float. I'm also
debating switching the name to subnormal to match the current
preferred IEEE terminology (also used by nofpclass and other
contexts).

This has a behavior change when using the command flag debug
options to set the denormal mode. The behavior of the flag
ignored functions with an explicit attribute set, per
the default and f32 version. Now that these are one attribute,
the flag logic can't distinguish which of the two components
were explicitly set on the function. Only one test appeared to
rely on this behavior, so I just avoided using the flags in it.

This also does not perform all the code cleanups this enables.
In particular the attributor handling could be cleaned up.

I also guessed at how to support this in MLIR. I followed
MemoryEffects as a reference; it appears bitfields are expanded
into arguments to attributes, so the representation there is
a bit uglier with the 2 2-element fields flattened into 4 arguments.
2026-02-05 13:31:26 +00:00

777 lines
44 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-codegenprepare < %s | FileCheck %s
define double @rsq_f64(double %x) {
; CHECK-LABEL: define double @rsq_f64(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = call i1 @llvm.is.fpclass.f64(double [[X]], i32 608)
; CHECK-NEXT: [[TMP3:%.*]] = select contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul contract double [[TMP6]], [[TMP1]]
; CHECK-NEXT: [[TMP8:%.*]] = call contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @neg_rsq_f64(double %x) {
; CHECK-LABEL: define double @neg_rsq_f64(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = call i1 @llvm.is.fpclass.f64(double [[X]], i32 608)
; CHECK-NEXT: [[TMP3:%.*]] = select contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul contract double [[TMP6]], [[TMP4]]
; CHECK-NEXT: [[TMP8:%.*]] = call contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP4]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double -1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_nnan(double %x) {
; CHECK-LABEL: define double @rsq_f64_nnan(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = call i1 @llvm.is.fpclass.f64(double [[X]], i32 608)
; CHECK-NEXT: [[TMP3:%.*]] = select nnan contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg nnan contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul nnan contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call nnan contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul nnan contract double [[TMP6]], [[TMP1]]
; CHECK-NEXT: [[TMP8:%.*]] = call nnan contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call nnan contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract nnan double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract nnan double 1.0, %sqrt.x
ret double %fdiv
}
define double @neg_rsq_f64_nnan(double %x) {
; CHECK-LABEL: define double @neg_rsq_f64_nnan(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = call i1 @llvm.is.fpclass.f64(double [[X]], i32 608)
; CHECK-NEXT: [[TMP3:%.*]] = select nnan contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg nnan contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul nnan contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call nnan contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul nnan contract double [[TMP6]], [[TMP4]]
; CHECK-NEXT: [[TMP8:%.*]] = call nnan contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call nnan contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP4]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract nnan double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract nnan double -1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_ninf(double %x) {
; CHECK-LABEL: define double @rsq_f64_ninf(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call ninf contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fneg ninf contract double [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul ninf contract double [[X]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = call ninf contract double @llvm.fma.f64(double [[TMP3]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP5:%.*]] = fmul ninf contract double [[TMP4]], [[TMP1]]
; CHECK-NEXT: [[TMP6:%.*]] = call ninf contract double @llvm.fma.f64(double [[TMP4]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call ninf contract double @llvm.fma.f64(double [[TMP5]], double [[TMP6]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract ninf double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract ninf double 1.0, %sqrt.x
