1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 04:32:44 +01:00
llvm-mirror/test/CodeGen/AMDGPU/sub-zext-cc-zext-cc.ll
Jay Foad cc94ceb292 [AMDGPU] Extend macro fusion for ADDC and SUBB to SUBBREV
Summary:
There's a lot of test case churn but the overall effect is to increase
the number of back-to-back v_sub,v_subbrev pairs, which can execute with
no delay even on gfx10.

Reviewers: arsenm, rampitec, nhaehnle

Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, hiraditya, kerbowa, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D75999
2020-03-11 17:59:21 +00:00

35 lines
1.2 KiB
LLVM

; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx900 -verify-machineinstrs <%s | FileCheck -check-prefixes=GCN %s
;
; This test checks that we have the correct fold for zext(cc1) - zext(cc2).
;
; GCN-LABEL: sub_zext_zext:
; GCN: ds_read_b32 [[VAL:v[0-9]+]],
; GCN: v_cmp_lt_f32{{.*}} vcc, 0, [[VAL]]
; GCN: v_cndmask_{{.*}} [[ZEXTCC1:v[0-9]+]], 0, 1, vcc
; GCN: v_cmp_gt_f32{{.*}} vcc, 0, [[VAL]]
; GCN: v_subbrev{{.*}} {{v[0-9]+}}, vcc, 0, [[ZEXTCC1]], vcc
;
; Before the reversion that this test is attached to, the compiler commuted
; the operands to the sub and used different logic to select the addc/subc
; instruction:
; sub zext (setcc), x => addcarry 0, x, setcc
; sub sext (setcc), x => subcarry 0, x, setcc
;
; ... but that is bogus. I believe it is not possible to fold those commuted
; patterns into any form of addcarry or subcarry.
define amdgpu_cs float @sub_zext_zext() {
.entry:
%t519 = load float, float addrspace(3)* null
%t524 = fcmp ogt float %t519, 0.000000e+00
%t525 = fcmp olt float %t519, 0.000000e+00
%t526 = zext i1 %t524 to i32
%t527 = zext i1 %t525 to i32
%t528 = sub nsw i32 %t526, %t527
%t529 = sitofp i32 %t528 to float
ret float %t529
}