caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
1650f1b3d7f97ca95eb930984e74bdfd91b02b4e
clang-p2996/llvm/test/CodeGen/AMDGPU/lower-buffer-fat-pointers-p7-in-memory.ll
Krzysztof Drewniak 6540f1635a [AMDGPU] Add IR-level pass to rewrite away address space 7 (#77952) 
This commit adds the -lower-buffer-fat-pointers pass, which is
applicable to all AMDGCN compilations.

The purpose of this pass is to remove the type `ptr addrspace(7)` from
incoming IR. This must be done at the LLVM IR level because `ptr
addrspace(7)`, as a 160-bit primitive type, cannot be correctly handled
by SelectionDAG.

The detailed operation of the pass is described in comments, but, in
summary, the removal proceeds by:
1. Rewriting loads and stores of ptr addrspace(7) to loads and stores of
i160 (including vectors and aggregates). This is needed because the
in-register representation of these pointers will stop matching their
in-memory representation in step 2, and so ptrtoint/inttoptr operations
are used to preserve the expected memory layout

2. Mutating the IR to replace all occurrences of `ptr addrspace(7)` with
the type `{ptr addrspace(8), ptr addrspace(6) }`, which makes the two
parts of a buffer fat pointer (the 128-bit address space 8 resource and
the 32-bit address space 6 offset) visible in the IR. This also impacts
the argument and return types of functions.

3. *Splitting* the resource and offset parts. All instructions that
produce or consume buffer fat pointers (like GEP or load) are rewritten
to produce or consume the resource and offset parts separately. For
example, GEP updates the offset part of the result and a load uses the
resource and offset parts to populate the relevant
llvm.amdgcn.raw.ptr.buffer.load intrinsic call.

At the end of this process, the original mutated instructions are
replaced by their new split counterparts, ensuring no invalidly-typed IR
escapes this pass. (For operations like call, where the struct form is
needed, insertelement operations are inserted).

Compared to LGC's PatchBufferOp (

32cda89776/lgc/patch/PatchBufferOp.cpp
): this pass
- Also handles vectors of ptr addrspace(7)s
- Also handles function boundaries
- Includes the same uniform buffer optimization for loops and
conditionals
- Does *not* handle memcpy() and friends (this is future work)
- Does *not* break up large loads and stores into smaller parts. This
should be handled by extending the legalization
of *.buffer.{load,store} to handle larger types by producing multiple
instructions (the same way ordinary LOAD and STORE are legalized). That
work is planned for a followup commit.
- Does *not* have special logic for handling divergent buffer
descriptors. The logic in LGC is, as far as I can tell, incorrect in
general, and, per discussions with @nhaehnle, isn't widely used.
Therefore, divergent descriptors are handled with waterfall loops later
in legalization.

As a final matter, this commit updates atomic expansion to treat buffer
operations analogously to global ones.

(One question for reviewers: is the new pass is the right place? Should
it be later in the pipeline?)

Differential Revision: https://reviews.llvm.org/D158463
2024-03-06 09:49:58 -06:00

