* [PATCH] selftests/powerpc: Fix matrix multiply assist test
@ 2022-06-17 4:39 Rashmica Gupta
2022-07-29 13:03 ` Michael Ellerman
0 siblings, 1 reply; 2+ messages in thread
From: Rashmica Gupta @ 2022-06-17 4:39 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin, alistair
The ISA states: "when ACC[i] contains defined data, the contents of VSRs
4×i to 4×i+3 are undefined until either a VSX Move From ACC instruction
is used to copy the contents of ACC[i] to VSRs 4×i to 4×i+3 or some other
instruction directly writes to one of these VSRs." We aren't doing this.
This test only works on Power10 because the hardware implementation
happens to map ACC0 to VSRs 0-3, but will fail on any other implementation
that doesn't do this. So add xxmfacc between writing to the accumulator
and accessing the VSRs.
Fixes commit 3527e1ab9a79 ("selftests/powerpc: Add matrix multiply assist
(MMA) test")
Signed-off-by: Rashmica Gupta <rashmica@linux.ibm.com>
---
tools/testing/selftests/powerpc/math/mma.S | 3 +++
1 file changed, 3 insertions(+)
diff --git a/tools/testing/selftests/powerpc/math/mma.S b/tools/testing/selftests/powerpc/math/mma.S
index 8528c9849565..61cc88b1b26b 100644
--- a/tools/testing/selftests/powerpc/math/mma.S
+++ b/tools/testing/selftests/powerpc/math/mma.S
@@ -20,6 +20,9 @@ test_mma:
/* xvi16ger2s */
.long 0xec042958
+ /* Deprime the accumulator - xxmfacc 0 */
+ .long 0x7c000162
+
/* Store result in image passed in r5 */
stxvw4x 0,0,5
addi 5,5,16
--
2.35.3
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH] selftests/powerpc: Fix matrix multiply assist test
2022-06-17 4:39 [PATCH] selftests/powerpc: Fix matrix multiply assist test Rashmica Gupta
@ 2022-07-29 13:03 ` Michael Ellerman
0 siblings, 0 replies; 2+ messages in thread
From: Michael Ellerman @ 2022-07-29 13:03 UTC (permalink / raw)
To: Rashmica Gupta, linuxppc-dev; +Cc: alistair, npiggin
On Fri, 17 Jun 2022 14:39:35 +1000, Rashmica Gupta wrote:
> The ISA states: "when ACC[i] contains defined data, the contents of VSRs
> 4×i to 4×i+3 are undefined until either a VSX Move From ACC instruction
> is used to copy the contents of ACC[i] to VSRs 4×i to 4×i+3 or some other
> instruction directly writes to one of these VSRs." We aren't doing this.
>
> This test only works on Power10 because the hardware implementation
> happens to map ACC0 to VSRs 0-3, but will fail on any other implementation
> that doesn't do this. So add xxmfacc between writing to the accumulator
> and accessing the VSRs.
>
> [...]
Applied to powerpc/next.
[1/1] selftests/powerpc: Fix matrix multiply assist test
https://git.kernel.org/powerpc/c/cd1e64935f79e31d666172c52c951ca97152b783
cheers
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2022-07-29 13:22 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-06-17 4:39 [PATCH] selftests/powerpc: Fix matrix multiply assist test Rashmica Gupta
2022-07-29 13:03 ` Michael Ellerman
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).