ia-32_instruction-set-ref_a-m

And any serializing instructions such as the cpuid

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: E2[bit 26] = 0. Vol. 2 3-577 INSTRUCTION SET REFERENCE, A-M Virtual-8086 Mode Exceptions Same exceptions as in Real Address Mode #PF(fault-code) For a page fault. Compatibility Mode Exceptions Same exceptions as in Protected Mode. 64-Bit Mode Exceptions #SS(0) #GP(0) If a memory address referencing the SS segment is in a noncanonical form. If the memory address is in a non-canonical form. If memory operand is not aligned on a 16-byte boundary, regardless of segment. #PF(fault-code) #NM #XM #UD For a page fault. If CR0.TS[bit 3] = 1. If an unmasked SIMD floating-point exception and CR4.OSXMMEXCPT[bit 10] = 1. If an unmasked SIMD floating-point exception and CR4.OSXMMEXCPT[bit 10] = 0. If CR0.EM[bit 2] = 1. If CR4.OSFXSR[bit 9] = 0. If CPUID.01H:EDX.SSE2[bit 26] = 0. 3-578 Vol. 2 INSTRUCTION SET REFERENCE, A-M MINPS--Return Minimum Packed Single-Precision Floating-Point Values Opcode 0F 5D /r Instruction MINPS xmm1, xmm2/m128 64-Bit Mode Valid Compat/ Leg Mode Valid Description Return the minimum singleprecision floating-point values between xmm2/m128 and xmm1. Description Performs a SIMD compare of the packed single-precision floating-point values in the destination operand (first operand) and the source operand (second operand), and returns the minimum value for each pair of values to the destination operand. The source operand can be an XMM register or a 128-bit memory location. The destination operand is an XMM register. If the values being compared are both 0.0s (of either sign), the value in the second operand (source operand) is returned. If a value in the second operand is an SNaN, that SNaN is returned unchanged to the destination (that is, a QNaN version of the SNaN is not returned). If only one value is a NaN (SNaN or QNaN) for this instruction, the second operand (source operand), either a NaN or a valid floating-point value, is written to the result. If instead of this behavior, it is required that the NaN source operand (from either the first or second operand) be returned, the action of MINPS can be emulated using a sequence of instructions, such as, a comparison followed by AND, ANDN and OR. In 64-bit mode, use of the REX.R prefix permits this instruction to access additional registers (XMM8-XMM15). Operation IF ((DEST[31:0] = 0.0) and (SRC[31:0] = 0.0)) THEN SRC[31:0]; ELSE IF (DEST[31:0] = SNaN) THEN SRC[31:0]; FI; ELSE IF SRC[31:0] = SNaN) THEN SRC[31:0]; FI; ELSE IF (DEST[31:0] > SRC[31:0]) THEN DEST[31:0] ELSE SRC[31:0]; FI; FI; (* Repeat operation for 2nd and 3rd doublewords *); DEST[63:0] DEST[127:64] IF ((DEST127:96] = 0.0) and (SRC[127:96] = 0.0)) THEN SRC[127:96]; ELSE IF (DEST[127:96] = SNaN) THEN SRC[127:96]; FI; ELSE IF SRC[127:96] = SNaN) THEN SRC[127:96]; FI; ELSE IF (DEST[127:96] < SRC[127:96]) Vol. 2 3-579 INSTRUCTION SET REFERENCE, A-M THEN DEST[127:96] ELSE SRC[127:96]; FI; FI; Intel C/C++ Compiler Intrinsic Equivalent MINPS __m128d _mm_min_ps(__m128d a, __m128d b) SIMD Floating-Point Exceptions Invalid (including QNaN source operand), Denorm...
View Full Document

Ask a homework question - tutors are online