derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
71 lines
2.1 KiB
LLVM
71 lines
2.1 KiB
LLVM
; RUN: llc -mtriple=mips64el -mcpu=r5900 < %s | FileCheck %s -check-prefix=FIX
|
|
; RUN: llc -mtriple=mips64el -mcpu=r5900 -mattr=-fix-r5900 < %s | FileCheck %s -check-prefix=NOFIX
|
|
;
|
|
; Test R5900 short loop erratum fix.
|
|
; The R5900 has a hardware bug where short loops (6 instructions or fewer)
|
|
; with a branch may exit after 1-2 iterations instead of the expected count.
|
|
; The fix ensures the delay slot contains a NOP for such short backward branches.
|
|
|
|
; Short loop test with store - delay slot can be filled when fix is disabled
|
|
; With fix enabled: bnez followed by nop
|
|
; With fix disabled: bnez followed by daddiu (delay slot filled)
|
|
|
|
; FIX-LABEL: test_short_loop_store:
|
|
; FIX: .LBB0_1:
|
|
; FIX: bnez
|
|
; FIX-NEXT: nop
|
|
|
|
; NOFIX-LABEL: test_short_loop_store:
|
|
; NOFIX: .LBB0_1:
|
|
; NOFIX: bnez
|
|
; NOFIX-NEXT: daddiu
|
|
define void @test_short_loop_store(ptr %arr, i32 %n) {
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%i = phi i32 [ 0, %entry ], [ %inc, %loop ]
|
|
%ptr = getelementptr i32, ptr %arr, i32 %i
|
|
store i32 %i, ptr %ptr
|
|
%inc = add i32 %i, 1
|
|
%cmp = icmp slt i32 %inc, %n
|
|
br i1 %cmp, label %loop, label %exit
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|
|
; Long loop - should NOT be affected by the fix (too many instructions)
|
|
; Delay slot can be filled since loop is longer than 6 instructions
|
|
; The scheduler may choose different instructions for the delay slot
|
|
; FIX-LABEL: test_long_loop:
|
|
; FIX: .LBB1_1:
|
|
; FIX: bnez ${{[0-9]+}}, .LBB1_1
|
|
; Delay slot should be filled with actual instruction, not nop
|
|
; FIX-NEXT: {{sw|daddiu|addu}}
|
|
|
|
; NOFIX-LABEL: test_long_loop:
|
|
; NOFIX: .LBB1_1:
|
|
; NOFIX: bnez ${{[0-9]+}}, .LBB1_1
|
|
; NOFIX-NEXT: {{sw|daddiu|addu}}
|
|
define i32 @test_long_loop(ptr %arr, i32 %n) {
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%i = phi i32 [ 0, %entry ], [ %inc, %loop ]
|
|
%sum = phi i32 [ 0, %entry ], [ %add, %loop ]
|
|
%ptr = getelementptr i32, ptr %arr, i32 %i
|
|
%val = load i32, ptr %ptr
|
|
%mul = mul i32 %val, %i
|
|
%add = add i32 %sum, %mul
|
|
%ptr2 = getelementptr i32, ptr %arr, i32 %add
|
|
store i32 %add, ptr %ptr2
|
|
%inc = add i32 %i, 1
|
|
%cmp = icmp slt i32 %inc, %n
|
|
br i1 %cmp, label %loop, label %exit
|
|
|
|
exit:
|
|
ret i32 %add
|
|
}
|