mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-27 13:30:05 +00:00
86245071b5
Print the range of registers used with a single letter prefix. This better matches what the shader compiler produces and is overall less obnoxious than concatenating all of the subregister names together. Instead of SGPR0, it will print s0. Instead of SGPR0_SGPR1, it will print s[0:1] and so on. There doesn't appear to be a straightforward way to get the actual register info in the InstPrinter, so this parses the generated name to print with the new syntax. The required test changes are pretty nasty, and register matching regexes are now worse. Since there isn't a way to add to a variable in FileCheck, some of the tests now don't check the exact number of registers used, but I don't think that will be a real problem. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194443 91177308-0d34-0410-b5e6-96231b3b80d8
52 lines
2.4 KiB
LLVM
52 lines
2.4 KiB
LLVM
;RUN: llc < %s -march=r600 -mcpu=verde -verify-machineinstrs | FileCheck %s
|
|
|
|
; This shader has the potential to generated illegal VGPR to SGPR copies if
|
|
; the wrong register class is used for the REG_SEQUENCE instructions.
|
|
|
|
; CHECK: @main
|
|
; CHECK: IMAGE_SAMPLE_B v{{\[[0-9]:[0-9]\]}}, 15, 0, 0, 0, 0, 0, 0, 0, v{{\[[0-9]:[0-9]\]}}
|
|
|
|
define void @main(<16 x i8> addrspace(2)* inreg, <16 x i8> addrspace(2)* inreg, <32 x i8> addrspace(2)* inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, float, float, float, float) #0 {
|
|
main_body:
|
|
%20 = getelementptr <16 x i8> addrspace(2)* %0, i32 0
|
|
%21 = load <16 x i8> addrspace(2)* %20, !tbaa !1
|
|
%22 = call float @llvm.SI.load.const(<16 x i8> %21, i32 16)
|
|
%23 = getelementptr <32 x i8> addrspace(2)* %2, i32 0
|
|
%24 = load <32 x i8> addrspace(2)* %23, !tbaa !1
|
|
%25 = getelementptr <16 x i8> addrspace(2)* %1, i32 0
|
|
%26 = load <16 x i8> addrspace(2)* %25, !tbaa !1
|
|
%27 = call float @llvm.SI.fs.interp(i32 0, i32 0, i32 %3, <2 x i32> %5)
|
|
%28 = call float @llvm.SI.fs.interp(i32 1, i32 0, i32 %3, <2 x i32> %5)
|
|
%29 = bitcast float %22 to i32
|
|
%30 = bitcast float %27 to i32
|
|
%31 = bitcast float %28 to i32
|
|
%32 = insertelement <4 x i32> undef, i32 %29, i32 0
|
|
%33 = insertelement <4 x i32> %32, i32 %30, i32 1
|
|
%34 = insertelement <4 x i32> %33, i32 %31, i32 2
|
|
%35 = insertelement <4 x i32> %34, i32 undef, i32 3
|
|
%36 = call <4 x float> @llvm.SI.sampleb.v4i32(<4 x i32> %35, <32 x i8> %24, <16 x i8> %26, i32 2)
|
|
%37 = extractelement <4 x float> %36, i32 0
|
|
%38 = extractelement <4 x float> %36, i32 1
|
|
%39 = extractelement <4 x float> %36, i32 2
|
|
%40 = extractelement <4 x float> %36, i32 3
|
|
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 0, float %37, float %38, float %39, float %40)
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: nounwind readnone
|
|
declare float @llvm.SI.load.const(<16 x i8>, i32) #1
|
|
|
|
; Function Attrs: nounwind readnone
|
|
declare float @llvm.SI.fs.interp(i32, i32, i32, <2 x i32>) #1
|
|
|
|
; Function Attrs: nounwind readnone
|
|
declare <4 x float> @llvm.SI.sampleb.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32) #1
|
|
|
|
declare void @llvm.SI.export(i32, i32, i32, i32, i32, float, float, float, float)
|
|
|
|
attributes #0 = { "ShaderType"="0" }
|
|
attributes #1 = { nounwind readnone }
|
|
|
|
!0 = metadata !{metadata !"const", null}
|
|
!1 = metadata !{metadata !0, metadata !0, i64 0, i32 1}
|