ret double %fdiv
}
define double @neg_rsq_f64_ninf(double %x) {
; CHECK-LABEL: define double @neg_rsq_f64_ninf(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call ninf contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fneg ninf contract double [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul ninf contract double [[X]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = call ninf contract double @llvm.fma.f64(double [[TMP3]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP5:%.*]] = fmul ninf contract double [[TMP4]], [[TMP2]]
; CHECK-NEXT: [[TMP6:%.*]] = call ninf contract double @llvm.fma.f64(double [[TMP4]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call ninf contract double @llvm.fma.f64(double [[TMP5]], double [[TMP6]], double [[TMP2]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract ninf double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract ninf double -1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_nnan_ninf(double %x) {
; CHECK-LABEL: define double @rsq_f64_nnan_ninf(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan ninf contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fneg nnan ninf contract double [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul nnan ninf contract double [[X]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP3]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP5:%.*]] = fmul nnan ninf contract double [[TMP4]], [[TMP1]]
; CHECK-NEXT: [[TMP6:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP4]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP5]], double [[TMP6]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract nnan ninf double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract nnan ninf double 1.0, %sqrt.x
ret double %fdiv
}
define double @neg_rsq_f64_nnan_ninf(double %x) {
; CHECK-LABEL: define double @neg_rsq_f64_nnan_ninf(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan ninf contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fneg nnan ninf contract double [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul nnan ninf contract double [[X]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP3]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP5:%.*]] = fmul nnan ninf contract double [[TMP4]], [[TMP2]]
; CHECK-NEXT: [[TMP6:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP4]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP5]], double [[TMP6]], double [[TMP2]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract nnan ninf double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract nnan ninf double -1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_sqrt_nnan_ninf(double %x) {
; CHECK-LABEL: define double @rsq_f64_sqrt_nnan_ninf(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan ninf contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fcmp nnan ninf contract oeq double [[X]], 0.000000e+00
; CHECK-NEXT: [[TMP3:%.*]] = select nnan ninf contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg nnan ninf contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul nnan ninf contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul nnan ninf contract double [[TMP6]], [[TMP1]]
; CHECK-NEXT: [[TMP8:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract nnan ninf double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_fdiv_nnan_ninf(double %x) {
; CHECK-LABEL: define double @rsq_f64_fdiv_nnan_ninf(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan ninf contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fneg nnan ninf contract double [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul nnan ninf contract double [[X]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP3]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP5:%.*]] = fmul nnan ninf contract double [[TMP4]], [[TMP1]]
; CHECK-NEXT: [[TMP6:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP4]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP5]], double [[TMP6]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract nnan ninf double 1.0, %sqrt.x
ret double %fdiv
}
define <2 x double> @rsq_v2f64(<2 x double> %x) {
; CHECK-LABEL: define <2 x double> @rsq_v2f64(
; CHECK-SAME: <2 x double> [[X:%.*]]) {
; CHECK-NEXT: [[SQRT_X:%.*]] = call contract <2 x double> @llvm.sqrt.v2f64(<2 x double> [[X]])
