00aa0aeb06
Texture/sampler/surface operands can be either a register or an
immediate (an index of .texref, .samplerref or .surfref).
TableGen declarations for these instructions used to only have
Int64Regs operands, so this caused issues when machine verifier
is turned on:
*** Bad machine code: Expected a register operand. ***
- function: bar
- basic block: %bb.0 (0x55b144d99ab8)
- instruction: %4:int32regs = SULD_1D_I32_TRAP 0, killed %2:int32regs
- operand 1: 0
The solution is to duplicate these instructions for all possible
operand types (i16imm and Int64Regs). Since this would
essentially double the amount code in TableGen, the patch also
does some refactoring for the original instructions to keep
things manageable.
Differential Revision: https://reviews.llvm.org/D112232
54 lines
2.1 KiB
LLVM
54 lines
2.1 KiB
LLVM
; RUN: llc < %s -march=nvptx -mcpu=sm_20 -verify-machineinstrs | FileCheck %s --check-prefix=SM20
|
|
; RUN: llc < %s -march=nvptx -mcpu=sm_30 -verify-machineinstrs | FileCheck %s --check-prefix=SM30
|
|
|
|
target triple = "nvptx-unknown-cuda"
|
|
|
|
declare i32 @llvm.nvvm.suld.1d.i32.trap(i64, i32)
|
|
declare i64 @llvm.nvvm.texsurf.handle.internal.p1i64(i64 addrspace(1)*)
|
|
|
|
|
|
; SM20-LABEL: .entry foo
|
|
; SM30-LABEL: .entry foo
|
|
define void @foo(i64 %img, float* %red, i32 %idx) {
|
|
; SM20: ld.param.u64 %rd[[SURFREG:[0-9]+]], [foo_param_0];
|
|
; SM20: suld.b.1d.b32.trap {%r[[RED:[0-9]+]]}, [%rd[[SURFREG]], {%r{{[0-9]+}}}]
|
|
; SM30: ld.param.u64 %rd[[SURFREG:[0-9]+]], [foo_param_0];
|
|
; SM30: suld.b.1d.b32.trap {%r[[RED:[0-9]+]]}, [%rd[[SURFREG]], {%r{{[0-9]+}}}]
|
|
%val = tail call i32 @llvm.nvvm.suld.1d.i32.trap(i64 %img, i32 %idx)
|
|
; SM20: cvt.rn.f32.s32 %f[[REDF:[0-9]+]], %r[[RED]]
|
|
; SM30: cvt.rn.f32.s32 %f[[REDF:[0-9]+]], %r[[RED]]
|
|
%ret = sitofp i32 %val to float
|
|
; SM20: st.global.f32 [%r{{[0-9]+}}], %f[[REDF]]
|
|
; SM30: st.global.f32 [%r{{[0-9]+}}], %f[[REDF]]
|
|
store float %ret, float* %red
|
|
ret void
|
|
}
|
|
|
|
@surf0 = internal addrspace(1) global i64 0, align 8
|
|
|
|
; SM20-LABEL: .entry bar
|
|
; SM30-LABEL: .entry bar
|
|
define void @bar(float* %red, i32 %idx) {
|
|
; SM30: mov.u64 %rd[[SURFHANDLE:[0-9]+]], surf0
|
|
%surfHandle = tail call i64 @llvm.nvvm.texsurf.handle.internal.p1i64(i64 addrspace(1)* @surf0)
|
|
; SM20: suld.b.1d.b32.trap {%r[[RED:[0-9]+]]}, [surf0, {%r{{[0-9]+}}}]
|
|
; SM30: suld.b.1d.b32.trap {%r[[RED:[0-9]+]]}, [%rd[[SURFHANDLE]], {%r{{[0-9]+}}}]
|
|
%val = tail call i32 @llvm.nvvm.suld.1d.i32.trap(i64 %surfHandle, i32 %idx)
|
|
; SM20: cvt.rn.f32.s32 %f[[REDF:[0-9]+]], %r[[RED]]
|
|
; SM30: cvt.rn.f32.s32 %f[[REDF:[0-9]+]], %r[[RED]]
|
|
%ret = sitofp i32 %val to float
|
|
; SM20: st.global.f32 [%r{{[0-9]+}}], %f[[REDF]]
|
|
; SM30: st.global.f32 [%r{{[0-9]+}}], %f[[REDF]]
|
|
store float %ret, float* %red
|
|
ret void
|
|
}
|
|
|
|
|
|
|
|
|
|
!nvvm.annotations = !{!1, !2, !3}
|
|
!1 = !{void (i64, float*, i32)* @foo, !"kernel", i32 1}
|
|
!2 = !{void (float*, i32)* @bar, !"kernel", i32 1}
|
|
!3 = !{i64 addrspace(1)* @surf0, !"surface", i32 1}
|
|
|