155 lines
10 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
; RUN: opt -S -mcpu=gfx900 -amdgpu-lower-buffer-fat-pointers < %s | FileCheck %s
; RUN: opt -S -mcpu=gfx900 -passes=amdgpu-lower-buffer-fat-pointers < %s | FileCheck %s
target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-p7:160:256:256:32-p8:128:128-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5-G1-ni:7:8"
target triple = "amdgcn--"
define void @scalar_copy(ptr %a, ptr %b) {
; CHECK-LABEL: define void @scalar_copy
; CHECK-SAME: (ptr [[A:%.*]], ptr [[B:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: [[X:%.*]] = load i160, ptr [[A]], align 32
; CHECK-NEXT: [[TMP1:%.*]] = lshr i160 [[X]], 32
; CHECK-NEXT: [[TMP2:%.*]] = trunc i160 [[TMP1]] to i128
; CHECK-NEXT: [[X_PTR_RSRC:%.*]] = inttoptr i128 [[TMP2]] to ptr addrspace(8)
; CHECK-NEXT: [[X_PTR_OFF:%.*]] = trunc i160 [[X]] to i32
; CHECK-NEXT: [[B1:%.*]] = getelementptr i160, ptr [[B]], i64 1
; CHECK-NEXT: [[X_PTR_INT_RSRC:%.*]] = ptrtoint ptr addrspace(8) [[X_PTR_RSRC]] to i160
; CHECK-NEXT: [[TMP3:%.*]] = shl nuw i160 [[X_PTR_INT_RSRC]], 32
; CHECK-NEXT: [[X_PTR_INT_OFF:%.*]] = zext i32 [[X_PTR_OFF]] to i160
; CHECK-NEXT: [[X_PTR_INT:%.*]] = or i160 [[TMP3]], [[X_PTR_INT_OFF]]
; CHECK-NEXT: store i160 [[X_PTR_INT]], ptr [[B1]], align 32
; CHECK-NEXT: ret void
;
%x = load ptr addrspace(7), ptr %a
%b1 = getelementptr ptr addrspace(7), ptr %b, i64 1
store ptr addrspace(7) %x, ptr %b1
ret void
}
define void @vector_copy(ptr %a, ptr %b) {
; CHECK-LABEL: define void @vector_copy
; CHECK-SAME: (ptr [[A:%.*]], ptr [[B:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[X:%.*]] = load <4 x i160>, ptr [[A]], align 128
; CHECK-NEXT: [[TMP1:%.*]] = lshr <4 x i160> [[X]], <i160 32, i160 32, i160 32, i160 32>
; CHECK-NEXT: [[TMP2:%.*]] = trunc <4 x i160> [[TMP1]] to <4 x i128>
; CHECK-NEXT: [[X_PTR_RSRC:%.*]] = inttoptr <4 x i128> [[TMP2]] to <4 x ptr addrspace(8)>
; CHECK-NEXT: [[X_PTR_OFF:%.*]] = trunc <4 x i160> [[X]] to <4 x i32>
; CHECK-NEXT: [[B1:%.*]] = getelementptr <4 x i160>, ptr [[B]], i64 2
; CHECK-NEXT: [[X_PTR_INT_RSRC:%.*]] = ptrtoint <4 x ptr addrspace(8)> [[X_PTR_RSRC]] to <4 x i160>
; CHECK-NEXT: [[TMP3:%.*]] = shl nuw <4 x i160> [[X_PTR_INT_RSRC]], <i160 32, i160 32, i160 32, i160 32>
; CHECK-NEXT: [[X_PTR_INT_OFF:%.*]] = zext <4 x i32> [[X_PTR_OFF]] to <4 x i160>
; CHECK-NEXT: [[X_PTR_INT:%.*]] = or <4 x i160> [[TMP3]], [[X_PTR_INT_OFF]]
; CHECK-NEXT: store <4 x i160> [[X_PTR_INT]], ptr [[B1]], align 128
; CHECK-NEXT: ret void