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <2 x double> [[SQRT_X]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[SQRT_X]], i64 1
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x double> [[X]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <2 x double> [[X]], i64 1
; CHECK-NEXT: [[TMP5:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[TMP3]])
; CHECK-NEXT: [[TMP6:%.*]] = call i1 @llvm.is.fpclass.f64(double [[TMP3]], i32 608)
; CHECK-NEXT: [[TMP7:%.*]] = select contract i1 [[TMP6]], double [[TMP5]], double [[TMP3]]
; CHECK-NEXT: [[TMP8:%.*]] = fneg contract double [[TMP5]]
; CHECK-NEXT: [[TMP9:%.*]] = fmul contract double [[TMP7]], [[TMP8]]
; CHECK-NEXT: [[TMP10:%.*]] = call contract double @llvm.fma.f64(double [[TMP9]], double [[TMP5]], double 1.000000e+00)
; CHECK-NEXT: [[TMP11:%.*]] = fmul contract double [[TMP10]], [[TMP5]]
; CHECK-NEXT: [[TMP12:%.*]] = call contract double @llvm.fma.f64(double [[TMP10]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[TMP13:%.*]] = call contract double @llvm.fma.f64(double [[TMP11]], double [[TMP12]], double [[TMP5]])
; CHECK-NEXT: [[TMP14:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[TMP4]])
; CHECK-NEXT: [[TMP15:%.*]] = call i1 @llvm.is.fpclass.f64(double [[TMP4]], i32 608)
; CHECK-NEXT: [[TMP16:%.*]] = select contract i1 [[TMP15]], double [[TMP14]], double [[TMP4]]
; CHECK-NEXT: [[TMP17:%.*]] = fneg contract double [[TMP14]]
; CHECK-NEXT: [[TMP18:%.*]] = fmul contract double [[TMP16]], [[TMP17]]
; CHECK-NEXT: [[TMP19:%.*]] = call contract double @llvm.fma.f64(double [[TMP18]], double [[TMP14]], double 1.000000e+00)
; CHECK-NEXT: [[TMP20:%.*]] = fmul contract double [[TMP19]], [[TMP14]]
; CHECK-NEXT: [[TMP21:%.*]] = call contract double @llvm.fma.f64(double [[TMP19]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[TMP22:%.*]] = call contract double @llvm.fma.f64(double [[TMP20]], double [[TMP21]], double [[TMP14]])
; CHECK-NEXT: [[TMP23:%.*]] = insertelement <2 x double> poison, double [[TMP13]], i64 0
; CHECK-NEXT: [[FDIV:%.*]] = insertelement <2 x double> [[TMP23]], double [[TMP22]], i64 1
; CHECK-NEXT: ret <2 x double> [[FDIV]]
;
%sqrt.x = call contract <2 x double> @llvm.sqrt.f64(<2 x double> %x)
%fdiv = fdiv contract <2 x double> splat (double 1.0), %sqrt.x
ret <2 x double> %fdiv
}
define <2 x double> @neg_rsq_v2f64(<2 x double> %x) {
; CHECK-LABEL: define <2 x double> @neg_rsq_v2f64(
; CHECK-SAME: <2 x double> [[X:%.*]]) {
; CHECK-NEXT: [[SQRT_X:%.*]] = call contract <2 x double> @llvm.sqrt.v2f64(<2 x double> [[X]])
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <2 x double> [[SQRT_X]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[SQRT_X]], i64 1
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x double> [[X]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <2 x double> [[X]], i64 1
; CHECK-NEXT: [[TMP5:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[TMP3]])
; CHECK-NEXT: [[TMP6:%.*]] = call i1 @llvm.is.fpclass.f64(double [[TMP3]], i32 608)
; CHECK-NEXT: [[TMP7:%.*]] = select contract i1 [[TMP6]], double [[TMP5]], double [[TMP3]]
; CHECK-NEXT: [[TMP8:%.*]] = fneg contract double [[TMP5]]
; CHECK-NEXT: [[TMP9:%.*]] = fmul contract double [[TMP7]], [[TMP8]]
; CHECK-NEXT: [[TMP10:%.*]] = call contract double @llvm.fma.f64(double [[TMP9]], double [[TMP5]], double 1.000000e+00)
; CHECK-NEXT: [[TMP11:%.*]] = fmul contract double [[TMP10]], [[TMP5]]
; CHECK-NEXT: [[TMP12:%.*]] = call contract double @llvm.fma.f64(double [[TMP10]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[TMP13:%.*]] = call contract double @llvm.fma.f64(double [[TMP11]], double [[TMP12]], double [[TMP5]])
; CHECK-NEXT: [[TMP14:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[TMP4]])
; CHECK-NEXT: [[TMP15:%.*]] = call i1 @llvm.is.fpclass.f64(double [[TMP4]], i32 608)
; CHECK-NEXT: [[TMP16:%.*]] = select contract i1 [[TMP15]], double [[TMP14]], double [[TMP4]]
; CHECK-NEXT: [[TMP17:%.*]] = fneg contract double [[TMP14]]
; CHECK-NEXT: [[TMP18:%.*]] = fmul contract double [[TMP16]], [[TMP17]]
; CHECK-NEXT: [[TMP19:%.*]] = call contract double @llvm.fma.f64(double [[TMP18]], double [[TMP14]], double 1.000000e+00)
; CHECK-NEXT: [[TMP20:%.*]] = fmul contract double [[TMP19]], [[TMP14]]
; CHECK-NEXT: [[TMP21:%.*]] = call contract double @llvm.fma.f64(double [[TMP19]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[TMP22:%.*]] = call contract double @llvm.fma.f64(double [[TMP20]], double [[TMP21]], double [[TMP14]])
