-
Notifications
You must be signed in to change notification settings - Fork 11.8k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[DirectX] Add atan2 intrinsic and expand for DXIL backend
This change is part of this proposal: https://discourse.llvm.org/t/rfc-all-the-math-intrinsics/78294 This preliminary work adds the intrinsic to llvm and expands using atan intrinsic for DXIL backend, since DXIL has no atan2 op.
- Loading branch information
Showing
5 changed files
with
147 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,52 @@ | ||
; RUN: opt -S -dxil-op-lower -mtriple=dxil-pc-shadermodel6.3-library %s | FileCheck %s | ||
|
||
; Make sure correct dxil expansions for atan2 are generated for float and half. | ||
|
||
define noundef float @atan2_float(float noundef %y, float noundef %x) { | ||
entry: | ||
; CHECK: [[DIV:%.+]] = fdiv float %y, %x | ||
; CHECK: [[TAN:%.+]] = call float @dx.op.unary.f32(i32 17, float [[DIV]]) | ||
; CHECK-DAG: [[ADD_PI:%.+]] = fadd float [[TAN]], 0x400921FB60000000 | ||
; CHECK-DAG: [[SUB_PI:%.+]] = fsub float [[TAN]], 0x400921FB60000000 | ||
; CHECK-DAG: [[X_LT_0:%.+]] = fcmp olt float %x, 0.000000e+00 | ||
; CHECK-DAG: [[X_EQ_0:%.+]] = fcmp oeq float %x, 0.000000e+00 | ||
; CHECK-DAG: [[Y_GE_0:%.+]] = fcmp oge float %y, 0.000000e+00 | ||
; CHECK-DAG: [[Y_LT_0:%.+]] = fcmp olt float %y, 0.000000e+00 | ||
; CHECK: [[XLT0_AND_YGE0:%.+]] = and i1 [[X_LT_0]], [[Y_GE_0]] | ||
; CHECK: [[SELECT_ADD_PI:%.+]] = select i1 [[XLT0_AND_YGE0]], float [[ADD_PI]], float [[TAN]] | ||
; CHECK: [[XLT0_AND_YLT0:%.+]] = and i1 [[X_LT_0]], [[Y_LT_0]] | ||
; CHECK: [[SELECT_SUB_PI:%.+]] = select i1 [[XLT0_AND_YLT0]], float [[SUB_PI]], float [[SELECT_ADD_PI]] | ||
; CHECK: [[XEQ0_AND_YLT0:%.+]] = and i1 [[X_EQ_0]], [[Y_LT_0]] | ||
; CHECK: [[SELECT_NEGHPI:%.+]] = select i1 [[XEQ0_AND_YLT0]], float 0xBFF921FB60000000, float [[SELECT_SUB_PI]] | ||
; CHECK: [[XEQ0_AND_YGE0:%.+]] = and i1 [[X_EQ_0]], [[Y_GE_0]] | ||
; CHECK: [[SELECT_HPI:%.+]] = select i1 [[XEQ0_AND_YGE0]], float 0x3FF921FB60000000, float [[SELECT_NEGHPI]] | ||
; CHECK: ret float [[SELECT_HPI]] | ||
%elt.atan2 = call float @llvm.atan2.f32(float %y, float %x) | ||
ret float %elt.atan2 | ||
} | ||
|
||
define noundef half @atan2_half(half noundef %y, half noundef %x) { | ||
entry: | ||
; CHECK: [[DIV:%.+]] = fdiv half %y, %x | ||
; CHECK: [[TAN:%.+]] = call half @dx.op.unary.f16(i32 17, half [[DIV]]) | ||
; CHECK-DAG: [[ADD_PI:%.+]] = fadd half [[TAN]], 0xH4248 | ||
; CHECK-DAG: [[SUB_PI:%.+]] = fsub half [[TAN]], 0xH4248 | ||
; CHECK-DAG: [[X_LT_0:%.+]] = fcmp olt half %x, 0xH0000 | ||
; CHECK-DAG: [[X_EQ_0:%.+]] = fcmp oeq half %x, 0xH0000 | ||
; CHECK-DAG: [[Y_GE_0:%.+]] = fcmp oge half %y, 0xH0000 | ||
; CHECK-DAG: [[Y_LT_0:%.+]] = fcmp olt half %y, 0xH0000 | ||
; CHECK: [[XLT0_AND_YGE0:%.+]] = and i1 [[X_LT_0]], [[Y_GE_0]] | ||
; CHECK: [[SELECT_ADD_PI:%.+]] = select i1 [[XLT0_AND_YGE0]], half [[ADD_PI]], half [[TAN]] | ||
; CHECK: [[XLT0_AND_YLT0:%.+]] = and i1 [[X_LT_0]], [[Y_LT_0]] | ||
; CHECK: [[SELECT_SUB_PI:%.+]] = select i1 [[XLT0_AND_YLT0]], half [[SUB_PI]], half [[SELECT_ADD_PI]] | ||
; CHECK: [[XEQ0_AND_YLT0:%.+]] = and i1 [[X_EQ_0]], [[Y_LT_0]] | ||
; CHECK: [[SELECT_NEGHPI:%.+]] = select i1 [[XEQ0_AND_YLT0]], half 0xHBE48, half [[SELECT_SUB_PI]] | ||
; CHECK: [[XEQ0_AND_YGE0:%.+]] = and i1 [[X_EQ_0]], [[Y_GE_0]] | ||
; CHECK: [[SELECT_HPI:%.+]] = select i1 [[XEQ0_AND_YGE0]], half 0xH3E48, half [[SELECT_NEGHPI]] | ||
; CHECK: ret half [[SELECT_HPI]] | ||
%elt.atan2 = call half @llvm.atan2.f16(half %y, half %x) | ||
ret half %elt.atan2 | ||
} | ||
|
||
declare half @llvm.atan2.f16(half, half) | ||
declare float @llvm.atan2.f32(float, float) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,11 @@ | ||
; RUN: not opt -S -dxil-op-lower -mtriple=dxil-pc-shadermodel6.3-library %s 2>&1 | FileCheck %s | ||
|
||
; DXIL operation atan does not support double overload type | ||
; CHECK: in function atan2_double | ||
; CHECK-SAME: Cannot create ATan operation: Invalid overload type | ||
|
||
define noundef double @atan2_double(double noundef %a, double noundef %b) #0 { | ||
entry: | ||
%1 = call double @llvm.atan2.f64(double %a, double %b) | ||
ret double %1 | ||
} |