;
%x = load <4 x ptr addrspace(7)>, ptr %a
%b1 = getelementptr <4 x ptr addrspace(7)>, ptr %b, i64 2
store <4 x ptr addrspace(7)> %x, ptr %b1
ret void
}
define void @alloca(ptr %a, ptr %b) {
; CHECK-LABEL: define void @alloca
; CHECK-SAME: (ptr [[A:%.*]], ptr [[B:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[ALLOCA:%.*]] = alloca [5 x i160], align 32, addrspace(5)
; CHECK-NEXT: [[X:%.*]] = load i160, ptr [[A]], align 32
; CHECK-NEXT: [[TMP1:%.*]] = lshr i160 [[X]], 32
; CHECK-NEXT: [[TMP2:%.*]] = trunc i160 [[TMP1]] to i128
; CHECK-NEXT: [[X_PTR_RSRC:%.*]] = inttoptr i128 [[TMP2]] to ptr addrspace(8)
; CHECK-NEXT: [[X_PTR_OFF:%.*]] = trunc i160 [[X]] to i32
; CHECK-NEXT: [[L:%.*]] = getelementptr i160, ptr addrspace(5) [[ALLOCA]], i32 1
; CHECK-NEXT: [[X_PTR_INT_RSRC:%.*]] = ptrtoint ptr addrspace(8) [[X_PTR_RSRC]] to i160
; CHECK-NEXT: [[TMP3:%.*]] = shl nuw i160 [[X_PTR_INT_RSRC]], 32
; CHECK-NEXT: [[X_PTR_INT_OFF:%.*]] = zext i32 [[X_PTR_OFF]] to i160
; CHECK-NEXT: [[X_PTR_INT:%.*]] = or i160 [[TMP3]], [[X_PTR_INT_OFF]]
; CHECK-NEXT: store i160 [[X_PTR_INT]], ptr addrspace(5) [[L]], align 32
; CHECK-NEXT: [[Y:%.*]] = load i160, ptr addrspace(5) [[L]], align 32
; CHECK-NEXT: [[TMP4:%.*]] = lshr i160 [[Y]], 32
; CHECK-NEXT: [[TMP5:%.*]] = trunc i160 [[TMP4]] to i128
; CHECK-NEXT: [[Y_PTR_RSRC:%.*]] = inttoptr i128 [[TMP5]] to ptr addrspace(8)
; CHECK-NEXT: [[Y_PTR_OFF:%.*]] = trunc i160 [[Y]] to i32
; CHECK-NEXT: [[Y_PTR_INT_RSRC:%.*]] = ptrtoint ptr addrspace(8) [[Y_PTR_RSRC]] to i160
; CHECK-NEXT: [[TMP6:%.*]] = shl nuw i160 [[Y_PTR_INT_RSRC]], 32
; CHECK-NEXT: [[Y_PTR_INT_OFF:%.*]] = zext i32 [[Y_PTR_OFF]] to i160
; CHECK-NEXT: [[Y_PTR_INT:%.*]] = or i160 [[TMP6]], [[Y_PTR_INT_OFF]]
; CHECK-NEXT: store i160 [[Y_PTR_INT]], ptr [[B]], align 32
; CHECK-NEXT: ret void
;
%alloca = alloca [5 x ptr addrspace(7)], addrspace(5)
%x = load ptr addrspace(7), ptr %a
%l = getelementptr ptr addrspace(7), ptr addrspace(5) %alloca, i32 1
store ptr addrspace(7) %x, ptr addrspace(5) %l
%y = load ptr addrspace(7), ptr addrspace(5) %l
store ptr addrspace(7) %y, ptr %b
ret void
}
define void @complex_copy(ptr %a, ptr %b) {
; CHECK-LABEL: define void @complex_copy
; CHECK-SAME: (ptr [[A:%.*]], ptr [[B:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[X:%.*]] = load { [2 x i160], i32, i160 }, ptr [[A]], align 32
; CHECK-NEXT: [[TMP1:%.*]] = extractvalue { [2 x i160], i32, i160 } [[X]], 0
; CHECK-NEXT: [[TMP2:%.*]] = extractvalue [2 x i160] [[TMP1]], 0
