0f1b5f115a
ptxas is a proprietary compiler from Nvidia that can compile PTX to machine code (SASS). It has a lot of diagnostics to catch errors in PTX, which can be used to verify PTX output from llc. Set -DPXTAS_EXECUTABLE=/path/to/ptxas CMake option to enable it. If this option is not set, then ptxas is substituted to true which effectively disables all ptxas RUN lines. LLVM_PTXAS_EXECUTABLE environment variable takes precedence over the CMake option, and allows to override ptxas executable that is used for LIT without complete re-configuration. Differential Revision: https://reviews.llvm.org/D121727
47 lines
1.9 KiB
LLVM
47 lines
1.9 KiB
LLVM
; RUN: llc -march=nvptx -verify-machineinstrs < %s | FileCheck %s
|
|
; RUN: %if ptxas %{ llc -march=nvptx -verify-machineinstrs < %s | %ptxas-verify %}
|
|
|
|
declare float @llvm.convert.from.fp16.f32(i16) nounwind readnone
|
|
declare double @llvm.convert.from.fp16.f64(i16) nounwind readnone
|
|
declare i16 @llvm.convert.to.fp16.f32(float) nounwind readnone
|
|
declare i16 @llvm.convert.to.fp16.f64(double) nounwind readnone
|
|
|
|
; CHECK-LABEL: @test_convert_fp16_to_fp32
|
|
; CHECK: cvt.f32.f16
|
|
define void @test_convert_fp16_to_fp32(float addrspace(1)* noalias %out, i16 addrspace(1)* noalias %in) nounwind {
|
|
%val = load i16, i16 addrspace(1)* %in, align 2
|
|
%cvt = call float @llvm.convert.from.fp16.f32(i16 %val) nounwind readnone
|
|
store float %cvt, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
|
|
; CHECK-LABEL: @test_convert_fp16_to_fp64
|
|
; CHECK: cvt.f64.f16
|
|
define void @test_convert_fp16_to_fp64(double addrspace(1)* noalias %out, i16 addrspace(1)* noalias %in) nounwind {
|
|
%val = load i16, i16 addrspace(1)* %in, align 2
|
|
%cvt = call double @llvm.convert.from.fp16.f64(i16 %val) nounwind readnone
|
|
store double %cvt, double addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
|
|
; CHECK-LABEL: @test_convert_fp32_to_fp16
|
|
; CHECK: cvt.rn.f16.f32
|
|
define void @test_convert_fp32_to_fp16(i16 addrspace(1)* noalias %out, float addrspace(1)* noalias %in) nounwind {
|
|
%val = load float, float addrspace(1)* %in, align 2
|
|
%cvt = call i16 @llvm.convert.to.fp16.f32(float %val) nounwind readnone
|
|
store i16 %cvt, i16 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
|
|
; CHECK-LABEL: @test_convert_fp64_to_fp16
|
|
; CHECK: cvt.rn.f16.f64
|
|
define void @test_convert_fp64_to_fp16(i16 addrspace(1)* noalias %out, double addrspace(1)* noalias %in) nounwind {
|
|
%val = load double, double addrspace(1)* %in, align 2
|
|
%cvt = call i16 @llvm.convert.to.fp16.f64(double %val) nounwind readnone
|
|
store i16 %cvt, i16 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|