; CHECK-NEXT: [[TMP23:%.*]] = insertelement <2 x double> poison, double [[TMP13]], i64 0
; CHECK-NEXT: [[FDIV:%.*]] = insertelement <2 x double> [[TMP23]], double [[TMP22]], i64 1
; CHECK-NEXT: ret <2 x double> [[FDIV]]
;
%sqrt.x = call contract <2 x double> @llvm.sqrt.f64(<2 x double> %x)
%fdiv = fdiv contract <2 x double> splat (double 1.0), %sqrt.x
ret <2 x double> %fdiv
}
define <2 x double> @mixed_sign_rsq_v2f64(<2 x double> %x) {
; CHECK-LABEL: define <2 x double> @mixed_sign_rsq_v2f64(
; CHECK-SAME: <2 x double> [[X:%.*]]) {
; CHECK-NEXT: [[SQRT_X:%.*]] = call contract <2 x double> @llvm.sqrt.v2f64(<2 x double> [[X]])
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <2 x double> [[SQRT_X]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[SQRT_X]], i64 1
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x double> [[X]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <2 x double> [[X]], i64 1
; CHECK-NEXT: [[TMP5:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[TMP3]])
; CHECK-NEXT: [[TMP6:%.*]] = call i1 @llvm.is.fpclass.f64(double [[TMP3]], i32 608)
; CHECK-NEXT: [[TMP7:%.*]] = select contract i1 [[TMP6]], double [[TMP5]], double [[TMP3]]
; CHECK-NEXT: [[TMP8:%.*]] = fneg contract double [[TMP5]]
; CHECK-NEXT: [[TMP9:%.*]] = fmul contract double [[TMP7]], [[TMP8]]
; CHECK-NEXT: [[TMP10:%.*]] = call contract double @llvm.fma.f64(double [[TMP9]], double [[TMP5]], double 1.000000e+00)
; CHECK-NEXT: [[TMP11:%.*]] = fmul contract double [[TMP10]], [[TMP5]]
; CHECK-NEXT: [[TMP12:%.*]] = call contract double @llvm.fma.f64(double [[TMP10]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[TMP13:%.*]] = call contract double @llvm.fma.f64(double [[TMP11]], double [[TMP12]], double [[TMP5]])
; CHECK-NEXT: [[TMP14:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[TMP4]])
; CHECK-NEXT: [[TMP15:%.*]] = call i1 @llvm.is.fpclass.f64(double [[TMP4]], i32 608)
; CHECK-NEXT: [[TMP16:%.*]] = select contract i1 [[TMP15]], double [[TMP14]], double [[TMP4]]
; CHECK-NEXT: [[TMP17:%.*]] = fneg contract double [[TMP14]]
; CHECK-NEXT: [[TMP18:%.*]] = fmul contract double [[TMP16]], [[TMP17]]
; CHECK-NEXT: [[TMP19:%.*]] = call contract double @llvm.fma.f64(double [[TMP18]], double [[TMP14]], double 1.000000e+00)
; CHECK-NEXT: [[TMP20:%.*]] = fmul contract double [[TMP19]], [[TMP17]]
; CHECK-NEXT: [[TMP21:%.*]] = call contract double @llvm.fma.f64(double [[TMP19]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[TMP23:%.*]] = call contract double @llvm.fma.f64(double [[TMP20]], double [[TMP21]], double [[TMP17]])
; CHECK-NEXT: [[TMP24:%.*]] = insertelement <2 x double> poison, double [[TMP13]], i64 0
; CHECK-NEXT: [[FDIV:%.*]] = insertelement <2 x double> [[TMP24]], double [[TMP23]], i64 1
; CHECK-NEXT: ret <2 x double> [[FDIV]]
;
%sqrt.x = call contract <2 x double> @llvm.sqrt.f64(<2 x double> %x)
%fdiv = fdiv contract <2 x double> <double 1.0, double -1.0>, %sqrt.x
ret <2 x double> %fdiv
}
define <2 x double> @rsq_some_elements_v2f64(<2 x double> %x) {
; CHECK-LABEL: define <2 x double> @rsq_some_elements_v2f64(
; CHECK-SAME: <2 x double> [[X:%.*]]) {
; CHECK-NEXT: [[SQRT_X:%.*]] = call contract <2 x double> @llvm.sqrt.v2f64(<2 x double> [[X]])
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <2 x double> [[SQRT_X]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[SQRT_X]], i64 1
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x double> [[X]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <2 x double> [[X]], i64 1
; CHECK-NEXT: [[TMP5:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[TMP3]])
; CHECK-NEXT: [[TMP6:%.*]] = call i1 @llvm.is.fpclass.f64(double [[TMP3]], i32 608)
; CHECK-NEXT: [[TMP7:%.*]] = select contract i1 [[TMP6]], double [[TMP5]], double [[TMP3]]
; CHECK-NEXT: [[TMP8:%.*]] = fneg contract double [[TMP5]]
; CHECK-NEXT: [[TMP9:%.*]] = fmul contract double [[TMP7]], [[TMP8]]
; CHECK-NEXT: [[TMP10:%.*]] = call contract double @llvm.fma.f64(double [[TMP9]], double [[TMP5]], double 1.000000e+00)
; CHECK-NEXT: [[TMP11:%.*]] = fmul contract double [[TMP10]], [[TMP5]]
; CHECK-NEXT: [[TMP12:%.*]] = call contract double @llvm.fma.f64(double [[TMP10]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[TMP13:%.*]] = call contract double @llvm.fma.f64(double [[TMP11]], double [[TMP12]], double [[TMP5]])
; CHECK-NEXT: [[TMP14:%.*]] = fdiv contract double 2.000000e+00, [[TMP2]]
