060df78cdb
Completes #83626 - `CGBuiltin.cpp` - modify `getDotProductIntrinsic` to be able to emit `dot2`, `dot3`, and `dot4` intrinsics based on element count - `IntrinsicsDirectX.td` - for floating point add `dot2`, `dot3`, and `dot4` inntrinsics -`DXIL.td` add dxilop intrinsic lowering for `dot2`, `dot3`, & `dot4`. - `DXILOpLowering.cpp` - add vector arg flattening for dot product. - `DXILOpBuilder.h` - modify `createDXILOpCall` to take a smallVector instead of an iterator - `DXILOpBuilder.cpp` - modify `createDXILOpCall` by moving the small vector up to the calling function in `DXILOpLowering.cpp`. - Moving one function up gives us access to the `CallInst` and `Function` which were needed to distinguish the dot product intrinsics and get the operands without using the iterator.
11 lines
351 B
LLVM
11 lines
351 B
LLVM
; RUN: not opt -S -dxil-op-lower %s 2>&1 | FileCheck %s
|
|
|
|
; DXIL operation dot2 does not support double overload type
|
|
; CHECK: LLVM ERROR: Invalid Overload
|
|
|
|
define noundef double @dot_double2(<2 x double> noundef %a, <2 x double> noundef %b) {
|
|
entry:
|
|
%dx.dot = call double @llvm.dx.dot2.v2f64(<2 x double> %a, <2 x double> %b)
|
|
ret double %dx.dot
|
|
}
|