lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <1586864113-30682-1-git-send-email-bernard@vivo.com>
Date:   Tue, 14 Apr 2020 04:35:08 -0700
From:   Bernard Zhao <bernard@...o.com>
To:     Alex Deucher <alexander.deucher@....com>,
        Christian König <christian.koenig@....com>,
        "David (ChunMing) Zhou" <David1.Zhou@....com>,
        David Airlie <airlied@...ux.ie>,
        Daniel Vetter <daniel@...ll.ch>,
        Felix Kuehling <Felix.Kuehling@....com>,
        Bernard Zhao <bernard@...o.com>,
        Xiaojie Yuan <xiaojie.yuan@....com>,
        Oak Zeng <Oak.Zeng@....com>, Sam Ravnborg <sam@...nborg.org>,
        Alex Sierra <alex.sierra@....com>,
        Huang Rui <ray.huang@....com>,
        Kent Russell <kent.russell@....com>,
        amd-gfx@...ts.freedesktop.org, dri-devel@...ts.freedesktop.org,
        linux-kernel@...r.kernel.org
Cc:     kernel@...o.com
Subject: [PATCH] Optimized division operation to shift operation

On some processors, the / operate will call the compiler`s div lib,
which is low efficient, We can replace the / operation with shift,
so that we can replace the call of the division library with one
shift assembly instruction.

Signed-off-by: Bernard Zhao <bernard@...o.com>
---
 drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c | 4 ++--
 drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c | 4 ++--
 drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index b205039..66cd078 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -175,10 +175,10 @@ static int gmc_v6_0_mc_load_microcode(struct amdgpu_device *adev)
 	amdgpu_ucode_print_mc_hdr(&hdr->header);
 
 	adev->gmc.fw_version = le32_to_cpu(hdr->header.ucode_version);
-	regs_size = le32_to_cpu(hdr->io_debug_size_bytes) / (4 * 2);
+	regs_size = le32_to_cpu(hdr->io_debug_size_bytes) >> 3;
 	new_io_mc_regs = (const __le32 *)
 		(adev->gmc.fw->data + le32_to_cpu(hdr->io_debug_array_offset_bytes));
-	ucode_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
+	ucode_size = le32_to_cpu(hdr->header.ucode_size_bytes) >> 2;
 	new_fw_data = (const __le32 *)
 		(adev->gmc.fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 9da9596..ca26d63 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -193,10 +193,10 @@ static int gmc_v7_0_mc_load_microcode(struct amdgpu_device *adev)
 	amdgpu_ucode_print_mc_hdr(&hdr->header);
 
 	adev->gmc.fw_version = le32_to_cpu(hdr->header.ucode_version);
-	regs_size = le32_to_cpu(hdr->io_debug_size_bytes) / (4 * 2);
+	regs_size = le32_to_cpu(hdr->io_debug_size_bytes) >> 3;
 	io_mc_regs = (const __le32 *)
 		(adev->gmc.fw->data + le32_to_cpu(hdr->io_debug_array_offset_bytes));
-	ucode_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
+	ucode_size = le32_to_cpu(hdr->header.ucode_size_bytes) >> 2;
 	fw_data = (const __le32 *)
 		(adev->gmc.fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 27d83204..295039c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -318,10 +318,10 @@ static int gmc_v8_0_tonga_mc_load_microcode(struct amdgpu_device *adev)
 	amdgpu_ucode_print_mc_hdr(&hdr->header);
 
 	adev->gmc.fw_version = le32_to_cpu(hdr->header.ucode_version);
-	regs_size = le32_to_cpu(hdr->io_debug_size_bytes) / (4 * 2);
+	regs_size = le32_to_cpu(hdr->io_debug_size_bytes) >> 3;
 	io_mc_regs = (const __le32 *)
 		(adev->gmc.fw->data + le32_to_cpu(hdr->io_debug_array_offset_bytes));
-	ucode_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
+	ucode_size = le32_to_cpu(hdr->header.ucode_size_bytes) >> 2;
 	fw_data = (const __le32 *)
 		(adev->gmc.fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes));
 
-- 
2.7.4

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