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <2 x double> poison, double [[TMP13]], i64 0
; CHECK-NEXT: [[FDIV:%.*]] = insertelement <2 x double> [[TMP15]], double [[TMP14]], i64 1
; CHECK-NEXT: ret <2 x double> [[FDIV]]
;
%sqrt.x = call contract <2 x double> @llvm.sqrt.f64(<2 x double> %x)
%fdiv = fdiv contract <2 x double> <double 1.0, double 2.0>, %sqrt.x
ret <2 x double> %fdiv
}
; Negative test
define double @rsq_f64_missing_contract0(double %x) {
; CHECK-LABEL: define double @rsq_f64_missing_contract0(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[SQRT_X:%.*]] = call double @llvm.sqrt.f64(double [[X]])
; CHECK-NEXT: [[FDIV:%.*]] = fdiv contract double 1.000000e+00, [[SQRT_X]]
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
; Negative test
define double @rsq_f64_missing_contract1(double %x) {
; CHECK-LABEL: define double @rsq_f64_missing_contract1(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[SQRT_X:%.*]] = call contract double @llvm.sqrt.f64(double [[X]])
; CHECK-NEXT: [[FDIV:%.*]] = fdiv double 1.000000e+00, [[SQRT_X]]
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv double 1.0, %sqrt.x
ret double %fdiv
}
declare double @sqrt(double)
define double @rsq_f64_not_sqrt_intrin(double %x) {
; CHECK-LABEL: define double @rsq_f64_not_sqrt_intrin(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[SQRT_X:%.*]] = call contract double @sqrt(double [[X]])
; CHECK-NEXT: [[FDIV:%.*]] = fdiv contract double 1.000000e+00, [[SQRT_X]]
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @sqrt(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @rcp_f64(double %x) {
; CHECK-LABEL: define double @rcp_f64(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[FDIV:%.*]] = fdiv arcp contract double 1.000000e+00, [[X]]
; CHECK-NEXT: ret double [[FDIV]]
;
%fdiv = fdiv contract arcp double 1.0, %x
ret double %fdiv
}
define double @rcp_afn_f64(double %x) {
; CHECK-LABEL: define double @rcp_afn_f64(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[FDIV:%.*]] = fdiv arcp contract afn double 1.000000e+00, [[X]]
; CHECK-NEXT: ret double [[FDIV]]
;
%fdiv = fdiv contract arcp afn double 1.0, %x
ret double %fdiv
}
define double @neg_rcp_f64(double %x) {
; CHECK-LABEL: define double @neg_rcp_f64(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[FDIV:%.*]] = fdiv arcp contract double -1.000000e+00, [[X]]
; CHECK-NEXT: ret double [[FDIV]]
;
%fdiv = fdiv contract arcp double -1.0, %x
ret double %fdiv
}
define double @neg_rcp_afn_f64(double %x) {
; CHECK-LABEL: define double @neg_rcp_afn_f64(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[FDIV:%.*]] = fdiv arcp contract afn double -1.000000e+00, [[X]]
; CHECK-NEXT: ret double [[FDIV]]
;
%fdiv = fdiv contract arcp afn double -1.0, %x
ret double %fdiv
}
; Make sure this doesn't accidentally go down f32 paths
define double @v_fdiv_f64_ulp25(double %a, double %b) {
; CHECK-LABEL: define double @v_fdiv_f64_ulp25(
; CHECK-SAME: double [[A:%.*]], double [[B:%.*]]) {
; CHECK-NEXT: [[FDIV:%.*]] = fdiv double [[A]], [[B]], !fpmath [[META0:![0-9]+]]
; CHECK-NEXT: ret double [[FDIV]]
;
%fdiv = fdiv double %a, %b, !fpmath !0
ret double %fdiv
}
; TODO: Handle arcp case
define double @fdiv_arcp_2_f64(double %x) {
; CHECK-LABEL: define double @fdiv_arcp_2_f64(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[SQRT_X:%.*]] = call arcp contract double @llvm.sqrt.f64(double [[X]])
; CHECK-NEXT: [[FDIV:%.*]] = fdiv arcp contract double 2.000000e+00, [[SQRT_X]]
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call arcp contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv arcp contract double 2.0, %sqrt.x
ret double %fdiv
}
define double @fdiv_arcp_var_f64(double %x, double %y) {
; CHECK-LABEL: define double @fdiv_arcp_var_f64(
; CHECK-SAME: double [[X:%.*]], double [[Y:%.*]]) {
; CHECK-NEXT: [[SQRT_X:%.*]] = call arcp contract double @llvm.sqrt.f64(double [[X]])
; CHECK-NEXT: [[FDIV:%.*]] = fdiv arcp contract double [[Y]], [[SQRT_X]]
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call arcp contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv arcp contract double %y, %sqrt.x
ret double %fdiv
}
define double @rsq_amdgcn_f64(double %x) {
; CHECK-LABEL: define double @rsq_amdgcn_f64(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[SQRT_X:%.*]] = call contract double @llvm.amdgcn.sqrt.f64(double [[X]])
; CHECK-NEXT: [[FDIV:%.*]] = fdiv contract double 1.000000e+00, [[SQRT_X]]