; CHECK-NEXT: [[TMP3:%.*]] = lshr i160 [[TMP2]], 32
; CHECK-NEXT: [[TMP4:%.*]] = trunc i160 [[TMP3]] to i128
; CHECK-NEXT: [[X_0_0_PTR_RSRC:%.*]] = inttoptr i128 [[TMP4]] to ptr addrspace(8)
; CHECK-NEXT: [[X_0_0_PTR_OFF:%.*]] = trunc i160 [[TMP2]] to i32
; CHECK-NEXT: [[TMP5:%.*]] = insertvalue { ptr addrspace(8), i32 } poison, ptr addrspace(8) [[X_0_0_PTR_RSRC]], 0
; CHECK-NEXT: [[X_0_0_PTR:%.*]] = insertvalue { ptr addrspace(8), i32 } [[TMP5]], i32 [[X_0_0_PTR_OFF]], 1
; CHECK-NEXT: [[TMP6:%.*]] = insertvalue [2 x { ptr addrspace(8), i32 }] poison, { ptr addrspace(8), i32 } [[X_0_0_PTR]], 0
; CHECK-NEXT: [[TMP7:%.*]] = extractvalue [2 x i160] [[TMP1]], 1
; CHECK-NEXT: [[TMP8:%.*]] = lshr i160 [[TMP7]], 32
; CHECK-NEXT: [[TMP9:%.*]] = trunc i160 [[TMP8]] to i128
; CHECK-NEXT: [[X_0_1_PTR_RSRC:%.*]] = inttoptr i128 [[TMP9]] to ptr addrspace(8)
; CHECK-NEXT: [[X_0_1_PTR_OFF:%.*]] = trunc i160 [[TMP7]] to i32
; CHECK-NEXT: [[TMP10:%.*]] = insertvalue { ptr addrspace(8), i32 } poison, ptr addrspace(8) [[X_0_1_PTR_RSRC]], 0
; CHECK-NEXT: [[X_0_1_PTR:%.*]] = insertvalue { ptr addrspace(8), i32 } [[TMP10]], i32 [[X_0_1_PTR_OFF]], 1
; CHECK-NEXT: [[TMP11:%.*]] = insertvalue [2 x { ptr addrspace(8), i32 }] [[TMP6]], { ptr addrspace(8), i32 } [[X_0_1_PTR]], 1
; CHECK-NEXT: [[TMP12:%.*]] = insertvalue { [2 x { ptr addrspace(8), i32 }], i32, { ptr addrspace(8), i32 } } poison, [2 x { ptr addrspace(8), i32 }] [[TMP11]], 0
; CHECK-NEXT: [[TMP13:%.*]] = extractvalue { [2 x i160], i32, i160 } [[X]], 1
; CHECK-NEXT: [[TMP14:%.*]] = insertvalue { [2 x { ptr addrspace(8), i32 }], i32, { ptr addrspace(8), i32 } } [[TMP12]], i32 [[TMP13]], 1
; CHECK-NEXT: [[TMP15:%.*]] = extractvalue { [2 x i160], i32, i160 } [[X]], 2
; CHECK-NEXT: [[TMP16:%.*]] = lshr i160 [[TMP15]], 32
; CHECK-NEXT: [[TMP17:%.*]] = trunc i160 [[TMP16]] to i128
; CHECK-NEXT: [[X_2_PTR_RSRC:%.*]] = inttoptr i128 [[TMP17]] to ptr addrspace(8)
; CHECK-NEXT: [[X_2_PTR_OFF:%.*]] = trunc i160 [[TMP15]] to i32
; CHECK-NEXT: [[TMP18:%.*]] = insertvalue { ptr addrspace(8), i32 } poison, ptr addrspace(8) [[X_2_PTR_RSRC]], 0
; CHECK-NEXT: [[X_2_PTR:%.*]] = insertvalue { ptr addrspace(8), i32 } [[TMP18]], i32 [[X_2_PTR_OFF]], 1
; CHECK-NEXT: [[TMP19:%.*]] = insertvalue { [2 x { ptr addrspace(8), i32 }], i32, { ptr addrspace(8), i32 } } [[TMP14]], { ptr addrspace(8), i32 } [[X_2_PTR]], 2
; CHECK-NEXT: [[TMP20:%.*]] = extractvalue { [2 x { ptr addrspace(8), i32 }], i32, { ptr addrspace(8), i32 } } [[TMP19]], 0
; CHECK-NEXT: [[TMP21:%.*]] = extractvalue [2 x { ptr addrspace(8), i32 }] [[TMP20]], 0
