diff options
| -rw-r--r-- | src/mesa/drivers/dri/radeon/radeon_vtxtmp_x86.S | 492 |
1 files changed, 492 insertions, 0 deletions
diff --git a/src/mesa/drivers/dri/radeon/radeon_vtxtmp_x86.S b/src/mesa/drivers/dri/radeon/radeon_vtxtmp_x86.S new file mode 100644 index 00000000000..c77b41059ef --- /dev/null +++ b/src/mesa/drivers/dri/radeon/radeon_vtxtmp_x86.S @@ -0,0 +1,492 @@ +/* $XFree86: xc/lib/GL/mesa/src/drv/radeon/radeon_vtxtmp_x86.S,v 1.1 2002/10/30 12:51:58 alanh Exp $ */ +/************************************************************************** + +Copyright 2002 Tungsten Graphics Inc., Cedar Park, Texas. + +All Rights Reserved. + +Permission is hereby granted, free of charge, to any person obtaining a +copy of this software and associated documentation files (the "Software"), +to deal in the Software without restriction, including without limitation +on the rights to use, copy, modify, merge, publish, distribute, sub +license, and/or sell copies of the Software, and to permit persons to whom +the Software is furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice (including the next +paragraph) shall be included in all copies or substantial portions of the +Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL +ATI, TUNGSTEN GRAPHICS AND/OR THEIR SUPPLIERS BE LIABLE FOR ANY CLAIM, +DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR +OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE +USE OR OTHER DEALINGS IN THE SOFTWARE. + +**************************************************************************/ + +#define GLOBL( x ) \ +.globl x; \ +x: + +.data +.align 4 + +/* + vertex 3f vertex size 4 +*/ + +GLOBL ( _x86_Vertex3f_4 ) + movl (0), %ecx + movl 4(%esp), %eax + movl 8(%esp), %edx + movl %eax, (%ecx) + movl %edx, 4(%ecx) + movl 12(%esp), %eax + movl (0), %edx + movl %eax, 8(%ecx) + movl %edx, 12(%ecx) + movl (0), %eax + addl $16, %ecx + dec %eax + movl %ecx, (0) + movl %eax, (0) + je .1 + ret +.1: jmp *0 + +GLOBL ( _x86_Vertex3f_4_end ) + +/* + vertex 3f vertex size 6 +*/ +GLOBL ( _x86_Vertex3f_6 ) + push %edi + movl (0), %edi + movl 8(%esp), %eax + movl 12(%esp), %edx + movl 16(%esp), %ecx + movl %eax, (%edi) + movl %edx, 4(%edi) + movl %ecx, 8(%edi) + movl (0), %eax + movl (0), %edx + movl (0), %ecx + movl %eax, 12(%edi) + movl %edx, 16(%edi) + movl %ecx, 20(%edi) + addl $24, %edi + movl (0), %eax + movl %edi, (0) + dec %eax + pop %edi + movl %eax, (0) + je .2 + ret +.2: jmp *0 +GLOBL ( _x86_Vertex3f_6_end ) +/* + vertex 3f generic size +*/ +GLOBL ( _x86_Vertex3f ) + push %edi + push %esi + movl $0, %esi + movl (0), %edi + movl 12(%esp), %eax + movl 16(%esp), %edx + movl 20(%esp), %ecx + movl %eax, (%edi) + movl %edx, 4(%edi) + movl %ecx, 8(%edi) + addl $12, %edi + movl $0, %ecx + repz + movsl %ds:(%esi), %es:(%edi) + movl (0), %eax + movl %edi, (0) + dec %eax + movl %eax, (0) + pop %esi + pop %edi + je .3 + ret +.3: jmp *0 + +GLOBL ( _x86_Vertex3f_end ) + +/* + Vertex 3fv vertex size 6 +*/ +GLOBL ( _x86_Vertex3fv_6 ) + movl (0), %eax + movl 4(%esp), %ecx + movl (%ecx), %edx + movl %edx, (%eax) + movl 4(%ecx), %edx + movl 8(%ecx), %ecx + movl %edx, 4(%eax) + movl %ecx, 8(%eax) + movl (28), %edx + movl (32), %ecx + movl %edx, 12(%eax) + movl %ecx, 16(%eax) + movl (36), %edx + movl %edx, 20(%eax) + addl $24, %eax + movl %eax, 0 + movl 4, %eax + dec %eax + movl %eax, 4 + je .4 + ret +.4: jmp *8 + +GLOBL ( _x86_Vertex3fv_6_end ) + +/* + Vertex 3fv vertex size 8 +*/ +GLOBL ( _x86_Vertex3fv_8 ) + movl (0), %eax + movl 4(%esp), %ecx + movl (%ecx), %edx + movl %edx ,(%eax) + movl 4(%ecx) ,%edx + movl 8(%ecx) ,%ecx + movl %edx, 4(%eax) + movl %ecx, 8(%eax) + movl (28), %edx + movl (32), %ecx + movl %edx, 12(%eax) + movl %ecx, 16(%eax) + movl (28), %edx + movl (32), %ecx + movl %edx, 20(%eax) + movl %ecx, 24(%eax) + movl (36), %edx + movl %edx, 28(%eax) + addl $32, %eax + movl %eax, (0) + movl 4, %eax + dec %eax + movl %eax, (4) + je .5 + ret +.5: jmp *8 + +GLOBL ( _x86_Vertex3fv_8_end ) + +/* + Vertex 3fv generic vertex size +*/ +GLOBL ( _x86_Vertex3fv ) + movl 4(%esp), %edx + push %edi + push %esi + movl (0x1010101), %edi + movl (%edx), %eax + movl 4(%edx), %ecx + movl 8(%edx), %esi + movl %eax, (%edi) + movl %ecx, 4(%edi) + movl %esi, 8(%edi) + addl $12, %edi + movl $6, %ecx + movl $0x58, %esi + repz + movsl %ds:(%esi), %es:(%edi) + movl %edi, (0x1010101) + movl (0x2020202), %eax + pop %esi + pop %edi + dec %eax + movl %eax, (0x2020202) + je .6 + ret +.6: jmp *0 +GLOBL ( _x86_Vertex3fv_end ) + + +/** + * Generic handler for 2 float format data. This can be used for + * TexCoord2f and possibly other functions. + */ + +GLOBL ( _x86_Attribute2f ) + movl $0x0, %edx + movl 4(%esp), %eax + movl 8(%esp), %ecx + movl %eax, (%edx) + movl %ecx, 4(%edx) + ret +GLOBL ( _x86_Attribute2f_end ) + + +/** + * Generic handler for 2 float vector format data. This can be used for + * TexCoord2fv and possibly other functions. + */ + +GLOBL( _x86_Attribute2fv) + movl 4(%esp), %eax /* load 'v' off stack */ + movl (%eax), %ecx /* load v[0] */ + movl 4(%eax), %eax /* load v[1] */ + movl %ecx, 0 /* store v[0] to current vertex */ + movl %eax, 4 /* store v[1] to current vertex */ + ret +GLOBL ( _x86_Attribute2fv_end ) + + +/** + * Generic handler for 3 float format data. This can be used for + * Normal3f, Color3f (when the color target is also float), or + * TexCoord3f. + */ + +GLOBL ( _x86_Attribute3f ) + movl 4(%esp), %ecx + movl 8(%esp), %edx + movl 12(%esp), %eax + movl %ecx, 0 + movl %edx, 4 + movl %eax, 8 + ret +GLOBL ( _x86_Attribute3f_end ) + +/** + * Generic handler for 3 float vector format data. This can be used for + * Normal3f, Color3f (when the color target is also float), or + * TexCoord3f. + */ + +GLOBL( _x86_Attribute3fv) + movl 4(%esp), %eax /* load 'v' off stack */ + movl (%eax), %ecx /* load v[0] */ + movl 4(%eax), %edx /* load v[1] */ + movl 8(%eax), %eax /* load v[2] */ + movl %ecx, 0 /* store v[0] to current vertex */ + movl %edx, 4 /* store v[1] to current vertex */ + movl %eax, 8 /* store v[2] to current vertex */ + ret +GLOBL ( _x86_Attribute3fv_end ) + + +/* + Color 4ubv_ub +*/ +GLOBL ( _x86_Color4ubv_ub ) + movl 4(%esp), %eax + movl $0x12345678, %edx + movl (%eax), %eax + movl %eax, (%edx) + ret +GLOBL ( _x86_Color4ubv_ub_end ) + +/* + Color 4ubv 4f +*/ +GLOBL ( _x86_Color4ubv_4f ) + push %ebx + movl $0, %edx + xor %eax, %eax + xor %ecx, %ecx + movl 8(%esp), %ebx + movl (%ebx), %ebx + mov %bl, %al + mov %bh, %cl + movl (%edx,%eax,4),%eax + movl (%edx,%ecx,4),%ecx + movl %eax, (0xdeadbeaf) + movl %ecx, (0xdeadbeaf) + xor %eax, %eax + xor %ecx, %ecx + shr $16, %ebx + mov %bl, %al + mov %bh, %cl + movl (%edx,%eax,4), %eax + movl (%edx,%ecx,4), %ecx + movl %eax, (0xdeadbeaf) + movl %ecx, (0xdeadbeaf) + pop %ebx + ret +GLOBL ( _x86_Color4ubv_4f_end ) + +/* + + Color4ub_ub +*/ +GLOBL( _x86_Color4ub_ub ) + push %ebx + movl 8(%esp), %eax + movl 12(%esp), %edx + movl 16(%esp), %ecx + movl 20(%esp), %ebx + mov %al, (0) + mov %dl, (0) + mov %cl, (0) + mov %bl, (0) + pop %ebx + ret +GLOBL( _x86_Color4ub_ub_end ) + + +/* + MultiTexCoord2fv st0/st1 +*/ +GLOBL( _x86_MultiTexCoord2fv ) + movl 4(%esp), %eax + movl 8(%esp), %ecx + and $1, %eax + movl (%ecx), %edx + shl $3, %eax + movl 4(%ecx), %ecx + movl %edx, 0xdeadbeef(%eax) + movl %ecx, 0xdeadbeef(%eax) + ret +GLOBL( _x86_MultiTexCoord2fv_end ) + +/* + MultiTexCoord2fv +*/ + +GLOBL( _x86_MultiTexCoord2fv_2 ) + movl 4(%esp,1), %eax + movl 8(%esp,1), %ecx + and $0x1, %eax + movl 0(,%eax,4), %edx + movl (%ecx), %eax + movl %eax, (%edx) + movl 4(%ecx), %eax + movl %eax, 4(%edx) + ret +GLOBL( _x86_MultiTexCoord2fv_2_end ) + +/* + MultiTexCoord2f st0/st1 +*/ +GLOBL( _x86_MultiTexCoord2f ) + movl 4(%esp), %eax + movl 8(%esp), %edx + movl 12(%esp), %ecx + and $1, %eax + shl $3, %eax + movl %edx, 0xdeadbeef(%eax) + movl %ecx, 0xdeadbeef(%eax) + ret +GLOBL( _x86_MultiTexCoord2f_end ) + +/* + MultiTexCoord2f +*/ +GLOBL( _x86_MultiTexCoord2f_2 ) + movl 4(%esp), %eax + movl 8(%esp), %edx + movl 12(%esp,1), %ecx + and $1,%eax + movl 0(,%eax,4), %eax + movl %edx, (%eax) + movl %ecx, 4(%eax) + ret +GLOBL( _x86_MultiTexCoord2f_2_end ) + +/** + * This can be used as a template for either Color3fv (when the color + * target is also a 3f) or Normal3fv. + */ + +GLOBL( _sse_Attribute3fv ) + movl 4(%esp), %eax + movlps (%eax), %xmm0 + movl 8(%eax), %eax + movlps %xmm0, 0 + movl %eax, 8 + ret +GLOBL( _sse_Attribute3fv_end ) + +/** + * This can be used as a template for either Color3f (when the color + * target is also a 3f) or Normal3f. + */ + +GLOBL( _sse_Attribute3f ) + movlps 4(%esp), %xmm0 + movl 12(%esp), %eax + movlps %xmm0, 0 + movl %eax, 8 + ret +GLOBL( _sse_Attribute3f_end ) + + +/** + * Generic handler for 2 float vector format data. This can be used for + * TexCoord2fv and possibly other functions. + */ + +GLOBL( _sse_Attribute2fv ) + movl 4(%esp), %eax + movlps (%eax), %xmm0 + movlps %xmm0, 0 + ret +GLOBL( _sse_Attribute2fv_end ) + + +/** + * Generic handler for 2 float format data. This can be used for + * TexCoord2f and possibly other functions. + */ + +GLOBL( _sse_Attribute2f ) + movlps 4(%esp), %xmm0 + movlps %xmm0, 0 + ret +GLOBL( _sse_Attribute2f_end ) + +/* + MultiTexCoord2fv st0/st1 +*/ +GLOBL( _sse_MultiTexCoord2fv ) + movl 4(%esp), %eax + movl 8(%esp), %ecx + and $1, %eax + movlps (%ecx), %xmm0 + movlps %xmm0, 0xdeadbeef(,%eax,8) + ret +GLOBL( _sse_MultiTexCoord2fv_end ) + +/* + MultiTexCoord2fv +*/ +GLOBL( _sse_MultiTexCoord2fv_2 ) + movl 4(%esp), %eax + movl 8(%esp), %ecx + and $0x1, %eax + movl 0(,%eax,4), %edx + movlps (%ecx), %xmm0 + movlps %xmm0, (%edx) + ret +GLOBL( _sse_MultiTexCoord2fv_2_end ) + +/* + MultiTexCoord2f st0/st1 +*/ +GLOBL( _sse_MultiTexCoord2f ) + movl 4(%esp), %eax + and $1, %eax + movlps 8(%esp), %xmm0 + movlps %xmm0, 0xdeadbeef(,%eax,8) + ret +GLOBL( _sse_MultiTexCoord2f_end ) + +/* + MultiTexCoord2f +*/ +GLOBL( _sse_MultiTexCoord2f_2 ) + movl 4(%esp), %eax + movlps 8(%esp), %xmm0 + and $1,%eax + movl 0(,%eax,4), %eax + movlps %xmm0, (%eax) + ret +GLOBL( _sse_MultiTexCoord2f_2_end ) |