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.amdgcn.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @neg_rsq_amdgcn_f64(double %x) {
; CHECK-LABEL: define double @neg_rsq_amdgcn_f64(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[SQRT_X:%.*]] = call contract double @llvm.amdgcn.sqrt.f64(double [[X]])
; CHECK-NEXT: [[FDIV:%.*]] = fdiv contract double -1.000000e+00, [[SQRT_X]]
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.amdgcn.sqrt.f64(double %x)
%fdiv = fdiv contract double -1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_amdgcn_f64_nnan_ninf(double %x) {
; CHECK-LABEL: define double @rsq_amdgcn_f64_nnan_ninf(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[SQRT_X:%.*]] = call nnan ninf contract double @llvm.amdgcn.sqrt.f64(double [[X]])
; CHECK-NEXT: [[FDIV:%.*]] = fdiv nnan ninf contract double 1.000000e+00, [[SQRT_X]]
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract nnan ninf double @llvm.amdgcn.sqrt.f64(double %x)
%fdiv = fdiv contract nnan ninf double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_input_known_not_zero(double nofpclass(zero) %x) {
; CHECK-LABEL: define double @rsq_f64_input_known_not_zero(
; CHECK-SAME: double nofpclass(zero) [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fcmp contract oeq double [[X]], 0x7FF0000000000000
; CHECK-NEXT: [[TMP3:%.*]] = select contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul contract double [[TMP6]], [[TMP1]]
; CHECK-NEXT: [[TMP8:%.*]] = call contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_input_known_not_pinf(double nofpclass(pinf) %x) {
; CHECK-LABEL: define double @rsq_f64_input_known_not_pinf(
; CHECK-SAME: double nofpclass(pinf) [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fcmp contract oeq double [[X]], 0.000000e+00
; CHECK-NEXT: [[TMP3:%.*]] = select contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul contract double [[TMP6]], [[TMP1]]
; CHECK-NEXT: [[TMP8:%.*]] = call contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_input_known_not_pinf_zero(double nofpclass(pinf zero) %x) {
; CHECK-LABEL: define double @rsq_f64_input_known_not_pinf_zero(
; CHECK-SAME: double nofpclass(pinf zero) [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fneg contract double [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul contract double [[X]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = call contract double @llvm.fma.f64(double [[TMP3]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP5:%.*]] = fmul contract double [[TMP4]], [[TMP1]]
; CHECK-NEXT: [[TMP6:%.*]] = call contract double @llvm.fma.f64(double [[TMP4]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call contract double @llvm.fma.f64(double [[TMP5]], double [[TMP6]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_input_known_not_pinf_zero_dynamic_fp(double nofpclass(pinf zero) %x) #0 {
; CHECK-LABEL: define double @rsq_f64_input_known_not_pinf_zero_dynamic_fp(
; CHECK-SAME: double nofpclass(pinf zero) [[X:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: [[TMP1:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fcmp contract oeq double [[X]], 0.000000e+00
; CHECK-NEXT: [[TMP3:%.*]] = select contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul contract double [[TMP6]], [[TMP1]]
; CHECK-NEXT: [[TMP8:%.*]] = call contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_input_known_not_pinf_zero_daz(double nofpclass(pinf zero) %x) #1 {
; CHECK-LABEL: define double @rsq_f64_input_known_not_pinf_zero_daz(
; CHECK-SAME: double nofpclass(pinf zero) [[X:%.*]]) #[[ATTR1:[0-9]+]] {
; CHECK-NEXT: [[TMP1:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fcmp contract oeq double [[X]], 0.000000e+00
; CHECK-NEXT: [[TMP3:%.*]] = select contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul contract double [[TMP6]], [[TMP1]]
; CHECK-NEXT: [[TMP8:%.*]] = call contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_input_known_not_pinf_zero_denorm_daz(double nofpclass(pinf zero sub) %x) #1 {
; CHECK-LABEL: define double @rsq_f64_input_known_not_pinf_zero_denorm_daz(
; CHECK-SAME: double nofpclass(pinf zero sub) [[X:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fneg contract double [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul contract double [[X]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = call contract double @llvm.fma.f64(double [[TMP3]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP5:%.*]] = fmul contract double [[TMP4]], [[TMP1]]
