2195fe7e01
On new targets like `gfx1250`, the buffer resource (V#) now uses this format: ``` base (57-bit): resource[56:0] num_records (45-bit): resource[101:57] reserved (6-bit): resource[107:102] stride (14-bit): resource[121:108] ``` This PR changes the type of `num_records` from `i32` to `i64` in both builtin and intrinsic, and also adds the support for lowering the new format. Fixes SWDEV-554034. --------- Co-authored-by: Krzysztof Drewniak <Krzysztof.Drewniak@amd.com>
40 lines
2.1 KiB
LLVM
40 lines
2.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: opt -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 -passes=loop-vectorize -S < %s | FileCheck %s
|
|
|
|
; Reduced from a crash, variables added to make things more realistic.
|
|
; This is a roundabout test for TargetLowering::getValueType() returning
|
|
; a reasonable value for <N x p7> instead of asserting.
|
|
define amdgpu_kernel void @_dynamic_pack_simple_dispatch_0_pack_i32(ptr addrspace(1) %.ptr, i64 %v) {
|
|
; CHECK-LABEL: define amdgpu_kernel void @_dynamic_pack_simple_dispatch_0_pack_i32(
|
|
; CHECK-SAME: ptr addrspace(1) [[DOTPTR:%.*]], i64 [[V:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: [[ENTRY:.*]]:
|
|
; CHECK-NEXT: [[DOTRSRC:%.*]] = call ptr addrspace(8) @llvm.amdgcn.make.buffer.rsrc.p8.p1(ptr addrspace(1) [[DOTPTR]], i16 0, i64 2147483648, i32 159744)
|
|
; CHECK-NEXT: [[TMP1:%.*]] = addrspacecast ptr addrspace(8) [[DOTRSRC]] to ptr addrspace(7)
|
|
; CHECK-NEXT: br label %[[LOOP:.*]]
|
|
; CHECK: [[LOOP]]:
|
|
; CHECK-NEXT: [[TMP3:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[TMP5:%.*]], %[[LOOP]] ]
|
|
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr i32, ptr addrspace(7) [[TMP1]], i32 0
|
|
; CHECK-NEXT: [[TMP5]] = add i64 [[TMP3]], 1
|
|
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[TMP3]], [[V]]
|
|
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT:.*]], label %[[LOOP]]
|
|
; CHECK: [[EXIT]]:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%rsrc = call ptr addrspace(8) @llvm.amdgcn.make.buffer.rsrc.p1(ptr addrspace(1) %.ptr, i16 0, i64 2147483648, i32 159744)
|
|
%fat = addrspacecast ptr addrspace(8) %rsrc to ptr addrspace(7)
|
|
br label %loop
|
|
|
|
loop: ; preds = %loop, %entry
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
|
|
%ptr = getelementptr i32, ptr addrspace(7) %fat, i32 0
|
|
%iv.next = add i64 %iv, 1
|
|
%exitcond.not = icmp eq i64 %iv, %v
|
|
br i1 %exitcond.not, label %exit, label %loop
|
|
|
|
exit: ; preds = %exit
|
|
ret void
|
|
}
|
|
|
|
declare ptr addrspace(8) @llvm.amdgcn.make.buffer.rsrc.p1(ptr addrspace(1) readnone, i16, i64, i32)
|