maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[NVPTX] Add imm variants for surface and texture instructions 

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
This commit is contained in:
Andrew Savonichev 2021-11-10 19:02:27 +03:00
parent 4e2c978f44
commit 00aa0aeb06
10 changed files with 4274 additions and 4104 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

666
llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp
View File

File diff suppressed because it is too large Load Diff

6013
llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
View File

File diff suppressed because it is too large Load Diff

1677
llvm/lib/Target/NVPTX/NVPTXReplaceImageHandles.cpp
View File

File diff suppressed because it is too large Load Diff

4
llvm/test/CodeGen/NVPTX/surf-read-cuda.ll
View File

@ -1,5 +1,5 @@
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s --check-prefix=SM20
; RUN: llc < %s -march=nvptx -mcpu=sm_30 | FileCheck %s --check-prefix=SM30
; 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"

2
llvm/test/CodeGen/NVPTX/surf-read.ll
View File

@ -1,4 +1,4 @@
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
; RUN: llc < %s -march=nvptx -mcpu=sm_20 -verify-machineinstrs | FileCheck %s
target triple = "nvptx-unknown-nvcl"

4
llvm/test/CodeGen/NVPTX/surf-write-cuda.ll
View File

@ -1,5 +1,5 @@
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s --check-prefix=SM20
; RUN: llc < %s -march=nvptx -mcpu=sm_30 | FileCheck %s --check-prefix=SM30
; 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"

2
llvm/test/CodeGen/NVPTX/surf-write.ll
View File

@ -1,4 +1,4 @@
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
; RUN: llc < %s -march=nvptx -mcpu=sm_20 -verify-machineinstrs | FileCheck %s
target triple = "nvptx-unknown-nvcl"

4
llvm/test/CodeGen/NVPTX/tex-read-cuda.ll
View File

@ -1,5 +1,5 @@
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s --check-prefix=SM20
; RUN: llc < %s -march=nvptx -mcpu=sm_30 | FileCheck %s --check-prefix=SM30
; 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"

2
llvm/test/CodeGen/NVPTX/tex-read.ll
View File

@ -1,4 +1,4 @@
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
; RUN: llc < %s -march=nvptx -mcpu=sm_20 -verify-machineinstrs | FileCheck %s
target triple = "nvptx-unknown-nvcl"

4
llvm/test/CodeGen/NVPTX/texsurf-queries.ll
View File

@ -1,5 +1,5 @@
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s --check-prefix=SM20
; RUN: llc < %s -march=nvptx -mcpu=sm_30 | FileCheck %s --check-prefix=SM30
; 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"