; CHECK-NEXT: [[TMP6:%.*]] = call contract double @llvm.fma.f64(double [[TMP4]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call contract double @llvm.fma.f64(double [[TMP5]], double [[TMP6]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_dynamic_denormal(double %x) #0 {
; CHECK-LABEL: define double @rsq_f64_dynamic_denormal(
; CHECK-SAME: double [[X:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fcmp contract oeq double [[X]], 0.000000e+00
; CHECK-NEXT: [[TMP3:%.*]] = fcmp contract oeq double [[X]], 0x7FF0000000000000
; CHECK-NEXT: [[TMP4:%.*]] = or i1 [[TMP2]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = select contract i1 [[TMP4]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP6:%.*]] = fneg contract double [[TMP1]]
; CHECK-NEXT: [[TMP7:%.*]] = fmul contract double [[TMP5]], [[TMP6]]
; CHECK-NEXT: [[TMP8:%.*]] = call contract double @llvm.fma.f64(double [[TMP7]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP9:%.*]] = fmul contract double [[TMP8]], [[TMP1]]
; CHECK-NEXT: [[TMP10:%.*]] = call contract double @llvm.fma.f64(double [[TMP8]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call contract double @llvm.fma.f64(double [[TMP9]], double [[TMP10]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_dynamic_denormal_no_pinf(double nofpclass(pinf) %x) #0 {
; CHECK-LABEL: define double @rsq_f64_dynamic_denormal_no_pinf(
; CHECK-SAME: double nofpclass(pinf) [[X:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fcmp contract oeq double [[X]], 0.000000e+00
; CHECK-NEXT: [[TMP3:%.*]] = select contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul contract double [[TMP6]], [[TMP1]]
; CHECK-NEXT: [[TMP8:%.*]] = call contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_dynamic_denormal_no_zero_no_denorm(double nofpclass(zero sub) %x) #0 {
; CHECK-LABEL: define double @rsq_f64_dynamic_denormal_no_zero_no_denorm(
; CHECK-SAME: double nofpclass(zero sub) [[X:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fcmp contract oeq double [[X]], 0x7FF0000000000000
; CHECK-NEXT: [[TMP3:%.*]] = select contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul contract double [[TMP6]], [[TMP1]]
; CHECK-NEXT: [[TMP8:%.*]] = call contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_nnan_sqrt(double %x) {
; CHECK-LABEL: define double @rsq_f64_nnan_sqrt(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = call i1 @llvm.is.fpclass.f64(double [[X]], i32 608)
; CHECK-NEXT: [[TMP3:%.*]] = select nnan contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg nnan contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul nnan contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call nnan contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul nnan contract double [[TMP6]], [[TMP1]]
; CHECK-NEXT: [[TMP8:%.*]] = call nnan contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call nnan contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract nnan double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_nnan_fdiv(double %x) {
; CHECK-LABEL: define double @rsq_f64_nnan_fdiv(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = call i1 @llvm.is.fpclass.f64(double [[X]], i32 608)
; CHECK-NEXT: [[TMP3:%.*]] = select nnan contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg nnan contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul nnan contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call nnan contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul nnan contract double [[TMP6]], [[TMP1]]
; CHECK-NEXT: [[TMP8:%.*]] = call nnan contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call nnan contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract nnan double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_ninf_sqrt(double %x) {
; CHECK-LABEL: define double @rsq_f64_ninf_sqrt(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call ninf contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fcmp ninf contract oeq double [[X]], 0.000000e+00
; CHECK-NEXT: [[TMP3:%.*]] = select ninf contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg ninf contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul ninf contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call ninf contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul ninf contract double [[TMP6]], [[TMP1]]
; CHECK-NEXT: [[TMP8:%.*]] = call ninf contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call ninf contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract ninf double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_ninf_fdiv(double %x) {