; CHECK-NEXT: [[DOTRSRC:%.*]] = extractvalue { ptr addrspace(8), i32 } [[TMP21]], 0
; CHECK-NEXT: [[DOTOFF:%.*]] = extractvalue { ptr addrspace(8), i32 } [[TMP21]], 1
; CHECK-NEXT: [[DOT0_0_INT_RSRC:%.*]] = ptrtoint ptr addrspace(8) [[DOTRSRC]] to i160
; CHECK-NEXT: [[TMP22:%.*]] = shl nuw i160 [[DOT0_0_INT_RSRC]], 32
; CHECK-NEXT: [[DOT0_0_INT_OFF:%.*]] = zext i32 [[DOTOFF]] to i160
; CHECK-NEXT: [[DOT0_0_INT:%.*]] = or i160 [[TMP22]], [[DOT0_0_INT_OFF]]
; CHECK-NEXT: [[TMP23:%.*]] = insertvalue [2 x i160] poison, i160 [[DOT0_0_INT]], 0
; CHECK-NEXT: [[TMP24:%.*]] = extractvalue [2 x { ptr addrspace(8), i32 }] [[TMP20]], 1
; CHECK-NEXT: [[DOTRSRC1:%.*]] = extractvalue { ptr addrspace(8), i32 } [[TMP24]], 0
; CHECK-NEXT: [[DOTOFF2:%.*]] = extractvalue { ptr addrspace(8), i32 } [[TMP24]], 1
; CHECK-NEXT: [[DOT0_1_INT_RSRC:%.*]] = ptrtoint ptr addrspace(8) [[DOTRSRC1]] to i160
; CHECK-NEXT: [[TMP25:%.*]] = shl nuw i160 [[DOT0_1_INT_RSRC]], 32
; CHECK-NEXT: [[DOT0_1_INT_OFF:%.*]] = zext i32 [[DOTOFF2]] to i160
; CHECK-NEXT: [[DOT0_1_INT:%.*]] = or i160 [[TMP25]], [[DOT0_1_INT_OFF]]
; CHECK-NEXT: [[TMP26:%.*]] = insertvalue [2 x i160] [[TMP23]], i160 [[DOT0_1_INT]], 1
; CHECK-NEXT: [[TMP27:%.*]] = insertvalue { [2 x i160], i32, i160 } poison, [2 x i160] [[TMP26]], 0
; CHECK-NEXT: [[TMP28:%.*]] = extractvalue { [2 x { ptr addrspace(8), i32 }], i32, { ptr addrspace(8), i32 } } [[TMP19]], 1
; CHECK-NEXT: [[TMP29:%.*]] = insertvalue { [2 x i160], i32, i160 } [[TMP27]], i32 [[TMP28]], 1
; CHECK-NEXT: [[TMP30:%.*]] = extractvalue { [2 x { ptr addrspace(8), i32 }], i32, { ptr addrspace(8), i32 } } [[TMP19]], 2
; CHECK-NEXT: [[DOTRSRC3:%.*]] = extractvalue { ptr addrspace(8), i32 } [[TMP30]], 0
; CHECK-NEXT: [[DOTOFF4:%.*]] = extractvalue { ptr addrspace(8), i32 } [[TMP30]], 1
; CHECK-NEXT: [[DOT2_INT_RSRC:%.*]] = ptrtoint ptr addrspace(8) [[DOTRSRC3]] to i160
; CHECK-NEXT: [[TMP31:%.*]] = shl nuw i160 [[DOT2_INT_RSRC]], 32
; CHECK-NEXT: [[DOT2_INT_OFF:%.*]] = zext i32 [[DOTOFF4]] to i160
; CHECK-NEXT: [[DOT2_INT:%.*]] = or i160 [[TMP31]], [[DOT2_INT_OFF]]
; CHECK-NEXT: [[TMP32:%.*]] = insertvalue { [2 x i160], i32, i160 } [[TMP29]], i160 [[DOT2_INT]], 2
; CHECK-NEXT: store { [2 x i160], i32, i160 } [[TMP32]], ptr [[B]], align 32
; CHECK-NEXT: ret void
;
%x = load {[2 x ptr addrspace(7)], i32, ptr addrspace(7)}, ptr %a
store {[2 x ptr addrspace(7)], i32, ptr addrspace(7)} %x, ptr %b
ret void
}
Reference in New Issue View Git Blame Copy Permalink