; CHECK-LABEL: define double @rsq_f64_ninf_fdiv(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call ninf contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fneg ninf contract double [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul ninf contract double [[X]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = call ninf contract double @llvm.fma.f64(double [[TMP3]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP5:%.*]] = fmul ninf contract double [[TMP4]], [[TMP1]]
; CHECK-NEXT: [[TMP6:%.*]] = call ninf contract double @llvm.fma.f64(double [[TMP4]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call ninf contract double @llvm.fma.f64(double [[TMP5]], double [[TMP6]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract ninf double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_ninf_sqrt_nnan_fdiv(double %x) {
; CHECK-LABEL: define double @rsq_f64_ninf_sqrt_nnan_fdiv(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan ninf contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP7:%.*]] = fcmp nnan ninf contract oeq double [[X]], 0.000000e+00
; CHECK-NEXT: [[TMP8:%.*]] = select nnan ninf contract i1 [[TMP7]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP2:%.*]] = fneg nnan ninf contract double [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul nnan ninf contract double [[TMP8]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP3]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP5:%.*]] = fmul nnan ninf contract double [[TMP4]], [[TMP1]]
; CHECK-NEXT: [[TMP6:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP4]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP5]], double [[TMP6]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract ninf double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract nnan double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_nann_sqrt_ninf_fdiv(double %x) {
; CHECK-LABEL: define double @rsq_f64_nann_sqrt_ninf_fdiv(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan ninf contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fneg nnan ninf contract double [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul nnan ninf contract double [[X]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP3]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP5:%.*]] = fmul nnan ninf contract double [[TMP4]], [[TMP1]]
; CHECK-NEXT: [[TMP6:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP4]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call nnan ninf contract double @llvm.fma.f64(double [[TMP5]], double [[TMP6]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%sqrt.x = call contract nnan double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract ninf double 1.0, %sqrt.x
ret double %fdiv
}
define double @rsq_f64_assume_nonzero(double %x) {
; CHECK-LABEL: define double @rsq_f64_assume_nonzero(
; CHECK-SAME: double [[X:%.*]]) {
; CHECK-NEXT: [[NONZERO:%.*]] = fcmp one double [[X]], 0.000000e+00
; CHECK-NEXT: call void @llvm.assume(i1 [[NONZERO]])
; CHECK-NEXT: [[TMP1:%.*]] = call contract double @llvm.amdgcn.rsq.f64(double [[X]])
; CHECK-NEXT: [[TMP2:%.*]] = fcmp contract oeq double [[X]], 0x7FF0000000000000
; CHECK-NEXT: [[TMP3:%.*]] = select contract i1 [[TMP2]], double [[TMP1]], double [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = fneg contract double [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul contract double [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call contract double @llvm.fma.f64(double [[TMP5]], double [[TMP1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP7:%.*]] = fmul contract double [[TMP6]], [[TMP1]]
; CHECK-NEXT: [[TMP8:%.*]] = call contract double @llvm.fma.f64(double [[TMP6]], double 3.750000e-01, double 5.000000e-01)
; CHECK-NEXT: [[FDIV:%.*]] = call contract double @llvm.fma.f64(double [[TMP7]], double [[TMP8]], double [[TMP1]])
; CHECK-NEXT: ret double [[FDIV]]
;
%nonzero = fcmp one double %x, 0.0
call void @llvm.assume(i1 %nonzero)
%sqrt.x = call contract double @llvm.sqrt.f64(double %x)
%fdiv = fdiv contract double 1.0, %sqrt.x
ret double %fdiv
}
attributes #0 = { denormal_fpenv(ieee|dynamic) }
attributes #1 = { denormal_fpenv(ieee|preservesign) }
!0 = !{float 2.500000e+00}
;.
; CHECK: [[META0]] = !{float 2.500000e+00}
;.
Reference in New Issue View Git Blame Copy Permalink